Daily Papers

Word error rate (WER) is the dominant metric for automatic speech recognition, yet it cannot detect a systematic failure mode: models that produce fluent output in the wrong writing system. We define Script Fidelity Rate (SFR), the fraction of hypothesis characters in the target script block, computable without reference transcriptions, and report the first systematic measurement of script collapse across six languages spanning four writing systems (Pashto, Urdu, Hindi, Bengali, Malayalam, Somali) and nine ASR models on FLEURS test sets. Across 53 evaluated model-language pairs, 18 (34%; 95% Wilson CI: 23-47%) exhibit script collapse (SFR < 10%); MMS-1B and SeamlessM4T-v2 maintain SFR above 99% on every language evaluated, confirming that SFR correctly identifies high fidelity where it is present. We identify three distinct collapse patterns: Latin phonetic substitution (smaller Whisper on Indic languages), Arabic substitution for Somali's Latin-script orthography, and Devanagari substitution where larger Whisper models treat all Indic audio as Hindi, a failure present even in Whisper large-v3.

Large language models (LLMs) can generate fluent text, but their ability to replicate the distinctive style of a specific human author remains unclear. We present a fast, training-free framework for authorship verification and style imitation analysis. The method integrates TF-IDF character n-grams with transformer embeddings and classifies text pairs through empirical distance distributions, eliminating the need for supervised training or threshold tuning. It achieves 97.5\% accuracy on academic essays and 94.5\% in cross-domain evaluation, while reducing training time by 91.8\% and memory usage by 59\% relative to parameter-based baselines. Using this framework, we evaluate five LLMs from three separate families (Llama, Qwen, Mixtral) across four prompting strategies - zero-shot, one-shot, few-shot, and text completion. Results show that the prompting strategy has a more substantial influence on style fidelity than model size: few-shot prompting yields up to 23.5x higher style-matching accuracy than zero-shot, and completion prompting reaches 99.9\% agreement with the original author's style. Crucially, high-fidelity imitation does not imply human-like unpredictability - human essays average a perplexity of 29.5, whereas matched LLM outputs average only 15.2. These findings demonstrate that stylistic fidelity and statistical detectability are separable, establishing a reproducible basis for future work in authorship modeling, detection, and identity-conditioned generation.

Practitioners make three prompt-design decisions with almost no controlled evidence behind them: how to format instructions and context (markdown, plain text, prose, or tabular), how many simultaneous instructions a system prompt can carry before compliance degrades, and how much context a model can hold before recall and honesty degrade. We report two controlled experiments crossing all three factors on one held, contamination-free synthetic corpus (the "Book of Veyra," 8,780 uniquely-named entities, deterministically regenerable from a fixed seed), evaluated across five models. Experiment 1 (960 calls/model) measures instruction-following decay as rule count N grows from 10 to 160, crossed with four formats and system-prompt vs. user-turn placement. Perfect-response rate collapses to zero by N=80 for every model, format, and placement. Placement produces effects at least as large as format at N=160 in most models, but the direction is model-specific. No model shows a reliable markdown advantage; one 35B model favors plain text instead. Experiment 2 (5,520 calls/model) measures recall accuracy, false-premise sycophancy, and absent-fact fabrication across a 2k-to-512k-token context ladder in the same four formats. Recall stays near ceiling through 64-128k tokens, then degrades sharply and format-dependently: one model's accuracy spread reaches 48 points at 128k tokens. Fabrication never occurs (0/5,760 probes), and sycophancy stays negligible (<=8.3%). What rises sharply near each model's context ceiling is outright refusal to answer (0% to 79-90%), distinct from sycophancy or fabrication. Neither pre-registered format ordering holds, and token overhead (+22% to +37% over plain text) further changes which format is preferable where accuracy spread is genuine. We release the full harness, corpus generator, and raw results (VeyraBench): https://github.com/iNetanel/veyrabench

Automatic Speech Recognition (ASR) systems predominantly cater to monolingual inputs and struggle with the complexity introduced by mixed language audio. In this paper, we present a novel Multi-Agent Data Generation Framework (MADGF) to address this challenge. We finetune the open-source multilingual ASR model, Whisper, utilizing our generated Mixed Cantonese and English (MCE) audio dataset, Which achieved an impressive Mix Error Rate (MER) of 14.28%, 35.13% lower than the original model. Meanwhile, single language recognition ability is not affected, 12.6% Character Error Rate (CER) in Common voice zh-HK, 14.8% Word Error Rate (WER) in Common voice en. However, these metrics do not encompass all aspects critical to the ASR systems. Hence, we propose a novel evaluation metric called Fidelity to the Original Audio, Accuracy, and Latency (FAL).

Deployed language models must produce outputs that are both correct and format-compliant. We study this structured-output reliability gap using two mathematical benchmarks -- GSM8K and MATH -- as a controlled testbed: ground truth is unambiguous and the output contract is strict (JSON with required fields). We evaluate three 7-9B models under five prompting strategies and report output accuracy -- the joint event of mathematical correctness and valid JSON structure -- as the primary metric. A systematic format failure emerges: NAIVE prompting (no system prompt) achieves up to 85% task accuracy on GSM8K but 0% output accuracy across all models and datasets. REFERENCE prompting (a minimal hand-written JSON format prompt) fares little better, yielding 0% output accuracy for two of four models tested. Constrained decoding enforces syntactic validity but incurs 3.6x-8.2x latency overhead and in several settings degrades task performance substantially. To overcome this limitation, we developed AloLab, an iterative system-prompt optimizer (meta-agent: Claude Sonnet 4.5) requiring only black-box API access to the target model; it reaches 84-87% output accuracy on GSM8K and 34-40% on MATH across five independent runs per model, with 29/30 paired McNemar comparisons against the best static prompt significant at p < 0.05, at near-NAIVE inference latency and without model fine-tuning. The same format failure extends to GPT-4o (OpenAI, 2024), a proprietary closed-source model: REFERENCE achieves 0% output accuracy due to systematic markdown-fence wrapping, while AloLab reaches 95.2% [94.8, 95.6]. An ablation replacing the Sonnet 4.5 meta-agent with Claude 3 Haiku reduces mean output accuracy to 61.0% and increases run-to-run standard deviation from <1 pp to 21.8 pp, confirming that meta-agent capability is a primary driver of optimization quality.

The performance of Language Models (LMs) on low-resource, morphologically rich languages like Sinhala remains largely unexplored, particularly regarding script variation in digital communication. Sinhala exhibits script duality, with Unicode used in formal contexts and Romanized text dominating social media, while mixed-script usage is common in practice. This paper benchmarks 24 open-source LMs on Unicode, Romanized and mixed-script Sinhala using perplexity evaluation across diverse text sources. Results reveal substantial script sensitivity, with median performance degradation exceeding 300 times from Unicode to Romanized text. Critically, model size shows no correlation with script-handling competence, as smaller models often outperform architectures 28 times larger. Unicode performance strongly predicts mixed-script robustness but not Romanized capability, demonstrating that single-script evaluation substantially underestimates real-world deployment challenges. These findings establish baseline LM capabilities for Sinhala and provide practical guidance for model selection in multi-script low-resource environments.

The instruction-following ability of Large Language Models (LLMs) has cultivated a class of LLM-based systems capable of approaching complex tasks such as making edits to large code repositories. Due to the high sensitivity and unpredictability of LLM behavior in response to changes in prompting, robust evaluation tools are needed to drive future iteration of these systems. We propose RES-Q, a natural language instruction-based benchmark for evaluating Repository Editing Systems, which consists of 100 repository editing tasks derived from real GitHub commits. Given an edit instruction and a code repository, RES-Q evaluates an LLM system's ability to gather information and construct an edit that satisfies the criteria set by the instruction. We argue that evaluating LLMs in this way addresses issues with traditional benchmarks and provides a more holistic assessment of a model's abilities. We evaluate various state-of-the-art LLMs as language agents in a repository-editing system built on Qurrent OS, our language agent development software. Despite their 1% pass@1 performance difference on HumanEval, we find Claude Sonnet 3.5 outperforms GPT-4o by 12% pass@1 on RES-Q, indicating RES-Q's capacity to differentiate model capability as traditional benchmarks approach saturation. We further investigate token efficiency, performance relationships with existing benchmarks, and interesting disparities between closed and open-source LLMs. Code and dataset are available at https://github.com/Qurrent-AI/RES-Q.

Program synthesis has been long studied with recent approaches focused on directly using the power of Large Language Models (LLMs) to generate code. Programming benchmarks, with curated synthesis problems and test-cases, are used to measure the performance of various LLMs on code synthesis. However, these test-cases can be limited in both quantity and quality for fully assessing the functional correctness of the generated code. Such limitation in the existing benchmarks begs the following question: In the era of LLMs, is the code generated really correct? To answer this, we propose EvalPlus -- a code synthesis evaluation framework to rigorously benchmark the functional correctness of LLM-synthesized code. EvalPlus augments a given evaluation dataset with large amounts of test-cases newly produced by an automatic test input generator, powered by both LLM- and mutation-based strategies. While EvalPlus is general, we extend the test-cases of the popular HumanEval benchmark by 80x to build HumanEval+. Our extensive evaluation across 26 popular LLMs (e.g., GPT-4 and ChatGPT) demonstrates that HumanEval+ is able to catch significant amounts of previously undetected wrong code synthesized by LLMs, reducing the pass@k by up-to 19.3-28.9%. We also surprisingly found that test insufficiency can lead to mis-ranking. For example, both WizardCoder-CodeLlama and Phind-CodeLlama now outperform ChatGPT on HumanEval+, while none of them could on HumanEval. Our work not only indicates that prior popular code synthesis evaluation results do not accurately reflect the true performance of LLMs for code synthesis, but also opens up a new direction to improve such programming benchmarks through automated testing. We have open-sourced our tools, enhanced datasets as well as all LLM-generated code at https://github.com/evalplus/evalplus to facilitate and accelerate future LLM-for-code research.

Automatic speech recognition (ASR) in non-English clinical settings is challenged by multiscript variability, where the same term may appear in multiple valid orthographic forms. Conventional string-matching evaluation metrics often underestimate ASR performance by treating orthographic variants as errors. To address this issue, we introduce MultiClin, a clinical ASR benchmark designed to evaluate robustness to multiscript variability. Experiments across diverse ASR models show that multiscript-aware evaluation provides a fairer assessment of recognition quality than conventional single-reference evaluation. We further investigate the impact of script consistency during training and find that inconsistent script mappings increase orthographic uncertainty and hinder model convergence, with a balanced 50% mapping ratio producing the highest entropy. In contrast, script unification consistently yields the best ASR performance. Our dataset and code are publicly available at: https://github.com/aitrics-ronaldo/Interspeech_MultiClin.

Current coding-agent benchmarks usually pro- vide the full task specification upfront. Real research coding often does not: the intended system is progressively disclosed through in- teraction, requiring the agent to track durable design commitments across a long session. We introduce a benchmark for this setting and study faithfulne Ss Loss U nder eM ergent s Pecification (SLUMP), defined as the reduc- tion in final implementation faithfulness un- der emergent specification relative to a single- shot specification control. The benchmark con- tains 20 recent ML papers (10 ICML 2025, 10 NeurIPS 2025), 371 atomic verifiable compo- nents, and interaction scripts of approximately 60 coding requests that progressively disclose the target design without revealing the paper itself. Final repositories are scored with a five-level component-faithfulness rubric and accompanied by an exposure audit to verify that scored components are recoverable from the visible interaction. Evaluated on Claude Code and Codex, the single-shot specification control achieves higher overall implementation fidelity on 16/20 and 14/20 papers, respectively. Structural integration degrades under emergent specification on both platforms, while seman- tic faithfulness loss is substantial on Claude Code and small on Codex. As a mitigation case study, we introduce ProjectGuard, an exter- nal project-state layer for specification tracking. On Claude Code, ProjectGuard recovers 90% of the faithfulness gap, increases fully faith- ful components from 118 to 181, and reduces severe failures from 72 to 49. These results identify specification tracking as a distinct eval- uation target for long-horizon coding agents.

AI-generated text is proliferating across domains, from creative writing and journalism to marketing content and scientific articles. Models can follow user-provided instructions to generate coherent and grammatically correct outputs but in this work, we study a more fundamental question: how do we evaluate and improve the writing quality of AI-generated text? Writing quality assessment has received less attention from the community, in part because it is fundamentally subjective and requires expertise. We first introduce the Writing Quality Benchmark (WQ) by consolidating five writing-preference datasets into 4,729 writing quality judgments. Our experiments show that most of the competitive baselines, including state-of-the-art LLMs that excel at reasoning tasks, barely outperform random baselines on WQ. We then train specialized Writing Quality Reward Models (WQRM) of various sizes for writing quality assessment that demonstrate strong generalization on four out-of-distribution test sets and 74% accuracy on the WQ benchmark. To further show WQRM's practical benefits during inference, we leverage additional test-time compute to generate and rank multiple candidate revisions, allowing us to select higher-quality outputs from an initial draft. Human evaluation with 9 experienced writers confirm that WQRM-based selection produces writing samples preferred by experts 66% overall, and 72.2% when the reward gap is larger than 1 point. We release our datasets and models to encourage community engagement with writing quality assessment and development of AI writing systems better aligned with human preferences.

The integration of AI-powered coding agents into Continuous Integration/Continuous Delivery (CI/CD) pipelines has fundamentally altered how software verification is conducted. While these agents successfully automate the test generation, current evaluation benchmarks (e.g., SWE-bench) largely focus on pass-rates rather than the intrinsic quality of the generated tests. This raises the possibility of "stealth technical debt", in which test suites pass execution but do not offer comprehensive coverage or semantic value. We address this methodological gap through a large-scale, empirical comparison of 204,673 test artifacts which comprises of 24,941 human-authored files and 179,732 agent-generated files; sourced from the AIDev dataset. Using the Abstract Syntax Tree (AST) parsing with Python's naive ast module, we implemented a "white-box" static analysis framework to evaluate three quality dimensions: Assertion Strength (RQ1), Edge-Case Coverage (RQ2), and Flakiness Potential (RQ3). Our results present a nuanced inversion of traditional assumptions. AI agents performed better than humans in Edge-Case Coverage, with almost twice the variety of boundary checks (Variety Score: 0.62 vs 0.32) and a higher frequency of null-safety testing (13.40% vs. 8.3%), even though human developers had a slight advantage in Assertion Strength (88.1% strong assertions vs. 85.37% for agents). But this thoroughness comes at a price: due mostly to their reliance on file I/O and non-deterministic logic, agent-generated tests exhibited a higher risk of flakiness (Candidate Rate: 0.41 vs. 0.30). These findings suggest that while AI agents excel at rigorous boundary testing, they lack the "environmental awareness" needed to write stable, hermetic tests.

Agent Skills package procedural instructions and checks for use by general-purpose agents, but loading a skill does not guarantee that every requirement remains active throughout a long tool-using trajectory. We study this problem in a production-derived, white-box code-audit workflow. Holding the task and 24 artifact checks fixed, we vary the surrounding context and classify where failures first become visible: lost requirements, editing drift, failed checking, or non-agent evaluator/runtime failures. Codex with gpt-5.4-mini passes 8/10 runs in a 10,991-character clean context but only 3/10 in both a 299,140-character relevant context and an equal-length irrelevant context. This 50-percentage-point difference is large but remains trend-level under two-sided Fisher tests (p = 0.0698). Requirement coverage nevertheless stays above 92% in both long conditions, showing that a few omissions can invalidate an otherwise complete artifact. A second task passes all clean and long runs, so the evidence does not support a universal context-length threshold. A detailed external checklist passes 10/10 runs, compared with 5/10 for a generic self-check (p = 0.0325). Coding-agent scaffolds may help by selecting a smaller working set, but they do not eliminate failures. We do not introduce context rot or a new general monitoring method; we provide a bounded failure classification and empirical case study for white-box code auditing.

Wu et al. (2026) showed that most frontier large language models (LLMs) recommend a sponsored, roughly twice-as-expensive flight when their system prompt contains a soft sponsorship cue. We reproduce their evaluation on ten open-weight chat models plus the two of their twenty-three models that are still reachable today (gpt-3.5-turbo, gpt-4o). All reported rates in this paper are produced under the same judge the original paper used (gpt-4o); we additionally store every label under an open-weight (gpt-oss-120b) and a smaller proprietary (gpt-4o-mini) judge for an ablation. Three findings emerge. First, a prose description of an LLM evaluation pipeline is not, on its own, sufficient for accurate reproduction: we surfaced three silent implementation failures that each shifted a reported rate by tens of percentage points. Second, the central claims do generalise - the gpt-3.5-turbo logistic-regression intercept of alpha = 0.81 is within four points of the original alpha = 0.86, and 200 of 200 trials on gpt-3.5-turbo and gpt-4o promote a payday lender to a financially distressed user. Third, a thirty-token user prompt that asks the assistant for a neutral comparison table first cuts sponsored recommendation from 46.9% to 1.0% averaged across our ten open-source models, and from 53.0% to 0% averaged across the two OpenAI models. AI literacy and price-comparison portals are likely market-level mitigations; the harmful-product cell is bounded by neither. Raw data, labels and analysis scripts are at https://github.com/akmaier/Paper-LLM-Ads .

Language models in production do not write prose. They fill forms: JSON fields, function arguments, extraction templates. We show that the form itself causes hallucination. We ask thirteen models the same question about the same input and change only the answer format. The inputs are built so the question cannot be answered: a viral post showing 12,400 likes but no visible replies, a support ticket whose call was never transcribed. In free text, GPT-5.5 answers honestly. It says there is no reply data, 98% of the time. Given a required JSON field for sentiment, the same model invents an answer 40 times out of 40. It fabricates the mood of crowds it never saw and quotes customers it never heard. The pattern holds with force. Required fields drive fabrication to 100% in ten of thirteen models. An explicit "insufficient evidence" option rescues only the frontier: all nine open-weight models ignore it. A direct instruction, do not infer sentiment, is overridden by the schema in four of six models. Resistance does not come with scale: within a single model family, the smallest model refuses, the mid-sized model fabricates, the largest refuses again. Honesty under format pressure is a training outcome that no one is measuring. The fabrication hides exactly where hedging is impossible: in required enums and minimum-count arrays, fields where no disclaimer fits. We release PhantomFill, a benchmark with deterministic scoring and two reportable numbers: the Coerced Fabrication Rate and the Escape Utilization Rate. The fix we test is one line of schema. The failure we measure is everywhere.

We present an empirical evaluation of various outputs generated by nine of the most widely-available large language models (LLMs). Our analysis is done with off-the-shelf, readily-available tools. We find a correlation between percentage of memorized text, percentage of unique text, and overall output quality, when measured with respect to output pathologies such as counterfactual and logically-flawed statements, and general failures like not staying on topic. Overall, 80.0% of the outputs evaluated contained memorized data, but outputs containing the most memorized content were also more likely to be considered of high quality. We discuss and evaluate mitigation strategies, showing that, in the models evaluated, the rate of memorized text being output is reduced. We conclude with a discussion on potential implications around what it means to learn, to memorize, and to evaluate quality text.

Coding agents are now commonly evaluated on the SWE-bench family of benchmarks, whose tasks are built from curated GitHub issues: long, structured, and information-rich. Real user requests, however, are typically far shorter and less structured. To characterize this gap, we define a six-category information taxonomy and four dimensions of linguistic style, and apply them to real user prompts from SWE-chat and problem statements from SWE-bench Verified and Pro. We find that requests carrying only a problem statement, alone or with limited additional context, account for 88% of real prompts but just 7% of benchmark problems. Furthermore, 87% of real prompts are casually written whereas 94% of benchmark problems are formal. Guided by these observations, we introduce RealSWE, 381 multi-variant task families derived from SWE-bench Verified and Pro. Variants within each family share the same underlying task and gold patch while differing only in information composition and linguistic style. Evaluating seven contemporary LLMs with RealSWE, we find that i) realistic inputs reduce resolution rates by 6.4 pp on average and can change model rankings. Controlled analysis further shows that ii) including Desired Behavior and Motivation significantly affects performance, whereas Environment Information and Reproduction Steps merely add tokens without measurable benefit; iii) linguistic style has only small, model-dependent effects. These findings provide actionable guidance for users and agents: explicitly stating the desired behavior and motivation, which most real prompts omit, substantially improves the LLM's software engineering performance.

Evaluating ASR systems for Indian languages is challenging due to spelling variations, suffix splitting flexibility, and non-standard spellings in code-mixed words. Traditional Word Error Rate (WER) often presents a bleaker picture of system performance than what human users perceive. Better aligning evaluation with real-world performance requires capturing permissible orthographic variations, which is extremely challenging for under-resourced Indian languages. Leveraging recent advances in LLMs, we propose a framework for creating benchmarks that capture permissible variations. Through extensive experiments, we demonstrate that OIWER, by accounting for orthographic variations, reduces pessimistic error rates (an average improvement of 6.3 points), narrows inflated model gaps (e.g., Gemini-Canary performance difference drops from 18.1 to 11.5 points), and aligns more closely with human perception than prior methods like WER-SN by 4.9 points.

As large language models increasingly participate in scientific evaluation, we investigate a potential form of reward hacking: how rhetorical choices shape AI-review judgments when reported scientific content is preserved and how these effects vary across evaluation conditions. We construct a controlled corpus of 4,200 full-paper manuscripts derived from 120 anonymized ICLR 2026 submissions. Two LLM rewriters transform six rhetorical dimensions in opposing directions, and five LLM reviewers evaluate the resulting manuscripts under standard and strict protocols. We also test joint, recursive, and reviewer-guided rewriting. Our results show that rhetorical sensitivity is structured rather than uniform. Evidence framing and novelty stance produce the largest positive-negative contrasts in overall assessment, with scope framing forming a weaker second tier; the remaining dimensions have smaller or less stable effects. This hierarchy persists across human-assessed quality levels, but score movement depends strongly on the AI reviewer's original score: lower scores tend to rise, higher scores tend to fall, and directional contrasts are clearest in the middle ranges. More elaborate workflows do not reliably yield larger gains. Joint rewriting is strongly rewriter-dependent, reviewer guidance does not consistently outperform an unguided second pass, and repeated rewriting yields diminishing, configuration-dependent returns. Across conditions, the rewriter primarily determines the separation between opposing variants, whereas the reviewer determines the magnitude and sign of their score effects. Strict review lowers mean OA by 1.36 points without consistently changing rhetorical sensitivity. These findings identify when rhetorical presentation influences AI scientific review and motivate evaluation systems robust to content-preserving variation in scientific writing.

We introduce Codex, a GPT language model fine-tuned on publicly available code from GitHub, and study its Python code-writing capabilities. A distinct production version of Codex powers GitHub Copilot. On HumanEval, a new evaluation set we release to measure functional correctness for synthesizing programs from docstrings, our model solves 28.8% of the problems, while GPT-3 solves 0% and GPT-J solves 11.4%. Furthermore, we find that repeated sampling from the model is a surprisingly effective strategy for producing working solutions to difficult prompts. Using this method, we solve 70.2% of our problems with 100 samples per problem. Careful investigation of our model reveals its limitations, including difficulty with docstrings describing long chains of operations and with binding operations to variables. Finally, we discuss the potential broader impacts of deploying powerful code generation technologies, covering safety, security, and economics.

Code benchmarks such as HumanEval are widely adopted to evaluate Large Language Models' (LLMs) coding capabilities. However, there is an unignorable programming language bias in existing code benchmarks -- over 95% code generation benchmarks are dominated by Python, leaving the LLMs' capabilities in other programming languages such as Java and C/C++ unknown. Moreover, coding task bias is also crucial. Most benchmarks focus on code generation capability, while benchmarks for code reasoning (given input, reasoning output; and given output, reasoning input), an essential coding capability, are insufficient. Yet, constructing multi-lingual benchmarks can be expensive and labor-intensive, and codes in contest websites such as Leetcode suffer from data contamination during training. To fill this gap, we propose CRUXEVAL-X, a multi-lingual code reasoning benchmark that contains 19 programming languages. It comprises at least 600 subjects for each language, along with 19K content-consistent tests in total. In particular, the construction pipeline of CRUXEVAL-X works in a fully automated and test-guided manner, which iteratively generates and repairs based on execution feedback. Also, to cross language barriers (e.g., dynamic/static type systems in Python/C++), we formulated various transition rules between language pairs to facilitate translation. Our intensive evaluation of 24 representative LLMs reveals the correlation between language pairs. For example, TypeScript and JavaScript show a significant positive correlation, while Racket has less correlation with other languages. More interestingly, even a model trained solely on Python can achieve at most 34.4% Pass@1 in other languages, revealing the cross-language generalization of LLMs.

Large language models (LLMs) are increasingly used to automate data-processing workflows, yet coding agents typically produce scripts that are not automatically materialized as persistent, editable platform artifacts. We call this disconnect the NL2Pipeline gap. To bridge it, we introduce DataFlow-Harness, a platform that guides an LLM agent to construct platform-native directed acyclic graphs (DAGs) through typed, incremental mutations rather than free-form scripts. The platform combines DataFlow-Skills for procedural guidance, a Model Context Protocol (MCP) layer that exposes the live operator registry and current pipeline state, and DataFlow-WebUI, which synchronizes conversational authoring with a visual DAG editor. On a 12-task data-engineering benchmark, DataFlow-Harness achieves a 93.3\% observed end-to-end pass rate. Relative to Vanilla Claude Code, it reduces measured monetary cost by 72.5\% and generation latency by 49.9\%; its observed pass rate is within 0.9 percentage points of the Context-Aware Claude Code baseline while its cost is 42.8\% lower. Per-task analysis indicates that Skills are most useful when construction depends on implicit procedural knowledge. These results show that live platform grounding can produce persistent, editable workflow artifacts with an observed reliability close to script-generation baselines and with lower measured construction cost and latency.

Code benchmarks such as HumanEval are widely adopted to evaluate the capabilities of Large Language Models (LLMs), providing insights into their strengths and weaknesses. However, current benchmarks primarily exercise LLMs' capability on common coding tasks (e.g., bubble sort, greatest common divisor), leaving domain-specific coding tasks (e.g., computation, system, cryptography) unexplored. To fill this gap, we propose a multi-domain code benchmark, DOMAINEVAL, designed to evaluate LLMs' coding capabilities thoroughly. Our pipeline works in a fully automated manner, enabling a push-bottom construction from code repositories into formatted subjects under study. Interesting findings are observed by evaluating 12 representative LLMs against DOMAINEVAL. We notice that LLMs are generally good at computation tasks while falling short on cryptography and system coding tasks. The performance gap can be as much as 68.94% (80.94% - 12.0%) in some LLMs. We also observe that generating more samples can increase the overall performance of LLMs, while the domain bias may even increase. The contributions of this study include a code generation benchmark dataset DOMAINEVAL, encompassing six popular domains, a fully automated pipeline for constructing code benchmarks, and an identification of the limitations of LLMs in code generation tasks based on their performance on DOMAINEVAL, providing directions for future research improvements. The leaderboard is available at https://domaineval.github.io/.

As LLM-based agents are deployed in production systems, understanding their behavioral consistency (whether they produce similar action sequences when given identical tasks) becomes critical for reliability. We study consistency in the context of SWE-bench, a challenging software engineering benchmark requiring complex, multi-step reasoning. Comparing Claude~4.5~Sonnet, GPT-5, and Llama-3.1-70B across 50 runs each (10 tasks times 5 runs), we find that across models, higher consistency aligns with higher accuracy: Claude achieves the lowest variance (CV: 15.2\%) and highest accuracy (58\%), GPT-5 is intermediate (CV: 32.2\%, accuracy: 32\%), and Llama shows the highest variance (CV: 47.0\%) with lowest accuracy (4\%). However, within a model, consistency can amplify both correct and incorrect interpretations. Our analysis reveals a critical nuance: consistency amplifies outcomes rather than guaranteeing correctness. 71\% of Claude's failures stem from "consistent wrong interpretation": making the same incorrect assumption across all runs. Interestingly, GPT-5 achieves similar early strategic agreement as Claude (diverging at step 3.4 vs.\ 3.2) but exhibits 2.1times higher variance, suggesting that divergence timing alone does not determine consistency. These findings suggest that for production deployment, interpretation accuracy matters more than execution consistency, with implications for agent evaluation and training.

Academic citations are widely used for evaluating research and tracing knowledge flows. Such uses typically rely on raw citation counts and neglect variability in citation types. In particular, citations can vary in their fidelity as original knowledge from cited studies may be paraphrased, summarized, or reinterpreted, possibly wrongly, leading to variation in how much information changes from cited to citing paper. In this study, we introduce a computational pipeline to quantify citation fidelity at scale. Using full texts of papers, the pipeline identifies citations in citing papers and the corresponding claims in cited papers, and applies supervised models to measure fidelity at the sentence level. Analyzing a large-scale multi-disciplinary dataset of approximately 13 million citation sentence pairs, we find that citation fidelity is higher when authors cite papers that are 1) more recent and intellectually close, 2) more accessible, and 3) the first author has a lower H-index and the author team is medium-sized. Using a quasi-experiment, we establish the "telephone effect" - when citing papers have low fidelity to the original claim, future papers that cite the citing paper and the original have lower fidelity to the original. Our work reveals systematic differences in citation fidelity, underscoring the limitations of analyses that rely on citation quantity alone and the potential for distortion of evidence.

Agent skills today are hand-crafted, generated one-shot, or evolved through loosely controlled self-revision, none of which behaves like a deep-learning optimizer for the skill, and none of which reliably improves over its starting point under feedback. We argue the skill should instead be trained as the external state of a frozen agent, with the same discipline that makes weight-space optimization reproducible. SkillOpt is, to our knowledge, the first systematic controllable text-space optimizer for agent skills: a separate optimizer model turns scored rollouts into bounded add/delete/replace edits on a single skill document, and an edit is accepted only when it strictly improves a held-out validation score. A textual learning-rate budget, rejected-edit buffer, and epoch-wise slow/meta update make skill training stable while adding zero inference-time model calls at deployment. Across six benchmarks, seven target models, and three execution harnesses (direct chat, Codex, Claude Code), SkillOpt is best or tied on all 52 evaluated (model, benchmark, harness) cells and beats every per-cell competitor among human, one-shot LLM, Trace2Skill, TextGrad, GEPA, and EvoSkill skills. On GPT-5.5 it lifts the average no-skill accuracy by +23.5 points in direct chat, by +24.8 inside the Codex agentic loop, and by +19.1 inside Claude Code. Transfer experiments further show that optimized skill artifacts retain value when moved across model scales, between Codex and Claude Code execution environments, and to a nearby math benchmark without further optimization.

Current preference learning methods achieve high accuracy on standard benchmarks but exhibit significant performance degradation when objective quality signals are removed. We introduce WritingPreferenceBench, a dataset of 1,800 human-annotated preference pairs (1,200 English, 600 Chinese) across 8 creative writing genres, where responses are matched for objective correctness, factual accuracy, and length. On this benchmark, sequence-based reward models--the standard architecture for RLHF--achieve only 52.7% mean accuracy, while zero-shot language model judges perform at 53.9%. In contrast, generative reward models that produce explicit reasoning chains achieve 81.8% accuracy. We observe high within-model variance across genres: individual models range from 18.2% to 81.8% accuracy across different writing categories, with standard deviations averaging 10.1%. This variance persists regardless of model scale, with 27B parameter models showing no consistent improvement over 8B variants. Our results suggest that current RLHF methods primarily learn to detect objective errors rather than capture subjective quality preferences (e.g., creativity, stylistic flair, and emotional resonance), and that successful preference modeling may require intermediate reasoning representations rather than direct classification.

Corruption studies, the primary tool for evaluating chain-of-thought (CoT) faithfulness, identify which chain positions are "computationally important" by measuring accuracy when steps are replaced with errors. We identify a systematic confound: for chains with explicit terminal answer statements, the dominant format in standard benchmarks, corruption studies detect where the answer text appears, not where computation occurs. A within-dataset format ablation provides the key evidence: on standard GSM8K chains ending with "the answer is X," removing only the answer statement, preserving all reasoning, collapses suffix sensitivity ~19x at 3B (N=300, p=0.022). Conflicting-answer experiments quantify the causal mechanism: at 7B, CC accuracy drops to near-zero (<=0.02) across five architecture families; the followed-wrong rate spans 0.63-1.00 at 3B-7B and attenuates at larger scales (0.300 at Phi-4-14B, ~0.01 at 32B). A within-stable 7B replication (9.3x attenuation, N=76, p=7.8e-3; Qwen3-8B N=299, p=0.004) provides converging evidence, and the pattern replicates on MATH (DeepSeek-R1-7B: 10.9x suffix-survival recovery). On chains without answer suffixes the same protocol identifies the prefix as load-bearing (Delta=-0.77, p<10^-12). Generation-time probes confirm a dissociation: the answer is not early-determined during generation (early commitment <5%), yet at consumption time model outputs systematically follow the explicit answer text. The format-determination effect persists through 14B (8.5x ratio, p=0.001) and converges toward zero at 32B. We propose a three-prerequisite protocol (question-only control, format characterization, all-position sweep) as a minimum standard for corruption-based faithfulness studies.

The application of large language models (LLMs) in the field of coding is evolving rapidly: from code assistants, to autonomous coding agents, and then to generating complete projects through natural language. Early LLM code benchmarks primarily focused on code generation accuracy, but these benchmarks have gradually become saturated. Benchmark saturation weakens their guiding role for LLMs. For example, HumanEval Pass@1 has reached 99.4% and MBPP 94.2%. Among various attempts to address benchmark saturation, approaches based on software engineering have stood out, but the saturation of existing software engineering benchmarks is rapidly increasing. To address this, we propose a new benchmark, Web-Bench, which contains 50 projects, each consisting of 20 tasks with sequential dependencies. The tasks implement project features in sequence, simulating real-world human development workflows. When designing Web-Bench, we aim to cover the foundational elements of Web development: Web Standards and Web Frameworks. Given the scale and complexity of these projects, which were designed by engineers with 5 to 10 years of experience, each presents a significant challenge. On average, a single project takes 4 to 8 hours for a senior engineer to complete. On our given benchmark agent (Web-Agent), SOTA (Claude 3.7 Sonnet) achieves only 25.1% Pass@1, significantly lower (better) than SWE-Bench's Verified (65.4%) and Full (33.8%) scores. Finally, we discuss that in any development field, Standards and Frameworks represent foundational knowledge and efficiency tools, respectively, and LLMs require optimization tailored to them.

Large language model (LLM) agents are increasingly expected to assist users in completing tasks. However, existing benchmarks provide limited support for evaluating whether agents can carry out office-suite workflows at a reasonable cost. We introduce OmegaUse-OfficeVal, a benchmark for evaluating LLM agents on long-horizon office-suite tasks with task-level economic grounding. The benchmark comprises 100 tasks derived from office-suite requests proposed by practitioners and adapted through a privacy-preserving process. On average, these tasks require 2.32 hours of human labor to complete. An important feature of the benchmark is that each task is paired with two economic signals: human labor time and task price proxy. These signals enable direct comparisons between human costs and LLM inference costs, as well as value-weighted evaluation. To support stable evaluation, we develop code-based verifiers from fine-grained rubrics. We evaluate several frontier LLMs together with a human baseline. Although all evaluated LLMs are substantially cheaper and faster than human workers, they have not yet approached human-level deliverable quality. The code and dataset are fully open-sourced, and more information is available on our project website: https://omegause-officeval.github.io.

Capability evaluation of large language models (LLMs) is increasingly shadowed by rising concerns of data contamination that cast doubts on whether static benchmarks measure genuine reasoning or mere memorization. We present an empirical study using an infinitely scalable framework to synthesize research-level QA directly from arXiv papers, harnessing the natural temporal structure of research publications where performance decay after knowledge cutoffs may indicate potential contamination. We evaluated 4 frontier model represented by 2 models of different knowledge cutoff dates per family on 1,643 multi-step reasoning questions synthesized from 20,277 arXiv papers stratified over 26 months, covering at least 6 months before and after all cutoff dates. Our results consistently showed a lack of significant performance decay near knowledge cutoff dates for models of various sizes, developers, and release dates. We further performed a comparative analysis with previous longitudinal studies that reported significant post-cutoff performance decay using directly retrieved questions based on public data. we hypothesize that the multi-step reasoning required by our synthesis pipeline offered additional complexity that goes deeper than shallow memorization, which effectively serves a mitigation strategy against benchmark contamination. We fully open source our code and dataset to aid reproducibility and advocate for a paradigm shift that prioritize reasoning-driven synthesis to construct benchmarks over simply collecting newly released questions periodically.

This study investigates the consistency of feedback ratings generated by OpenAI's GPT-4, a state-of-the-art artificial intelligence language model, across multiple iterations, time spans and stylistic variations. The model rated responses to tasks within the Higher Education (HE) subject domain of macroeconomics in terms of their content and style. Statistical analysis was conducted in order to learn more about the interrater reliability, consistency of the ratings across iterations and the correlation between ratings in terms of content and style. The results revealed a high interrater reliability with ICC scores ranging between 0.94 and 0.99 for different timespans, suggesting that GPT-4 is capable of generating consistent ratings across repetitions with a clear prompt. Style and content ratings show a high correlation of 0.87. When applying a non-adequate style the average content ratings remained constant, while style ratings decreased, which indicates that the large language model (LLM) effectively distinguishes between these two criteria during evaluation. The prompt used in this study is furthermore presented and explained. Further research is necessary to assess the robustness and reliability of AI models in various use cases.

Automatic speech recognition replaces typing only when correction costs less than manual entry, a threshold determined by error types, not counts: fixing a misrecognized domain term costs far more than inserting a comma. Word error rate (WER) fails on two fronts: it collapses distinct error categories into a single scalar, and it structurally penalizes agglutinative languages where valid sandhi merges inflate scores. We introduce SCRIBE, a diagnostic framework that provides categorical error decomposition into lexical, punctuation, numeral, and domain-entity rates through sandhi-tolerant alignment with domain vocabulary injection. Human validation confirms SCRIBE aligns with expert judgment where WER does not. We release SCRIBE, an LLM curation pipeline, benchmarks, and open-weight rich transcription models for Hindi, Malayalam, and Kannada.

Recent advancements in large language models (LLMs) have greatly improved code generation, specifically at the function level. For instance, GPT-4 has achieved an 88.4% pass rate on HumanEval. However, this draws into question the adequacy of existing benchmarks in thoroughly assessing function-level code generation capabilities. Our study analyzed two common benchmarks, HumanEval and MBPP, and found that these might not thoroughly evaluate LLMs' code generation capacities due to limitations in quality, difficulty, and granularity. To resolve this, we introduce the Mostly Hard Python Problems (MHPP) dataset, consisting of 140 unique human-curated problems. By focusing on the combination of natural language and code reasoning, MHPP gauges LLMs' abilities to comprehend specifications and restrictions, engage in multi-step reasoning, and apply coding knowledge effectively. Initial evaluations of 22 LLMs using MHPP showed many high-performing models on HumanEval failed to achieve similar success on MHPP. Moreover, MHPP highlighted various previously undiscovered limitations within various LLMs, leading us to believe that it could pave the way for a better understanding of LLMs' capabilities and limitations. Dataset and code are available at https://github.com/SparksofAGI/MHPP.

Coding agents increasingly act as codebase-scale collaborators that can assist with codebase conversion, but this progress has exposed a critical weakness: agents often over-trust their own local validation routines and declare success on artifacts that satisfy surface checks while violating the semantic contracts users actually care about. This problem is especially acute in codebase conversion, where prior evaluation is largely outcome-driven and therefore unstable: two implementations can match on a shallow outcome, such as a single forward loss, while diverging in gradients, optimizer behavior, or short-horizon training dynamics. We introduce T2J-Bench, a benchmark for codebase conversion that reformulates conversion as transfer under a fixed equivalence contract. A fixed verifier then compares source and converted codebases through three ordered stages: Spec (interface admissibility), Numeric (forward outputs, losses, gradients, and objective-specific tensors), and Behavioral (short training dynamics under fixed seeds). Across 355 blind conversion attempts, the best system reaches only 26.7--28.9% overall pass rate despite Spec pass rates up to 91.1%; a 4.7x token-budget spread yields only a 2.2x pass-rate spread; and all systems overestimate success by 66.6--97.8 points relative to the fixed evaluator. This suggests that failures stem more from contract-misaligned self-validation than from limited budget or backbone strength.

Coding agents are increasingly used as iterative development partners, but most benchmarks still evaluate one specification followed by one final assessment. This leaves out a basic question: can an agent keep its own codebase working as requirements change? We introduce EvoCode-Bench, a benchmark of 26 stateful coding tasks and 227 evaluated rounds. Each task preserves the agent's workspace for 5-15 rounds, states requirements through observable behavior, and uses cumulative executable tests to check new requirements and still-active prior ones. We evaluate 13 coding agents with two metrics: MT@4, a four-attempt fail-stop multi-round score, and SR, a single-round score from a reference-completed prior state. For most agents, SR exceeds MT@4 by 22-40 points. The gap also changes rankings: the highest-SR agent (78.9) ranks only third in persistent execution (44.0 MT@4). Even the strongest agents achieve only about 50% success on multi-turn metrics, and aggregate pass rate drops below half of round-1 performance by round 5. Failure analysis shows tier-dependent behavior: weaker agents fail early, while stronger agents survive long enough to expose specification-tracking and regression failures. We release the benchmark data and Harbor multi-turn infrastructure.

Terminal-agent benchmarks have become a primary signal for measuring the coding and system-administration capabilities of large language models. As the market for evaluation environments grows, so does the pressure to ship tasks quickly, often without thorough adversarial review of the verification logic. This paper is a guideline for writing good benchmark tasks, drawn from over a year of contributing to and reviewing tasks for Terminal Bench. Most people write benchmark tasks the way they write prompts. They shouldn't. A prompt is designed to help the agent succeed; a benchmark is designed to find out if it can. We argue that good tasks are adversarial, difficult, and legible, and that a large class of common failure modes -- AI-generated instructions, over-prescriptive specifications, clerical difficulty, oracle solutions that assume hidden knowledge, tests that validate the wrong things, and reward-hackable environments -- are predictable consequences of treating task authoring as prompt authoring. We catalog these failure modes, argue that real difficulty is conceptual rather than environmental, and discuss recent empirical evidence that over 15% of tasks in popular terminal-agent benchmarks are reward-hackable. We hope this serves as a useful reference for benchmark maintainers, task contributors, and researchers using benchmark scores as evidence.

Evaluation of large language models (LLMs) for code has primarily relied on static benchmarks, including HumanEval (Chen et al., 2021), which measure the ability of LLMs to generate complete code that passes unit tests. As LLMs are increasingly used as programmer assistants, we study whether gains on existing benchmarks translate to gains in programmer productivity when coding with LLMs, including time spent coding. In addition to static benchmarks, we investigate the utility of preference metrics that might be used as proxies to measure LLM helpfulness, such as code acceptance or copy rates. To do so, we introduce RealHumanEval, a web interface to measure the ability of LLMs to assist programmers, through either autocomplete or chat support. We conducted a user study (N=213) using RealHumanEval in which users interacted with six LLMs of varying base model performance. Despite static benchmarks not incorporating humans-in-the-loop, we find that improvements in benchmark performance lead to increased programmer productivity; however gaps in benchmark versus human performance are not proportional -- a trend that holds across both forms of LLM support. In contrast, we find that programmer preferences do not correlate with their actual performance, motivating the need for better, human-centric proxy signals. We also open-source RealHumanEval to enable human-centric evaluation of new models and the study data to facilitate efforts to improve code models.

AI-generated text has become common in academic and professional writing, prompting research into detection methods. Less studied is the reverse: systematically rewriting AI-generated prose to read as genuinely human-authored. We build a parallel corpus of 25,140 paired AI-input and human-reference text chunks, identify 11 measurable stylistic markers separating the two registers, and fine-tune three models: BART-base, BART-large, and Mistral-7B-Instruct with QLoRA. BART-large achieves the highest reference similarity -- BERTScore F1 of 0.924, ROUGE-L of 0.566, and chrF++ of 55.92 -- with 17x fewer parameters than Mistral-7B. We show that Mistral-7B's higher marker shift score reflects overshoot rather than accuracy, and argue that shift accuracy is a meaningful blind spot in current style transfer evaluation.

Recent advancements in large language models (LLMs) have significantly enhanced text generation capabilities, yet evaluating their performance in generative writing remains a challenge. Existing benchmarks primarily focus on generic text generation or limited in writing tasks, failing to capture the diverse requirements of high-quality written contents across various domains. To bridge this gap, we present WritingBench, a comprehensive benchmark designed to evaluate LLMs across 6 core writing domains and 100 subdomains, encompassing creative, persuasive, informative, and technical writing. We further propose a query-dependent evaluation framework that empowers LLMs to dynamically generate instance-specific assessment criteria. This framework is complemented by a fine-tuned critic model for criteria-aware scoring, enabling evaluations in style, format and length. The framework's validity is further demonstrated by its data curation capability, which enables 7B-parameter models to approach state-of-the-art (SOTA) performance. We open-source the benchmark, along with evaluation tools and modular framework components, to advance the development of LLMs in writing.

This study explores Large Language Models (LLMs) as autonomous agents for real-world tasks, including freelance software development. This work presents a new benchmark that evaluates LLMs on freelance programming and data analysis tasks derived from economic data. We construct the benchmark using synthetic tasks created from a Kaggle Freelancer dataset of job postings, with all job prices standardized to USD (median fixed-project price around 250, and an average of 306). Each task is accompanied by structured input-output test cases and an estimated price tag, enabling automated correctness checking and a monetary performance valuation. This approach is inspired by OpenAI's recent SWE-Lancer benchmark (1,400 real Upwork tasks worth 1M total). Still, our framework simplifies evaluation using programmatically testable tasks and predicted price values, making it highly scalable and repeatable. On this benchmark, we evaluate four modern LLMs - Claude 3.5 Haiku, GPT-4o-mini, Qwen 2.5, and Mistral. We report each model's accuracy (task success rate and test-case pass rate) and the total "freelance earnings" it achieves (sum of prices of solved tasks). Our results show that Claude 3.5 Haiku performs best, earning approximately 1.52 million USD, followed closely by GPT-4o-mini at 1.49 million, then Qwen 2.5 (1.33M) and Mistral ($0.70M). We analyze the distribution of errors per task and observe that the strongest models solve the most tasks and rarely fail completely on any project. We discuss the implications of these results for the feasibility of AI as a freelance developer, the advantages and limitations of our automated benchmark approach, and the gap between performance on structured tasks versus the true complexity of real-world freelance jobs.

Existing evaluation benchmarks of language models of code (code LMs) focus almost exclusively on whether the LMs can generate functionally-correct code. In real-world software engineering, developers think beyond functional correctness. They have requirements on "how" a functionality should be implemented to meet overall system design objectives like efficiency, security, and maintainability. They would also trust the code LMs more if the LMs demonstrate robust understanding of requirements and code semantics. We propose a new benchmark NoFunEval to evaluate code LMs on non-functional requirements and simple classification instances for both functional and non-functional requirements. We propose a prompting method, Coding Concepts (CoCo), as a way for a developer to communicate the domain knowledge to the LMs. We conduct an extensive evaluation of twenty-two code LMs. Our finding is that they generally falter when tested on our benchmark, hinting at fundamental blindspots in their training setups. Surprisingly, even the classification accuracy on functional-correctness instances derived from the popular HumanEval benchmark is low, calling in question the depth of their comprehension and the source of their success in generating functionally-correct code in the first place. We will release our benchmark and evaluation scripts publicly at https://aka.ms/NoFunEval.

The task of generating code solutions for a given programming problem can benefit from the use of pre-trained language models such as Codex, which can produce multiple diverse samples. However, a major challenge for this task is to select the most appropriate solution from the multiple samples generated by the pre-trained language models. A natural way to evaluate the quality and correctness of a code solution is to run it against a set of test cases, but the manual creation of such test cases is often costly and time-consuming. In this paper, we propose a novel method, CodeT, that leverages the same pre-trained language models to automatically generate test cases for the code samples, thus reducing the human effort and increasing the coverage of the test scenarios. CodeT then executes the code samples using the generated test cases, and performs a dual execution agreement, which considers both the consistency of the outputs against the generated test cases and the agreement of the outputs with other code samples. We conduct comprehensive experiments on four benchmarks, HumanEval, MBPP, APPS and CodeContests, using five different pre-trained language models with varying sizes and capabilities. Our results show that CodeT can significantly improve the performance of code solution selection over previous methods, achieving remarkable and consistent gains across different models and benchmarks. For instance, CodeT improves the pass@1 metric on HumanEval to 65.8%, which represents an absolute improvement of 18.8% over the code-davinci-002 model, and an absolute improvement of more than 20% over the previous state-of-the-art results.

Speech enhancement (SE) is commonly applied as a preprocessing step in spoken AI pipelines under the assumption that better audio quality improves downstream task performance. Whether SE-induced distortions propagate to downstream LLM task performance remains an open question. We introduce Output Divergence Rate (ODR), which measures how often SE changes an LLM's intent classification relative to clean speech, and benchmark five conditions on 2,974 SLURP clips using Whisper large-v3 and wav2vec2-large cascades. Every condition produces ODR significantly above zero (p < 0.001, binomial test). MetricGAN{+} more than doubles ODR versus unenhanced noisy speech (0.318 vs. 0.135) despite improving PESQ, and unmitigated echo reaches an ODR of 0.836 through speaker substitution, a failure WER cannot capture. Audio quality metrics range from near-zero to moderate correlation with ODR (SQUIM-MOS ρ=-0.068, PESQ ρ=-0.467). The MetricGAN{+} and echo results replicate across ASR architectures, indicating that standard audio quality metrics are insufficient for LLM pipeline quality.

Standard text-to-speech (TTS) evaluation measures intelligibility (WER, CER) and overall naturalness (MOS, UTMOS) but does not quantify accent. A synthesiser may score well on all four yet sound non-native on features that are phonemic in the target language. For Indic languages, these features include retroflex articulation, aspiration, vowel length, and the Tamil retroflex approximant (letter zha). We present PSP, the Phoneme Substitution Profile, an interpretable, per-phonological-dimension accent benchmark for Indic TTS. PSP decomposes accent into six complementary dimensions: retroflex collapse rate (RR), aspiration fidelity (AF), vowel-length fidelity (LF), Tamil-zha fidelity (ZF), Frechet Audio Distance (FAD), and prosodic signature divergence (PSD). The first four are measured via forced alignment plus native-speaker-centroid acoustic probes over Wav2Vec2-XLS-R layer-9 embeddings; the latter two are corpus-level distributional distances. In this v1 we benchmark four commercial and open-source systems (ElevenLabs v3, Cartesia Sonic-3, Sarvam Bulbul, Indic Parler-TTS) on Hindi, Telugu, and Tamil pilot sets, with a fifth system (Praxy Voice) included on all three languages, plus an R5->R6 case study on Telugu. Three findings: (i) retroflex collapse grows monotonically with phonological difficulty Hindi < Telugu < Tamil (~1%, ~40%, ~68%); (ii) PSP ordering diverges from WER ordering -- commercial WER-leaders do not uniformly lead on retroflex or prosodic fidelity; (iii) no single system is Pareto-optimal across all six dimensions. We release native reference centroids (500 clips per language), 1000-clip embeddings for FAD, 500-clip prosodic feature matrices for PSD, 300-utterance golden sets per language, scoring code under MIT, and centroids under CC-BY. Formal MOS-correlation is deferred to v2; v1 reports five internal-consistency signals plus a native-audio sanity check.

Code-switching -- the natural alternation between two languages within a single utterance -- represents one of the most challenging and under-studied conditions for automatic speech recognition (ASR). Existing commercial ASR benchmarks predominantly evaluate clean, monolingual audio and report a single Word Error Rate (WER) figure that tells practitioners little about real-world multilingual performance. We present a benchmark evaluating five commercial ASR providers across four language pairs: Egyptian Arabic--English, Saudi Arabic (Najdi/Hijazi)--English, Persian (Farsi)--English, and German--English. Each dataset comprises 300 samples selected by a two-stage pipeline: a heuristic filter scoring transcripts on five structural code-switching signals, followed by a GPT-4o and Gemini 1.5 Pro ensemble scoring candidates across six linguistic dimensions. This pipeline reduces LLM scoring costs by approximately 91\% relative to exhaustive scoring. We evaluate the systems on both WER and BERTScore, arguing that BERTScore is a more reliable metric for Arabic and Persian pairs where transliteration variance causes WER to penalise semantically correct transcriptions. ElevenLabs Scribe v2 achieves the lowest WER across all four language pairs (13.2% overall; 13.1% on Egyptian Arabic) and leads on BERTScore (0.936 overall). We further demonstrate that difficulty-stratified analysis reveals performance gaps masked by aggregate averages, and that BERT embedding projections confirm semantic proximity between reference and hypothesis despite surface-level script differences. The benchmarking dataset is publicly available at https://huggingface.co/datasets/Perle-ai/ASR_Code_Switch.

Despite decades of research on reverberant speech, comparing methods remains difficult because most corpora lack per-file acoustic annotations or provide limited documentation for reproduction. We present RIR-Mega-Speech, a corpus of approximately 117.5 hours created by convolving LibriSpeech utterances with roughly 5,000 simulated room impulse responses from the RIR-Mega collection. Every file includes RT60, direct-to-reverberant ratio (DRR), and clarity index (C_{50}) computed from the source RIR using clearly defined, reproducible procedures. We also provide scripts to rebuild the dataset and reproduce all evaluation results. Using Whisper small on 1,500 paired utterances, we measure 5.20% WER (95% CI: 4.69--5.78) on clean speech and 7.70% (7.04--8.35) on reverberant versions, corresponding to a paired increase of 2.50 percentage points (2.06--2.98). This represents a 48% relative degradation. WER increases monotonically with RT60 and decreases with DRR, consistent with prior perceptual studies. While the core finding that reverberation harms recognition is well established, we aim to provide the community with a standardized resource where acoustic conditions are transparent and results can be verified independently. The repository includes one-command rebuild instructions for both Windows and Linux environments.

We present RepoST, a scalable method to construct environments that provide execution feedback for repository-level code generation for both training and evaluation. Unlike existing works that aim to build entire repositories for execution, which is challenging for both human and LLMs, we provide execution feedback with sandbox testing, which isolates a given target function and its dependencies to a separate script for testing. Sandbox testing reduces the complexity of external dependencies and enables constructing environments at a large scale. We use our method to construct RepoST-Train, a large-scale train set with 7,415 functions from 832 repositories. Training with the execution feedback provided by RepoST-Train leads to a performance gain of 5.5% Pass@1 on HumanEval and 3.5% Pass@1 on RepoEval. We also build an evaluation dataset, RepoST-Eval, and benchmark 12 code generation models.

We introduce Nile-Chat-4B, 3x4B-A6B, and 12B, a collection of LLMs for Egyptian dialect, uniquely designed to understand and generate texts written in both Arabic and Latin scripts. Specifically, with Nile-Chat-3x4B-A6B, we introduce a novel language adaptation approach by leveraging the Branch-Train-MiX strategy to merge script-specialized experts, into a single MoE model. Our Nile-Chat models significantly outperform leading multilingual and Arabic LLMs, such as LLaMa, Jais, and ALLaM, on our newly introduced Egyptian evaluation benchmarks, which span both understanding and generative tasks. Notably, our 12B model yields a 14.4% performance gain over Qwen2.5-14B-Instruct on Latin-script benchmarks. All our resources are publicly available. We believe this work presents a comprehensive methodology for adapting LLMs to dual-script languages, addressing an often overlooked aspect in modern LLM development.

Recent advancements in large language models (LLMs) have significantly enhanced code generation from natural language prompts. The HumanEval Benchmark, developed by OpenAI, remains the most widely used code generation benchmark. However, this and other Code LLM benchmarks face critical limitations, particularly in task diversity, test coverage, and linguistic scope. Current evaluations primarily focus on English-to-Python conversion tasks with limited test cases, potentially overestimating model performance. While recent works have addressed test coverage and programming language (PL) diversity, code generation from low-resource language prompts remains largely unexplored. To address this gap, we introduce mHumanEval, an extended benchmark supporting prompts in over 200 natural languages. We employ established machine translation methods to compile the benchmark, coupled with a quality assurance process. Furthermore, we provide expert human translations for 15 diverse natural languages (NLs). We conclude by analyzing the multilingual code generation capabilities of state-of-the-art (SOTA) Code LLMs, offering insights into the current landscape of cross-lingual code generation.

Agent skills, structured procedural knowledge packages injected at inference time, are increasingly used to augment LLM agents on software engineering tasks. However, their real utility in end-to-end development settings remains unclear. We present SWE-Skills-Bench, the first requirement-driven benchmark that isolates the marginal utility of agent skills in real-world software engineering (SWE). It pairs 49 public SWE skills with authentic GitHub repositories pinned at fixed commits and requirement documents with explicit acceptance criteria, yielding approximately 565 task instances across six SWE subdomains. We introduce a deterministic verification framework that maps each task's acceptance criteria to execution-based tests, enabling controlled paired evaluation with and without the skill. Our results show that skill injection benefits are far more limited than rapid adoption suggests: 39 of 49 skills yield zero pass-rate improvement, and the average gain is only +1.2%. Token overhead varies from modest savings to a 451% increase while pass rates remain unchanged. Only seven specialized skills produce meaningful gains (up to +30%), while three degrade performance (up to -10%) due to version-mismatched guidance conflicting with project context. These findings suggest that agent skills are a narrow intervention whose utility depends strongly on domain fit, abstraction level, and contextual compatibility. SWE-Skills-Bench provides a testbed for evaluating the design, selection, and deployment of skills in software engineering agents. SWE-Skills-Bench is available at https://github.com/GeniusHTX/SWE-Skills-Bench.

Agent benchmarks increasingly evaluate repository editing, web research, terminal use, and long-horizon interaction. Their scores support capability claims only when the evaluation protocol keeps the intended capability necessary for success. Recent reward-hacking benchmarks and system reports show that agents can instead recover public solutions, read evaluation artifacts, infer generator structure, manipulate feedback, or benefit from invalid scoring paths; existing responses do not provide a common procedure for attributing these shortcuts and quantifying their effect across benchmarks. We formulate protocol validity and introduce HackDetect, a post-hoc audit that identifies an exposure, determines how the agent used it, and assesses whether the resulting score is misleading. We quantify score inflation with the Mislead gap, defined as the exploit score minus the intended score. We audit 2,385 traces across 15 agent benchmarks and find evidence of exposures and reward hacking in 67.0% of Frontier Science traces and 66.7% of AutoLab tasks. Across paired comparisons, we measure score inflation of 0.45-1.00, showing that benchmark reports should provide evidence that scores reflect the intended capability.

The common standard for quality evaluation of automatic speech recognition (ASR) systems is reference-based metrics such as the Word Error Rate (WER), computed using manual ground-truth transcriptions that are time-consuming and expensive to obtain. This work proposes a multi-language referenceless quality metric, which allows comparing the performance of different ASR models on a speech dataset without ground truth transcriptions. To estimate the quality of ASR hypotheses, a pre-trained language model (LM) is fine-tuned with contrastive learning in a self-supervised learning manner. In experiments conducted on several unseen test datasets consisting of outputs from top commercial ASR engines in various languages, the proposed referenceless metric obtains a much higher correlation with WER scores and their ranks than the perplexity metric from the state-of-art multi-lingual LM in all experiments, and also reduces WER by more than 7% when used for ensembling hypotheses. The fine-tuned model and experiments are made available for the reproducibility: https://github.com/aixplain/NoRefER

We introduce ÌròyìnSpeech, a new corpus influenced by the desire to increase the amount of high quality, contemporary Yorùbá speech data, which can be used for both Text-to-Speech (TTS) and Automatic Speech Recognition (ASR) tasks. We curated about 23000 text sentences from news and creative writing domains with the open license CC-BY-4.0. To encourage a participatory approach to data creation, we provide 5000 curated sentences to the Mozilla Common Voice platform to crowd-source the recording and validation of Yorùbá speech data. In total, we created about 42 hours of speech data recorded by 80 volunteers in-house, and 6 hours of validated recordings on Mozilla Common Voice platform. Our TTS evaluation suggests that a high-fidelity, general domain, single-speaker Yorùbá voice is possible with as little as 5 hours of speech. Similarly, for ASR we obtained a baseline word error rate (WER) of 23.8.

Modern automatic speech recognition (ASR) systems have achieved superhuman Word Error Rate (WER) on many common corpora despite lacking adequate performance on speech in the wild. Beyond that, there is a lack of real-world, accented corpora to properly benchmark academic and commercial models. To ensure this type of speech is represented in ASR benchmarking, we present Earnings-22, a 125 file, 119 hour corpus of English-language earnings calls gathered from global companies. We run a comparison across 4 commercial models showing the variation in performance when taking country of origin into consideration. Looking at hypothesis transcriptions, we explore errors common to all ASR systems tested. By examining Individual Word Error Rate (IWER), we find that key speech features impact model performance more for certain accents than others. Earnings-22 provides a free-to-use benchmark of real-world, accented audio to bridge academic and industrial research.

Single-prompt accuracy is the dominant way to benchmark language models, but it can miss reliability failures that matter. We evaluate a 15-model open-weight corpus, with the main reliability analyses focused on 10 instruct models across five classification and reasoning benchmarks under five prompt variants each, measuring accuracy, token-probability calibration, verbal-confidence calibration, verbal parse rate, and prompt-perturbation spread for every (model x dataset x variant) cell. We find three broad results. First, evaluation design can materially change the conclusion. Switching Expected Calibration Error (ECE) token from a raw to a label-set-normalised definition changes per-cell calibration by a mean absolute 0.149. More strikingly, pairing a chain-of-thought prompt with a first-character evaluator on ARC-Challenge reduces apparent accuracy by 72-88% across all five primary models; two independent repair procedures recover 93.8% and 102.7% of the lost performance, indicating an evaluator-side rather than model-side failure. Second, confidence signals are fragile. On MMLU-Pro, every primary model verbally reports confidence substantially above both its accuracy and its token-probability confidence on the same rows, and verbal parse rate can collapse for a single model on a single prompt variant. Third, prompt robustness does not track parameter count reliably. Across 10 instruct models, the correlation between model size and prompt-perturbation spread ranges from -0.244 to 0.474 across benchmarks. Taken together, these results show that reliability conclusions for small language models depend not only on the model being evaluated, but also on the evaluation pipeline used to measure it. We argue that calibration definitions, evaluator logic, verbal parseability, and prompt robustness should be reported explicitly when making reliability claims.

Benchmarks like MMLU suggest flagship language models approach factuality saturation above 90\%. LLMpedia shows this picture is incomplete. We materialize {sim}1.3M encyclopedia articles entirely from parametric memory across three model families, then audit every claim against Wikipedia and curated web evidence. For gpt-5-mini, the verifiable true rate is 68.4\% on Wikipedia-covered subjects - more than 21\,pp below MMLU - and the gap is driven by unverifiability (30.5\%), not refutation (1.2\%). Beyond Wikipedia, frontier articles audited against curated web evidence reach 57.6\%; Wikipedia covers only 56.7\% of model-surfaced subjects, and three model families overlap in just 7.3\% of subject choices. In a retrieval-trap benchmark inspired by prior analysis of Grokipedia, LLMpedia is more factual at roughly half the textual similarity to Wikipedia. Every prompt, article, and verdict is released. Data, code, interface: https://llmpedia.net.

Large Language Models (LLMs) have shown promise in automated code generation but typically excel only in simpler tasks such as generating standalone code units. Real-world software development, however, often involves complex code repositories (named repo) with complex dependencies and extensive documentation. To fill this gap, our research pivots towards evaluating LLMs in a more realistic setting -- real-world repo-level code generation. We introduce CodeAgentBench, a manually curated benchmark for repo-level code generation. This benchmark comprises five high-quality Python projects, encompassing a total of 101 samples. We assess nine leading LLMs on repo-level tasks and observe a decline in their performance. To tackle this, we present CodeAgent, a novel LLM-based agent framework that employs external tools for effective repo-level code generation. CodeAgent integrates five programming tools, enabling interaction with software artifacts for information retrieval, code symbol navigation, and code testing. We implement four agent strategies to optimize these tools' usage. Our experiments on CodeAgentBench show that CodeAgent enhances LLM performance significantly, with improvements ranging from 18.1\% to 250\%. Further tests on the HumanEval benchmark confirm CodeAgent's adaptability and efficacy across various code generation tasks. Notably, CodeAgent outperforms commercial products like Github Copilot, showcasing superior accuracy and efficiency. These results demonstrate CodeAgent's robust capabilities in code generation, highlighting its potential for real-world repo-level coding challenges.

Agent skills, which are reusable, domain-specific knowledge artifacts, have become a popular mechanism for extending LLM-based agents, yet formally benchmarking skill usage performance remains scarce. Existing skill benchmarking efforts focus on overly idealized conditions, where LLMs are directly provided with hand-crafted, narrowly-tailored task-specific skills for each task, whereas in many realistic settings, the LLM agent may have to search for and select relevant skills on its own, and even the closest matching skills may not be well-tailored for the task. In this paper, we conduct the first comprehensive study of skill utility under progressively challenging realistic settings, where agents must retrieve skills from a large collection of 34k real-world skills and may not have access to any hand-curated skills. Our findings reveal that the benefits of skills are fragile: performance gains degrade consistently as settings become more realistic, with pass rates approaching no-skill baselines in the most challenging scenarios. To narrow this gap, we study skill refinement strategies, including query-specific and query-agnostic approaches, and we show that query-specific refinement substantially recovers lost performance when the initial skills are of reasonable relevance and quality. We further demonstrate the generality of retrieval and refinement on Terminal-Bench 2.0, where they improve the pass rate of Claude Opus 4.6 from 57.7% to 65.5%. Our results, consistent across multiple models, highlight both the promise and the current limitations of skills for LLM-based agents. Our code is available at https://github.com/UCSB-NLP-Chang/Skill-Usage.

Various benchmarks have been proposed to assess the performance of large language models (LLMs) in different coding scenarios. We refer to them as code-related benchmarks. However, there are no systematic guidelines by which such a benchmark should be developed to ensure its quality, reliability, and reproducibility. We propose How2Bench, which is comprised of a 55- 55-criteria checklist as a set of guidelines to govern the development of code-related benchmarks comprehensively. Using HOW2BENCH, we profiled 274 benchmarks released within the past decade and found concerning issues. Nearly 70% of the benchmarks did not take measures for data quality assurance; over 10% did not even open source or only partially open source. Many highly cited benchmarks have loopholes, including duplicated samples, incorrect reference codes/tests/prompts, and unremoved sensitive/confidential information. Finally, we conducted a human study involving 49 participants, which revealed significant gaps in awareness of the importance of data quality, reproducibility, and transparency.

Code Agent development is an extremely active research area, where a reliable performance metric is critical for tracking progress and guiding new developments. This demand is underscored by the meteoric rise in popularity of SWE-Bench. This benchmark challenges code agents to generate patches addressing GitHub issues given the full repository as context. The correctness of generated patches is then evaluated by executing a human-written test suite extracted from the repository after the issue's resolution. However, constructing benchmarks like SWE-Bench requires substantial manual effort to set up historically accurate execution environments for testing. Crucially, this severely limits the number of considered repositories, e.g., just 12 for SWE-Bench. Considering so few repositories, selected for their popularity runs the risk of leading to a distributional mismatch, i.e., the measured performance may not be representative of real-world scenarios potentially misguiding development efforts. In this work, we address this challenge and introduce SetUpAgent, a fully automated system capable of historically accurate dependency setup, test execution, and result parsing. Using SetUpAgent, we generate two new datasets: (i) SWEE-Bench an extended version of SWE-Bench encompassing hundreds of repositories, and (ii) SWA-Bench a benchmark focusing on applications rather than libraries. Comparing these datasets to SWE-Bench with respect to their characteristics and code agent performance, we find significant distributional differences, including lower issue description quality and detail level, higher fix complexity, and most importantly up to 40% lower agent success rates.

This paper presents an eight-week observational comparison of 68 single-file HTML generations collected across 17 public experiments in the "HTML AI Battle" project between December 10, 2025 and February 4, 2026. Four reasoning model families, GPT, Gemini, Grok, and Claude, were compared under a fixed public-interface protocol with no custom instructions, no personality tuning, and no repair prompts. Each output was evaluated from a rendered browser video using human scores and a Gemini LLM-as-a-judge layer for prompt adherence, functional correctness, and UI quality, then packaged into a standardized social-media protocol spanning X (Twitter), TikTok, and YouTube. The tracker was also used for two supervised predictive analyses: an experiment-level model for 24-hour X impressions and a generation-level model for HTML verbosity. Under this protocol, Claude was the strongest and most consistent family, leading mean performance and winning 9/17 prompts under the primary human weighted score. Longer measured reasoning time was not associated with higher quality overall. Gemini as a judge was significantly more lenient than the human evaluator on functional correctness and overall performance, while stable self-favoring bias remained unresolved. The exploratory X-impressions model remained weak under post-screen cross-validation (MAE = 46,874, R^2 = -0.377), whereas the HTML-lines model performed better, with a model-family-only baseline outperforming prompt-aware alternatives (MAE = 135.2, R^2 = 0.576). Overall, selected pre-publication technical/audio variables were not sufficient to predict 24-hour X reach, while code verbosity was driven much more by model family than by prompt wording. The comparisons remain observational and are limited by public-interface drift, access-path differences, and one primary human scorer.

Instruction embedding models have become common among state-of-the-art models, however are evaluated using a single prompt per task. The single-point evaluation ignores a main problem of the instruction-based approach namely: sensitivity to the phrasing of the instruction. We present an empirical study of prompt sensitivity across 6 embedding models, 11 datasets, and 15 task-specific prompts per dataset, a total of 990. We show that reported scores misrepresent the distribution of scores over plausible prompts. The default prompt can both systematically understate or overstate performance. Furthermore, we show that the leaderboard ranking is not robust to prompt selection: by choosing prompts favorably, any model in our study can be promoted to first place. Our findings suggest that single-prompt evaluation is insufficient for instruction-tuned embedding models and that benchmarks should incorporate prompt robustness, either by evaluating over multiple prompts or by reporting sensitivity alongside point estimates.

How to evaluate the coding abilities of Large Language Models (LLMs) remains an open question. We find that existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of LLMs. To address the knowledge gap, we propose a new benchmark named DevEval, which has three advances. (1) DevEval aligns with real-world repositories in multiple dimensions, e.g., code distributions and dependency distributions. (2) DevEval is annotated by 13 developers and contains comprehensive annotations (e.g., requirements, original repositories, reference code, and reference dependencies). (3) DevEval comprises 1,874 testing samples from 117 repositories, covering 10 popular domains (e.g., Internet, Database). Based on DevEval, we propose repository-level code generation and evaluate 8 popular LLMs on DevEval (e.g., gpt-4, gpt-3.5, StarCoder 2, DeepSeek Coder, CodeLLaMa). Our experiments reveal these LLMs' coding abilities in real-world code repositories. For example, in our experiments, the highest Pass@1 of gpt-4-turbo is only 53.04%. We also analyze LLMs' failed cases and summarize their shortcomings. We hope DevEval can facilitate the development of LLMs in real code repositories. DevEval, prompts, and LLMs' predictions have been released.

Modern coding agents expose multiple tool surfaces -- IDE primitives, bash, and Model Context Protocol (MCP) code-execution -- and the field has shipped three contradictory claims about which one matters. We run the missing crossed comparison: an integrity-clean three-arm ablation (baseline / bash_only / code_only) on synthetic computation tasks and SWE-bench Mini modification tasks, holding model, harness, and prompts fixed, with two agents (Claude Code, OpenAI Codex CLI) so the comparison spans both regime and agent-design axes. Across the four resulting (regime, agent) cells, restricting the agent to a single execute_code MCP tool is cheaper than -- or statistically tied with -- its cheapest tool-rich rival in three cells (significantly on Artifact/Claude and SWE-bench/Codex; directionally on Artifact/Codex), with pass rates statistically tied within each cell. The lone exception is SWE-bench/Claude, where code_only is directionally costlier (+14.4%, not significant); a conditional-cost analysis localizes that gap to failure-cost on doomed-run trajectories, not a per-edit tax on successful runs. Two implications: the cheapest tool surface is jointly determined by task regime and agent design rather than by either axis alone, and the headline cost signal lives in cache-adjusted cost -- not pass rate, which is invariant across surfaces at the model sizes we evaluate. The benchmark harness, task suite, and analysis code are available at https://github.com/hyang0129/onlycodes.

As large language models (LLMs) are adopted as a fundamental component of language technologies, it is crucial to accurately characterize their performance. Because choices in prompt design can strongly influence model behavior, this design process is critical in effectively using any modern pre-trained generative language model. In this work, we focus on LLM sensitivity to a quintessential class of meaning-preserving design choices: prompt formatting. We find that several widely used open-source LLMs are extremely sensitive to subtle changes in prompt formatting in few-shot settings, with performance differences of up to 76 accuracy points when evaluated using LLaMA-2-13B. Sensitivity remains even when increasing model size, the number of few-shot examples, or performing instruction tuning. Our analysis suggests that work evaluating LLMs with prompting-based methods would benefit from reporting a range of performance across plausible prompt formats, instead of the currently-standard practice of reporting performance on a single format. We also show that format performance only weakly correlates between models, which puts into question the methodological validity of comparing models with an arbitrarily chosen, fixed prompt format. To facilitate systematic analysis we propose FormatSpread, an algorithm that rapidly evaluates a sampled set of plausible prompt formats for a given task, and reports the interval of expected performance without accessing model weights. Furthermore, we present a suite of analyses that characterize the nature of this sensitivity, including exploring the influence of particular atomic perturbations and the internal representation of particular formats.

Recently, given the docstring for the target problem and the target function signature, large language models (LLMs) have been used not only to generate source code, but also to generate test cases, consisting of test inputs and assertions (e.g., in the form of checking an actual output against the expected output). However, as shown by our empirical study on assertions generated by four LLMs for the HumanEval benchmark, over 62% of the generated assertions are incorrect (i.e., failed on the ground-truth problem solution). To detect incorrect assertions (given the docstring and the target function signature along with a sample of example inputs and outputs), in this paper, we propose a new approach named DeCon to effectively detect incorrect assertions via LLM-generated postconditions for the target problem (a postcondition is a predicate that must always be true just after the execution of the ground-truth problem solution). Our approach requires a small set of I/O examples (i.e., a sample of example inputs and outputs) for the target problem (e.g., the I/O examples included in the docstring for a target problem in HumanEval). We use the given I/O examples to filter out those LLM-generated postconditions that are violated by at least one given I/O example. We then use the remaining postconditions to detect incorrect assertions as those assertions that violate at least one remaining postcondition. Experimental results show that DeCon can detect averagely more than 64% (63% and 65.5% detected by GPT-3.5 and GPT-4, respectively) incorrect assertions generated by four state-of-the-art LLMs, and DeCon can also improve the effectiveness of these LLMs in code generation by 4% in terms of Pass@1. In addition, although DeCon might filter out correct assertions, the fault-finding ability of the remaining correct assertions decreases only slightly.

We propose a benchmark to measure whether a language model is truthful in generating answers to questions. The benchmark comprises 817 questions that span 38 categories, including health, law, finance and politics. We crafted questions that some humans would answer falsely due to a false belief or misconception. To perform well, models must avoid generating false answers learned from imitating human texts. We tested GPT-3, GPT-Neo/J, GPT-2 and a T5-based model. The best model was truthful on 58% of questions, while human performance was 94%. Models generated many false answers that mimic popular misconceptions and have the potential to deceive humans. The largest models were generally the least truthful. This contrasts with other NLP tasks, where performance improves with model size. However, this result is expected if false answers are learned from the training distribution. We suggest that scaling up models alone is less promising for improving truthfulness than fine-tuning using training objectives other than imitation of text from the web.

Large language models can generate code and call tools with remarkable fluency, yet deploying them as practical software engineering assistants still expose stubborn gaps: finite context windows, single mistakes that derail entire sessions, agents that get stuck in dead ends, AI slop, and generated changes that are difficult to review or revert. We present KISS Sorcar, a general-purpose assistant and integrated development environment (IDE) built on top of the KISS Agent Framework, a stupidly-simple AI agent framework of roughly 1,850 lines of code. The framework addresses these gaps using a robust system prompt and through a five-layer agent hierarchy in which each layer adds exactly one concern: budget-tracked ReAct execution, automatic continuation across sub-sessions via summarization, coding, and browser tools with parallel sub-agents, persistent multi-turn chat with history recall, and git worktree isolation so every task runs on its own branch. To assess the power of the KISS agent framework, we implemented KISS Sorcar as a free, open-source Visual Studio Code extension that runs locally and effectively for long-horizon tasks, and supports browser automation, multimodal input, and Docker containers. In this research, we deliberately prioritize output quality over latency: giving a frontier model adequate time to validate its own output -- running linters, type checkers, and tests -- dramatically reduces the low-quality code that plagues faster but less thorough agents. The entire system was built using itself in 4.5 months, providing a continuous stress test in which any agent-introduced bug immediately impairs its own ability to work. On Terminal Bench 2.0, KISS Sorcar achieves a 62.2% overall pass rate with Claude Opus 4.6, comparing favorably to Claude Code (58%) and Cursor Composer 2 (61.7).

Existing benchmarks for tool-using LLM agents primarily report single-run success rates and miss reliability properties required in production. We introduce ReliabilityBench, a benchmark for evaluating agent reliability across three dimensions: (i) consistency under repeated execution using pass^k, (ii) robustness to semantically equivalent task perturbations at intensity ε, and (iii) fault tolerance under controlled tool/API failures at intensity λ. ReliabilityBench contributes a unified reliability surface R(k,ε,λ), action metamorphic relations that define correctness via end-state equivalence rather than text similarity, and a chaos-engineering-style fault injection framework (timeouts, rate limits, partial responses, schema drift). We evaluate two models (Gemini 2.0 Flash, GPT-4o) and two agent architectures (ReAct, Reflexion) across four domains (scheduling, travel, customer support, e-commerce) over 1,280 episodes. Perturbations alone reduce success from 96.9% at ε=0 to 88.1% at ε=0.2. Rate limiting is the most damaging fault in ablations. ReAct is more robust than Reflexion under combined stress, and Gemini 2.0 Flash achieves comparable reliability to GPT-4o at much lower cost. ReliabilityBench provides a systematic framework for assessing production readiness of LLM agents.

We introduce a corpus of 7,032 sentences rated by human annotators for formality, informativeness, and implicature on a 1-7 scale. The corpus was annotated using Amazon Mechanical Turk. Reliability in the obtained judgments was examined by comparing mean ratings across two MTurk experiments, and correlation with pilot annotations (on sentence formality) conducted in a more controlled setting. Despite the subjectivity and inherent difficulty of the annotation task, correlations between mean ratings were quite encouraging, especially on formality and informativeness. We further explored correlation between the three linguistic variables, genre-wise variation of ratings and correlations within genres, compatibility with automatic stylistic scoring, and sentential make-up of a document in terms of style. To date, our corpus is the largest sentence-level annotated corpus released for formality, informativeness, and implicature.

Computer-use agents pay full frontier inference to re-derive routines their user has already performed, because an agent's memory today records what the user said, not what the user did. We compile passively captured screen activity into agent memory with a deterministic, zero-model pipeline: it segments a local capture stream into typed activity frames, bounded episodes carrying application, site, timing, input volume, and evidence pointers back to the raw rows, with no model in the loop, so the output is byte-identical, cacheable, and mechanically auditable. On one professional's single-user corpus of 128,756 frames over 51 active days, the compiler reduces a day of raw capture to a prompt-ready context block 86x smaller in 68 ms, and an agent reading that block answers questions about the day at 98.4% accuracy (Wilson 95% CI 91.7-99.7%) against an independent oracle, versus 66-80% for an LLM summary of the same capture, a mid-tier model reading the block matching a frontier one. The same compiler doubles as a demand-side cost instrument. Read off passive, pre-delegation human activity rather than agent rollouts, it supplies two parameters that agent-cost models assume but, to our knowledge, have not measured: the Routine Overhead Ratio R and the routine recurrence h. We report first values of R, a modeled upper bound, at 60-343x, and a delegable recurrence of 9.0% in-sample and 7.7% out-of-sample, for a realistic all-fleet token ceiling near 8%; a compiled routine replays deterministically with the model out of the loop, demonstrated live at zero model tokens on a guard-matched hit. Schema, compiler, and evaluation harness are open.

As AI coding agents take on increasingly complex, long-horizon software engineering tasks, existing benchmarks are rapidly saturating and their evaluation quality has come under serious scrutiny: a recent audit found that nearly 60% of unsolved SWE-bench Verified instances contain flawed tests -- either overly narrow tests that reject correct solutions or overly broad tests that check unstated requirements -- and that frontier models can verbatim reproduce gold patches from training data. Code refactoring, which requires coordinated, behavior-preserving changes across many files, offers a substantially harder and more realistic test of agent capability, yet remains underserved by current benchmarks. We introduce SWE-Bench ProMax, an expert-curated, multilingual code refactoring benchmark of 170 instances drawn from real commits across seven programming languages (Python, Java, TypeScript, Go, C, C++, and Rust). Every instance undergoes rigorous, multi-stage curation that directly addresses the quality problems identified in prior benchmarks: issue descriptions are rewritten from scratch to provide precise, unambiguous specifications, and test suites are manually reviewed to remove overly narrow and overly broad tests. Tasks with insufficient complexity or limited cross-file scope are filtered out, yielding a benchmark of challenging, large-scale refactoring tasks that average 11.4 modified files and 261.6 lines of code per instance, substantially exceeding the scale of existing benchmarks. Experiments with frontier models under two agent scaffolds show that the best model achieves only 41.2% resolve rate, confirming that SWE-Bench ProMax presents a meaningful and unsaturated challenge for current AI coding agents. Our benchmark is available at https://huggingface.co/datasets/swe-bench-promax/SWE-Bench-ProMax.

The large-scale training of multi-modal models on data scraped from the web has shown outstanding utility in infusing these models with the required world knowledge to perform effectively on multiple downstream tasks. However, one downside of scraping data from the web can be the potential sacrifice of the benchmarks on which the abilities of these models are often evaluated. To safeguard against test data contamination and to truly test the abilities of these foundation models we propose LiveXiv: A scalable evolving live benchmark based on scientific ArXiv papers. LiveXiv accesses domain-specific manuscripts at any given timestamp and proposes to automatically generate visual question-answer pairs (VQA). This is done without any human-in-the-loop, using the multi-modal content in the manuscripts, like graphs, charts, and tables. Moreover, we introduce an efficient evaluation approach that estimates the performance of all models on the evolving benchmark using evaluations of only a subset of models. This significantly reduces the overall evaluation cost. We benchmark multiple open and proprietary Large Multi-modal Models (LMMs) on the first version of our benchmark, showing its challenging nature and exposing the models true abilities, avoiding contamination. Lastly, in our commitment to high quality, we have collected and evaluated a manually verified subset. By comparing its overall results to our automatic annotations, we have found that the performance variance is indeed minimal (<2.5%). Our dataset is available online on HuggingFace, and our code will be available here.

How much do large language models actually hallucinate when answering questions grounded in provided documents? Despite the critical importance of this question for enterprise AI deployments, reliable measurement has been hampered by benchmarks that rely on static datasets vulnerable to contamination, LLM-based judges with documented biases, or evaluation scales too small for statistical confidence. We address this gap using RIKER, a ground-truth-first evaluation methodology that enables deterministic scoring without human annotation. Across 35 open-weight models, three context lengths (32K, 128K, and 200K tokens), four temperature settings, and three hardware platforms (NVIDIA H200, AMD MI300X, and Intel Gaudi 3), we conducted over 172 billion tokens of evaluation - an order of magnitude beyond prior work. Our findings reveal that: (1) even the best-performing models fabricate answers at a non-trivial rate - 1.19% at best at 32K, with top-tier models at 5 - 7% - and fabrication rises steeply with context length, nearly tripling at 128K and exceeding 10% for all models at 200K; (2) model selection dominates all other factors, with overall accuracy spanning a 72-percentage-point range and model family predicting fabrication resistance better than model size; (3) temperature effects are nuanced - T=0.0 yields the best overall accuracy in roughly 60% of cases, but higher temperatures reduce fabrication for the majority of models and dramatically reduce coherence loss (infinite generation loops), which can reach 48x higher rates at T=0.0 versus T=1.0; (4) grounding ability and fabrication resistance are distinct capabilities - models that excel at finding facts may still fabricate facts that do not exist; and (5) results are consistent across hardware platforms, confirming that deployment decisions need not be hardware-dependent.

Large language models work well on English and behave in poorly understood ways on languages typologically far from it. Japanese is a clean example, where evaluation still leans on translation quality and JGLUE-style benchmarks, which roll lexical, syntactic and pragmatic competence into a single score. The phenomena on which general-purpose models fail Japanese users are pragmatic: honorifics, in-group and out-group reference, context-sensitive politeness, zero anaphora. I introduce J-PragEval-v0, a minimal-pair benchmark isolating four such phenomena from surface fluency, and combine it with linear probes and teacher-forced log-probability evaluation to ask where inside TinySwallow-1.5B (28 layers, hidden size 1536) the corresponding contrasts live. The four features split three ways. Honorific register sits cleanly in the residual stream: 0.96 balanced accuracy at layer 15, and the model flips its preferred continuation with the scenario on 93 percent of items. Implicit subject and in-group reference are not linearly decodable at the final prompt token (0.48 and 0.38), yet flip rates are 0.77 and 0.79, so the contrast is worked out during generation rather than stored at the prompt. Indirect refusal is the negative case: 0.95 probe accuracy collapsing to a 0.43 flip rate under length-normalised teacher forcing, because the current minimal pairs conflate politeness with continuation length. I also specify Pragmatic Representation Steering, a parameter-free inference-time method that edits residual-stream activations along the class-mean-difference directions probing identifies. Feasibility is argued indirectly rather than demonstrated: the contrastive activation addition baseline, the same geometry the method would inject, recovers probe accuracy within one to two points of logistic regression wherever a linear signal exists. Scaling to Llama-3.1-Swallow-8B is the next step.

Natural language to repository generation (NL2Repo) requires a system to construct an entire software repository from a natural-language requirements document. Compared with function-level code generation, this task demands longer planning horizons, stable interfaces across files, and iterative debugging of cross-file inconsistencies. To address these challenges, we propose CodeTeam, an LLM-based multi-agent framework that separates planning, decision making, and implementation into distinct, coordinated stages. In the planning stage, multiple Architect agents draft competing software design sketches (SDS), optionally grounded by retrieved design references. A CTO agent then evaluates, selects, and normalizes the most promising SDS into a machine-checkable contract that specifies file ownership, public interfaces, and dependency constraints. In the implementation stage, Developer agents generate code under a dependency-aware scheduler with bounded context and lightweight Git-based coordination, while a QA agent runs tests and drives iterative repairs. On the synthesis-based SketchEval benchmark, we explicitly compare CodeTeam's prompt-engineering (PE) and supervised fine-tuning (SFT) variants with the corresponding CodeS variants, where CodeTeam improves the overall SketchBLEU by 4.1 and 2.9 absolute points, respectively. On the execution-based NL2Repo-Bench benchmark, used as an external validation protocol, CodeTeam achieves the highest average test pass rate in both settings (34.6% PE, 42.3% SFT), confirming that the sketch-improvements extend to functional correctness under upstream test suites. Ablation results show that project-specific developer allocation and retrieval-augmented planning each contribute substantially to the SketchBLEU improvement (9.9% and 8.1% relative, respectively). CodeTeam and the experimental results are available at https://github.com/WhitenWhiten/CodeTeam

Benchmarks are essential for consistent evaluation and reproducibility. The integration of Artificial Intelligence into Software Engineering (AI4SE) has given rise to numerous benchmarks for tasks such as code generation and bug fixing. However, this surge presents challenges: (1) scattered benchmark knowledge across tasks, (2) difficulty in selecting relevant benchmarks, (3) the absence of a uniform standard for benchmark development, and (4) limitations of existing benchmarks. In this paper, we review 173 studies and identify 204 AI4SE benchmarks. We classify these benchmarks, analyze their limitations, and expose gaps in practices. Based on our review, we created BenchScout, a semantic search tool to find relevant benchmarks, using automated clustering of the contexts from associated studies. We conducted a user study with 22 participants to evaluate BenchScout's usability, effectiveness, and intuitiveness which resulted in average scores of 4.5, 4.0, and 4.1 out of 5. To advance benchmarking standards, we propose BenchFrame, a unified method to enhance benchmark quality. As a case study, we applied BenchFrame to the HumanEval benchmark and addressed its main limitations. This led to HumanEvalNext, featuring (1) corrected errors, (2) improved language conversion, (3) expanded test coverage, and (4) increased difficulty. We then evaluated ten state-of-the-art code language models on HumanEval, HumanEvalPlus, and HumanEvalNext. On HumanEvalNext, models showed a pass@1 score reduction of 31.22% and 19.94% compared to HumanEval and HumanEvalPlus, respectively.

Take three frontier mixture-of-experts models (Alibaba, OpenAI, NVIDIA; 3.6-4.0B active parameters each) and fine-tune them to reason in a low-resource language. On accuracy benchmarks almost nothing happens, and the benchmark itself is noise at this scale: changing only the random seed moves the score by 7.7 points, more than every data and recipe effect we measured. That null is our first result. The real changes live where accuracy cannot see. Base models never think in Greek: 0 of 1,000 reasoning traces, even when the question is Greek, so the model answers correctly while reasoning in a form its user cannot read, audit, or correct. After supervised fine-tuning (SFT), every released checkpoint reasons in the language of the question on ~98% of items, one family at 3x fewer tokens, with judged grammaticality improving on all four models and general ability within a few points of each base: nothing was forgotten, and fluency was gained. We propose six behavioural dimensions that make such changes measurable, each gated to reject any metric that correlates with output length, and we report how our own instruments lied: six failures, each caught by a control. What SFT cannot do is fix its own defects: a quarter of answers skip the requested format, answers leak into the reasoning channel, and an explicit "think in English" is obeyed under half the time. Reinforcement learning with verifiable rewards, pre-registered before training, fixes the first two outright (fallback 24% to 2.5%, leak 3.5% to 0.0%, both against a flat random-reward control) and moves the third (+9.1pp), while the Greek reasoning habit survives an accuracy-only gradient untouched. We release five checkpoints. The instruments, the controls and the pre-registration travel to any low-resource language; Greek is the case that let us measure them.

Code large language models (LLMs) enhance programming by understanding and generating code across languages, offering intelligent feedback, bug detection, and code updates through reflection, improving development efficiency and accessibility. While benchmarks (e.g. HumanEval/LiveCodeBench) evaluate code generation and real-world relevance, previous works ignore the scenario of modifying code in repositories. Considering challenges remaining in improving reflection capabilities and avoiding data contamination in dynamic benchmarks, we introduce LiveRepoReflection, a challenging benchmark for evaluating code understanding and generation in multi-file repository contexts, featuring 1,888 rigorously filtered test cases across 6 programming languages to ensure diversity, correctness, and high difficulty. Further, we create RepoReflection-Instruct, a large-scale, quality-filtered instruction-tuning dataset derived from diverse sources, used to train RepoReflectionCoder through a two-turn dialogue process involving code generation and error-driven repair. The leaderboard evaluates over 40 LLMs to reflect the model performance of repository-based code reflection.

While text-to-image (T2I) generative models have become ubiquitous, they do not necessarily generate images that align with a given prompt. While previous work has evaluated T2I alignment by proposing metrics, benchmarks, and templates for collecting human judgements, the quality of these components is not systematically measured. Human-rated prompt sets are generally small and the reliability of the ratings -- and thereby the prompt set used to compare models -- is not evaluated. We address this gap by performing an extensive study evaluating auto-eval metrics and human templates. We provide three main contributions: (1) We introduce a comprehensive skills-based benchmark that can discriminate models across different human templates. This skills-based benchmark categorises prompts into sub-skills, allowing a practitioner to pinpoint not only which skills are challenging, but at what level of complexity a skill becomes challenging. (2) We gather human ratings across four templates and four T2I models for a total of >100K annotations. This allows us to understand where differences arise due to inherent ambiguity in the prompt and where they arise due to differences in metric and model quality. (3) Finally, we introduce a new QA-based auto-eval metric that is better correlated with human ratings than existing metrics for our new dataset, across different human templates, and on TIFA160.

Software development is iterative, yet agentic coding benchmarks overwhelmingly evaluate single-shot solutions against complete specifications. Code can pass the test suite but become progressively harder to extend. Recent iterative benchmarks attempt to close this gap, but constrain the agent's design decisions too tightly to faithfully measure how code quality shapes future extensions. We introduce SlopCodeBench, a language-agnostic benchmark comprising 20 problems and 93 checkpoints, in which agents repeatedly extend their own prior solutions under evolving specifications that force architectural decisions without prescribing internal structure. We track two trajectory-level quality signals: verbosity, the fraction of redundant or duplicated code, and structural erosion, the share of complexity mass concentrated in high-complexity functions. No agent solves any problem end-to-end across 11 models; the highest checkpoint solve rate is 17.2%. Quality degrades steadily: erosion rises in 80% of trajectories and verbosity in 89.8%. Against 48 open-source Python repositories, agent code is 2.2x more verbose and markedly more eroded. Tracking 20 of those repositories over time shows that human code stays flat, while agent code deteriorates with each iteration. A prompt-intervention study shows that initial quality can be improved, but it does not halt degradation. These results demonstrate that pass-rate benchmarks systematically undermeasure extension robustness, and that current agents lack the design discipline iterative software development demands.

Driven by the surge in code generation using large language models (LLMs), numerous benchmarks have emerged to evaluate these LLMs capabilities. We conducted a large-scale human evaluation of HumanEval and MBPP, two popular benchmarks for Python code generation, analyzing their diversity and difficulty. Our findings unveil a critical bias towards a limited set of programming concepts, neglecting most of the other concepts entirely. Furthermore, we uncover a worrying prevalence of easy tasks, potentially inflating model performance estimations. To address these limitations, we propose a novel benchmark, PythonSaga, featuring 185 hand-crafted prompts on a balanced representation of 38 programming concepts across diverse difficulty levels. The robustness of our benchmark is demonstrated by the poor performance of existing Code-LLMs.

Niche-domain Indic ASR -- digit strings, currency amounts, addresses, brand names, English/Indic codemix -- is under-served by both open-source SOTA and commercial systems. On a synthesised entity-dense Telugu test set (held-out by synthesis system), vasista22/whisper-telugu-large-v2 (open SOTA) achieves Entity-Hit-Rate (EHR) 0.027 and Deepgram Nova-3 (commercial) 0.16. We close this gap with a self-contained TTS<->STT flywheel: an open-source Indic TTS pipeline synthesises ~22,000 entity-dense Indic-English code-mix utterances at <$50 marginal cost, and a LoRA fine-tune on top of vasista22 achieves EHR 0.473 on the held-out test (17x over open SOTA, 3x over commercial), with read-prose regression bounded to +6.6 pp WER on FLEURS-Te. Cross-language: beta-Hi 0.337 (7x vs vasista22) and beta-Ta 0.543 (22x vs vasista22, 22x vs Deepgram); on Hindi where Deepgram has substantial entity coverage, the flywheel underperforms commercial. All three beta models fall below pre-registered EHR targets (0.75 for Te, 0.65 for Hi/Ta); we report honestly. A native-human-recorded sanity check (n=20 Telugu) confirms transfer to real speech (beta-Te EHR 0.516 on native vs 0.473 on synth). An EDSA-isolation ablation (LoRA on FLEURS-Te alone) yields EHR 0.020 on the same held-out, attributing ~100% of the gain to the EDSA corpus. We additionally report a language-conditional finding: vanilla Whisper-large-v3 has Telugu-specific Script Collapse (SFR 0.46-0.71) that a per-language LoRA corrects (SFR 0.81-0.97), but the recipe is contraindicated on Hindi and Tamil where vanilla SFR >= 0.98. Code, holdouts, predictions, EDSA corpus, and entity dictionaries are released open-source.

AI tools are accelerating scientific publication while the systems that review it struggle to keep up, and independent verification of published research has become both harder and more important. As manual replication is slow and expensive, a growing line of work uses coding agents to automate parts of the process. Existing efforts are largely packaged as benchmarks with companion agents that only run inside the benchmark's own pipeline, and no general-purpose replication tool exists. We present VERITAS, a domain-agnostic replication framework built around CLI coding agents. Given a paper, a code repository, or both, VERITAS extracts the paper's claims, runs the methodology while resolving issues as they arise, and judges each claim against the evidence from experiment runs. The pipeline returns an importance-weighted Replication Score, a severity-rated log of every fix applied, and the patched codebase. We evaluate VERITAS on CORE-Bench and ReplicationBench, 65 papers spanning computer science, social science, medicine, and astrophysics. Against two strong Claude Code baselines on the same model and host environment, VERITAS achieves state-of-the-art performance and leads on every metric on both benchmarks.

In the era of large language models, creative writing quality lacks a computable theoretical anchor. The dominant approaches are rubric scoring -- decomposing holistic aesthetic judgment into sub-scores -- and RLHF preference signals -- replacing quality with group votes. Both bypass the statistical structure of the text itself. This paper provides an information-theoretic foundation to fill this gap. We propose 'calibrated surprise' as the information-theoretic essence of excellent creative writing. This judgment matches reading intuition and covers its opposite. This literary judgment admits a precise mathematical formulation. Under full-dimensional constraints Y, feasible writing choices are forced into an extremely narrow space. The rare survivors are, from the unconstrained perspective, exactly the least predictable choices. Both are measured precisely by Shannon mutual information I(X;Y) = H(X) - H(X|Y) -- 'calibrated' corresponds to H(X|Y) approaching 0; 'surprising' corresponds to H(X) going high. The subtraction structure of the formula naturally separates 'well-grounded surprise' from 'pure noise'. We use token-level logprobs from Qwen1.5-7B as an operational proxy for the ideal reader's probability distribution. Across 20 pairs (12 Chinese / 8 English) of high-quality vs. systematically degraded literary passages, 20/20 pairs support the core prediction: high-quality passages have systematically higher I(X;Y) than their degraded versions.

When an AI agent calls an API and hits a validation error, it needs more than what went wrong -- it needs what to do next. A self-reflective API returns, on validation failure, a machine-readable recovery\_feedback.suggestions[] payload sufficient for the agent to repair the request and retry without external reasoning. On a leak-audited pilot (N{=}30 per cell, 3 LLMs, 10 adversarial tasks), structured suggestions lift task-completion rate by +36.7--40.0pp over plain-English diagnoses on Anthropic models (Fisher's exact p le 0.0022), at 1.8--2.2times better per-success token efficiency. The lift is not significant on gpt-4o-mini (p{=}0.435); a second-domain replication on a billing API confirms the pattern. The comparison only holds after auditing two undocumented classes of answer leakage in LLM benchmarks. We shipaudit\_prompt\_leakage.py as reusable CI infrastructure. Code and data: https://github.com/arquicanedo/self-reflective-apis.

Multilingual pretrained models nominally support Nepali, yet no controlled benchmark has compared them under a single fine-tuning protocol. We fine-tune six pretrained models (XLSR-53, IndicWav2Vec, MMS-1B, Whisper-Medium, Whisper-Large-v3-Turbo, and Conformer-Hi) spanning CTC self-supervised, autoregressive encoder-decoder, and hybrid Conformer-CTC architectures, on the OpenSLR SLR54 Nepali corpus (~165 hours) using identical preprocessing, splits, optimizer, and family-matched learning-rate schedules. We evaluate Word Error Rate (WER), Character Error Rate (CER), and Real-Time Factor (RTF) on three independent test sets (OpenSLR, FLEURS, Common Voice). Whisper-Large-v3-Turbo (14.76% WER) and IndicWav2Vec (14.89% WER) tie at the top despite a 9x parameter gap and 40x pretraining-data gap, providing direct empirical evidence that language-family proximity in pretraining can substitute for raw scale for in-domain Nepali. CTC decoders run up to 29x faster than autoregressive Whisper at the same accuracy, flipping the practical deployment preference toward CTC under any latency budget. Massively multilingual pretraining (MMS-1B) yields the smallest out-of-domain degradation on FLEURS (+12.55 pp), indicating that scale buys robustness rather than peak in-domain accuracy. The resulting benchmark provides the first standardized, multi-model, efficiency-aware reference numbers for Nepali ASR.

Agent Skills augment large language model (LLM) agents with procedural knowledge at inference time, but current benchmarks rarely distinguish what a Skill says from how it is organized. We study this distinction through Progressive Disclosure, where a concise root file points agents to supporting resources on demand, and compare it with a normalized flat baseline. We present SkillJuror, a framework for evaluating Skill writing paradigms through semantically controlled variants, matched multi-trial evaluations, and trajectory evidence while holding task knowledge fixed. In an 82-task SkillsBench study, Progressive Disclosure changes runtime behavior before aggregate outcomes: distinct Skill resources touched per trajectory rise from 1.18 to 3.85, and effective uptake events rise from 1.33 to 3.92. It also yields 17 additional verifier-passing trials out of 410 matched trials (+4.1%) over the normalized flat baseline. The benefit is task-dependent. Progressive Disclosure helps when supporting resources guide implementation, checking, or repair, but is weaker when success hinges on exact output conventions, numerical thresholds, or long artifact-generation pipelines. These results show that Skill organization is not mere presentation: it can change how agents search and apply procedural knowledge, while outcome gains depend on whether the exposed resources are actionable for the task. Code is available at https://github.com/zhiyuchen-ai/skill-juror.

Evaluating the real-world applicability of large language models (LLMs) provides valuable insights for their development and use in software development tasks. Existing benchmarks often focus on standalone coding problems or specific libraries, overlooking multi-file, project-based scenarios and lacking a rigorous evaluation of consistency. The HackerRank-ASTRA Benchmark introduces project-based coding problems that mirror real-world scenarios. It evaluates model consistency through 32 runs (k = 32) and median standard deviation while incorporating taxonomy-level analysis to assess sub-skill capabilities. Initial evaluations on 65 problems show that the top three models -- o1, o1-preview, and Claude-3.5-Sonnet-1022 -- achieved comparable average scores of 75%, with no statistically significant differences in performance. Notably, Claude-3.5-Sonnet-1022 demonstrated the highest consistency across problems, with low variability (SD = 0.0497), which was statistically significant compared to other models, highlighting its reliability for real-world software development tasks.

We introduce Earnings25, a finance-domain benchmark for evaluating automatic speech recognition (ASR) on English-language earnings calls under realistic conditions. Earnings25 comprises two complementary test sets: (i) testset-full, 498 hours of full English-language S&P 500 earnings calls from Q4 2025, and (ii) testset-segmented, a 46-hour industry-balanced set of 290 segments sampled from English-language U.S. earnings calls in 2025. The benchmark provides aligned transcripts and structured metadata, including speaker roles, industry labels, and call structure, enabling speaker- and industry-aware evaluation beyond aggregate word error rate (WER). We report reproducible baselines for Whisper and Parakeet-TDT using standardized scoring.

Advanced LLMs have achieved near-ceiling instruction-following accuracy on benchmarks such as IFEval. However, these impressive scores do not necessarily translate to reliable services in real-world use, where users often vary their phrasing, contextual framing, and task formulations. In this paper, we study nuance-oriented reliability: whether models exhibit consistent competence across cousin prompts that convey analogous user intents but with subtle nuances. To quantify this, we introduce a new metric, reliable@k, and develop an automated pipeline that generates high-quality cousin prompts via data augmentation. Building upon this, we construct IFEval++ for systematic evaluation. Across 20 proprietary and 26 open-source LLMs, we find that current models exhibit substantial insufficiency in nuance-oriented reliability -- their performance can drop by up to 61.8% with nuanced prompt modifications. What's more, we characterize it and explore three potential improvement recipes. Our findings highlight nuance-oriented reliability as a crucial yet underexplored next step toward more dependable and trustworthy LLM behavior. Our code and benchmark are accessible: https://github.com/jianshuod/IFEval-pp.

Selecting high-quality pre-training data is important for creating capable language models, but existing methods rely on simple heuristics. We introduce QuRating, a method for selecting pre-training data that captures the abstract qualities of texts which humans intuitively perceive. In this paper, we investigate four qualities - writing style, required expertise, facts & trivia, and educational value. We find that LLMs are able to discern these qualities and observe that they are better at making pairwise judgments of texts than at rating the quality of a text directly. We train a QuRater model to learn scalar ratings from pairwise judgments, and use it to annotate a 260B training corpus with quality ratings for each of the four criteria. In our experiments, we select 30B tokens according to the different quality ratings and train 1.3B-parameter language models on the selected data. We find that it is important to balance quality and diversity, as selecting only the highest-rated documents leads to poor results. When we sample using quality ratings as logits over documents, our models achieve lower perplexity and stronger in-context learning performance than baselines. Beyond data selection, we use the quality ratings to construct a training curriculum which improves performance without changing the training dataset. We extensively analyze the quality ratings and discuss their characteristics, biases, and wider implications.

Agents powered by large language models (LLMs) are increasingly adopted in the software industry, contributing code as collaborators or even autonomous developers. As their presence grows, it becomes important to assess the current boundaries of their coding abilities. Existing agentic coding benchmarks, however, cover a limited task scope, e.g., bug fixing within a single pull request (PR), and often rely on non-executable evaluations or lack an automated approach for continually updating the evaluation coverage. To address such issues, we propose FeatureBench, a benchmark designed to evaluate agentic coding performance in end-to-end, feature-oriented software development. FeatureBench incorporates an execution-based evaluation protocol and a scalable test-driven method that automatically derives tasks from code repositories with minimal human effort. By tracing from unit tests along a dependency graph, our approach can identify feature-level coding tasks spanning multiple commits and PRs scattered across the development timeline, while ensuring the proper functioning of other features after the separation. Using this framework, we curated 200 challenging evaluation tasks and 3825 executable environments from 24 open-source repositories in the first version of our benchmark. Empirical evaluation reveals that the state-of-the-art agentic model, such as Claude 4.5 Opus, which achieves a 74.4% resolved rate on SWE-bench, succeeds on only 11.0% of tasks, opening new opportunities for advancing agentic coding. Moreover, benefiting from our automated task collection toolkit, FeatureBench can be easily scaled and updated over time to mitigate data leakage. The inherent verifiability of constructed environments also makes our method potentially valuable for agent training.

LLM agents often retry after external validation rejects a candidate, but the interface between validation and the next model call remains underspecified. We introduce VeriHarness, a code-controlled agent loop in which models generate candidates while external validators control acceptance, budgets, and traces. We use it to compare raw diagnostics with feedback that identifies the failure location, observed value, and admissible alternatives. Across 50 paired TextWorld games under a four-call cap, feedback containing all three fields raises terminal success from 14/50 to 36/50 for Qwen2.5-Coder-14B (+44 percentage points) and from 8/50 to 29/50 for Llama-3.1-8B (+42 points). Ablations locate most of the gain in the admissible alternatives: feedback containing only the location and observed value remains near the raw diagnostic baseline. Presenting the complete repair information in prose instead of a keyed JSON record yields nearly the same success, providing no evidence that JSON syntax itself improves repair. The ordering persists across the tested call budgets and one sampled-decoding setting.

Why do language models sometimes prefer correct statements even when trained on mixed-quality data? We introduce the Compression--Consistency Principle: next-token prediction favors hypotheses that allow shorter and more internally consistent descriptions of the training data. Truth bias emerges only when false alternatives are structurally harder to compress. We test this using small GPT-2-style character-level transformers (3.5M--86M parameters) on synthetic math corpora with controlled mixtures of correct and incorrect rules. In the random-error setting, models strongly prefer correct completions in paired evaluation: 83.1% accuracy at balanced data and 67.0% even when correct rules appear in only 10% of the corpus. Replacing random errors with a coherent but mathematically incorrect rule system largely eliminates the preference (near-chance accuracy). In a more natural-language-like synthetic world, the effect is weaker but still present (57.7%). Additional experiments show that embedding verification steps can restore preference for correctness even at small scale, while increasing the number of consistent rules produces a graded improvement in accuracy. Our results suggest that what appears as a "truth bias" is largely a side effect of compression pressure and preference for internal consistency, rather than an intrinsic drive toward truth. Full code and data are available at https://github.com/Rai220/compression-drives-truth.

When assessing the quality of coding agents, predominant benchmarks focus on solving single issues on GitHub, such as SWE-Bench. In contrast, in real use, these agents solve more various and complex tasks that involve other skills such as exploring codebases, testing software, and designing architecture. In this paper, we first characterize some transferable skills that are shared across diverse tasks by decomposing trajectories into fine-grained components, and derive a set of principles for designing auxiliary training tasks to teach language models these skills. Guided by these principles, we propose a training environment, Hybrid-Gym, consisting of a set of scalable synthetic tasks, such as function localization and dependency search. Experiments show that agents trained on our synthetic tasks effectively generalize to diverse real-world tasks that are not present in training, improving a base model by 25.4% absolute gain on SWE-Bench Verified, 7.9% on SWT-Bench Verified, and 5.1% on Commit-0 Lite. Hybrid-Gym also complements datasets built for the downstream tasks (e.g., improving SWE-Play by 4.9% on SWT-Bench Verified). Code available at: https://github.com/yiqingxyq/Hybrid-Gym.