Daily Papers

Command-line interface (CLI) agents increasingly execute longer-horizon tasks, yet existing benchmarks either assume that user instructions remain fixed throughout execution or evaluate task outcomes without capturing runtime collaboration quality. In this paper, we present REALCLI, a paired benchmark that unifies the evaluation of task execution and human-agent collaboration quality on realistic CLI tasks. To comprehensively measure collaboration, REALCLI builds a five-dimensional framework, operationalized into 22 sub-dimensions and 51 interaction scenario templates. REALCLI provides two modes for paired comparison: REALCLI-EXEC supplies complete specifications upfront, whereas REALCLI-COLLAB introduces a scripted user that delivers progressive information, corrections, constraint revisions, and authorization decisions. Evaluations reveal profound capability gaps in frontier agents: the best configuration attains an average score of only 49.2%, and when evaluated by the joint collaboration score (J_{collab}), the peak performance reaches merely 37.6%. These results show that task effectiveness diverges sharply from collaboration quality, with models consistently struggling in steerability, trust calibration, and safety boundary management. REALCLI provides a rigorous, reproducible foundation for measuring and advancing collaborative CLI agents.

Comprehensive structured data on inter-firm relationships is often scarce or inaccessible because many relationships are privately negotiated, selectively disclosed, and fragmented across proprietary databases. This scarcity hinders the discovery of collaboration opportunities, particularly for startups and small and medium-sized enterprises. Firm profiles are readily available, but collaboration potential cannot be inferred from business similarity alone, since similar firms may be competitors, whereas dissimilar firms may offer complementary products, technologies, channels, capabilities, or capital. We present FirmCORe (Inter-Firm Collaboration Opportunity Reasoning), a human-annotated benchmark for pairwise reasoning over weakly structured firm profiles, comprising 2,805 labeled firm pairs. Given two firm profiles, a model must determine whether the available evidence supports a collaboration opportunity and, for positive pairs, jointly predict its strength, primary collaboration type, and role direction. FirmCORe also provides parallel Chinese- and English-language evaluation sets containing identical instances and gold labels, enabling controlled analysis of input-language sensitivity. Experiments with representative locally deployed and hosted large language models (LLMs) show that the strongest model achieves a macro-F1 score of 74.51 for opportunity detection but only 61.57% exact match across all four output fields. Language effects vary across models, and high cross-language agreement can mask errors shared across languages. These results indicate that current LLMs are substantially more reliable at detecting broad collaboration opportunities than at identifying their specific types and role directions.

The rise of unifying frameworks that enable seamless interoperability of Large Language Models (LLMs) has made LLM-LLM collaboration for open-ended tasks a possibility. Despite this, there have not been efforts to explore such collaborative writing. We take the next step beyond human-LLM collaboration to explore this multi-LLM scenario by generating the first exclusively LLM-generated collaborative stories dataset called CollabStory. We focus on single-author (N=1) to multi-author (up to N=5) scenarios, where multiple LLMs co-author stories. We generate over 32k stories using open-source instruction-tuned LLMs. Further, we take inspiration from the PAN tasks that have set the standard for human-human multi-author writing tasks and analysis. We extend their authorship-related tasks for multi-LLM settings and present baselines for LLM-LLM collaboration. We find that current baselines are not able to handle this emerging scenario. Thus, CollabStory is a resource that could help propel an understanding as well as the development of techniques to discern the use of multiple LLMs. This is crucial to study in the context of writing tasks since LLM-LLM collaboration could potentially overwhelm ongoing challenges related to plagiarism detection, credit assignment, maintaining academic integrity in educational settings, and addressing copyright infringement concerns. We make our dataset and code available at \url{https://github.com/saranya-venkatraman/multi_llm_story_writing}.

Understanding collaboration patterns in introductory programming courses is essential, as teamwork is a critical skill in computer science. In professional environments, software development relies on effective teamwork, navigating diverse perspectives, and contributing to shared goals. This paper offers a comprehensive analysis of the factors influencing team efficiency and project success, providing actionable insights to enhance the effectiveness of collaborative programming education. By analyzing version control data, survey responses, and performance metrics, the study highlights the collaboration trends that emerge as first-semester students develop a 2D game project. Results indicate that students often slightly overestimate their contributions, with more engaged individuals more likely to acknowledge mistakes. Team performance shows no significant variation based on nationality or gender composition, though teams that disbanded frequently consisted of lone wolves, highlighting collaboration challenges and the need for strengthened teamwork skills. Presentations closely reflected individual project contributions, with active students excelling in evaluative questioning and performing better on the final exam. Additionally, the complete absence of plagiarism underscores the effectiveness of proactive academic integrity measures, reinforcing honest collaboration in educational settings.

Effective collaboration among large language model (LLM) agents in multi-agent systems requires sharing relevant evidence, requesting missing information, and incorporating teammates' contributions into decisions. Training these behaviors is challenging because final task outcomes provide limited feedback on the value of individual messages. We introduce CoSIR (Collaboration via Surprisal-based Information Rewards), a post-training approach that uses a simple, verifiable environment to teach collaboration behaviors that generalize to more complex, unseen tasks. We propose a Bayesian evaluator that scores shared information by its reduction in team surprisal, defined as the sum of the negative log probabilities assigned to the correct option given each agent's available evidence. Requests are scored by the potential reduction in the same quantity if the requested information were truthfully provided. Separate rewards encourage agents to use the received information in their private choices and calculations. We post-train Qwen3-4B, Qwen3-8B, and Gemma-3-4B-it through self-play and evaluate transfer to seven unseen natural-language collaboration tasks. CoSIR achieves the highest aggregate score, while its performance in general tasks remains competitive. Behavioral analyses show increased disclosure of private evidence and fewer judged failures to use teammates' input.

Multi-agent large language model (LLM) systems can improve reasoning by spending more computation, but deployment requires deciding when extra collaboration is worth its cost. We isolate this decision by running every problem under four protocols while holding the solver fixed within each setting: direct solving (Baseline), iterative self-correction (Single), planner-executor-reviewer collaboration (PER), and multi-agent deliberation (Broadcast). The primary benchmark comprises 4,181 competition-level math problems; paired robustness checks cover four benchmarks spanning competition math, biology, and broader science with two solver families. Across fixed policies, trained routers, and frozen LLM routers, conservative policies under-escalate, whereas higher-solve frozen routers often over-escalate. A post-answer, pre-collaboration gpt-oss-120b probe ranks Baseline failures with 0.8847 AUROC (4,151 parseable cases; 95% CI [0.8732, 0.8955]). The same score remains informative for predicting whether any collaboration helps (0.7683 AUPRC), but is much weaker for identifying PER- or Broadcast-specific value (0.1674 and 0.1041 AUPRC). Separately, the pre-answer self-confidence gate reaches 78.0% solve at 45K tokens, compared with 73.8% at 71.3K for a frozen gpt-oss-120b router and 92.4% for a retrospective fixed-order oracle. Across 10 paired model-condition settings, the oracle adds 23.2-58.3 points of retrospective coverage over Baseline, but protocol profiles vary by task. In the six settings with held-out router evaluations, oracle gaps remain 18.5-28.9 points. Confidence can therefore support initial escalation, while protocol-specific cost-aware routing remains unresolved.

Indic quality estimation (QE) and automatic post-editing (APE) data is spread across separate releases, so no single resource supports training and evaluation across tasks and language pairs on one footing. We consolidate the WMT 2020--2024 shared-task lineage with an extended English--Malayalam resource into \indicqe: 126{,}754 instances over nine directional pairs, with up to four label types aligned on the same segment, a direct assessment, a human post-edit, word-level OK/BAD tags and an error explanation, and a test set stratified over four difficulty axes. On it, we benchmark six prompted LLMs and three COMET metrics on segment-level QE, and three systems on APE. Two of the axes are defined partly on the direct assessment and select a compressed slice of it, so each axis is compared against a control drawn from the same language pair with the same score distribution. Only one survives that control: segments whose holistic and token-level quality signals conflict are ranked worse than equally-scored segments of the same language, for all nine systems and all seven pairs that carry the axis. Annotator disagreement, which looks second-hardest without the control, has no effect with it. Few-shot prompting costs every model leq 3.4B both correlation and output-format compliance. Within-language accuracy does not make scores comparable across pairs: of the three trained metrics, the one with the best within-language correlation loses most when the pairs are pooled. The benchmark and code will be released.

Many tasks revolve around editing a document, whether code or text. We formulate the revision similarity problem to unify a wide range of machine learning evaluation problems whose goal is to assess a revision to an existing document. We observe that revisions usually change only a small portion of an existing document, so the existing document and its immediate revisions share a majority of their content. We formulate five adequacy criteria for revision similarity measures, designed to align them with human judgement. We show that popular pairwise measures, like BLEU, fail to meet these criteria, because their scores are dominated by the shared content. They report high similarity between two revisions when humans would assess them as quite different. This is a fundamental flaw we address. We propose a novel static measure, Excision Score (ES), which computes longest common subsequence (LCS) to remove content shared by an existing document with the ground truth and predicted revisions, before comparing only the remaining divergent regions. This is analogous to a surgeon creating a sterile field to focus on the work area. We use approximation to speed the standard cubic LCS computation to quadratic. In code-editing evaluation, where static measures are often used as a cheap proxy for passing tests, we demonstrate that ES surpasses existing measures. When aligned with test execution on HumanEvalFix, ES improves over its nearest competitor, SARI, by 12% Pearson correlation and by >21% over standard measures like BLEU. The key criterion is invariance to shared context; when we perturb HumanEvalFix with increased shared context, ES' improvement over SARI increases to 20% and >30% over standard measures. ES also handles other corner cases that other measures do not, such as correctly aligning moved code blocks, and appropriately rewarding matching insertions or deletions.

This paper presents a scientometric analysis of research output from the University of Lagos, focusing on the two decades spanning 2004 to 2023. Using bibliometric data retrieved from the Web of Science, we examine trends in publication volume, collaboration patterns, citation impact, and the most prolific authors, departments, and research domains at the university. The study reveals a consistent increase in research productivity, with the highest publication output recorded in 2023. Health Sciences, Engineering, and Social Sciences are identified as dominant fields, reflecting the university's interdisciplinary research strengths. Collaborative efforts, both locally and internationally, show a positive correlation with higher citation impact, with the United States and the United Kingdom being the leading international collaborators. Notably, open-access publications account for a significant portion of the university's research output, enhancing visibility and citation rates. The findings offer valuable insights into the university's research performance over the past two decades, providing a foundation for strategic planning and policy formulation to foster research excellence and global impact.

We introduce the first version of KWBench (Knowledge Work Bench), a benchmark for unprompted problem recognition in large language models: can an LLM identify a professional scenario before attempting to solve it. Existing frontier benchmarks have saturated, and most knowledge-work evaluations to date reduce to extraction or task completion against a specification. KWBench targets the step before that: recognizing the governing structure of the situation from raw inputs alone. The benchmark contains 223 tasks sourced from practitioners across acquisitions, contract negotiations, clinical pharmacy, organizational politics, fraud analysis, and incentive design. Each task encodes a formal game-theoretic pattern (principal-agent conflict, signaling, mechanism design failure, strategic omission, coalitional dynamics, strategic interdependence) and carries structured ground truth recording the expert reading of the situation and the anticipated failure modes. Models receive raw data and a task prompt with no indication of problem type. Scoring is a three-tier rubric gated by a mandatory conjunctive check. Mandatory criteria encode the predicted wrong paths. We evaluate 16 models. The best model passes on 27.9% of tasks. The top two models agree on only 31.7% of their passes. Among the top 8, 44 tasks are solved by exactly one model; routing across the top 8 covers 50.7% of the benchmark, nearly double the best single model. Conditional on passing, quality scores converge (approx 83% across models); unconditional scores do not. Same models articulate the relevant game-theoretic concept correctly when asked, then fail to apply it unprompted. We release KWBench to shift how frontier models are evaluated on knowledge work, scoring them on whether they recognize the right problem from the situation alone, not only on how well they execute once the problem has been framed for them.

A benchmark score compares a system output against a reference, and methodological attention falls almost entirely on the first term. We measure the second. The retained annotation record of a six-language benchmark for personally identifiable information contains two independent annotator labellings, the aggregate shipped as gold, and a reviewer gold from independent expert re-annotation of a sample. Using it, we hold the scored output fixed and exchange the reference. The score moves by 4.95 F1 points for one output and 2.00 for the other (95% CIs [3.23, 6.27] and [0.26, 3.37]), and by 7.55 in the worst language. The comparison between two outputs moves as well: the paired interaction between reference and system is +2.95 points (CI [+1.97, +3.87]), survives correction for multiple testing, and changes one language's margin outright. The cause is an undocumented aggregation default that usually kept one annotator when adjudication did not fire, making the shipped reference a partial copy of an output being scored. We report the resulting reference-sensitivity band, show how to compute one from any retained annotation record, and argue that the quantity belongs beside the score.

Large Language Models (LLMs) are increasingly used as research collaborators for hypothesis refinement, methodological planning, and technical analysis across multi-turn interactions. In this setting, a useful assistant must be accurate, methodologically justified, logically consistent, and token-efficient. Current alignment approaches rarely achieve all of these together. Instruction-tuned models gain conversational quality through verbosity, and we show that science-agnostic general collaborative rewards compress responses at the expense of scientific rigor. We propose CollabSciReM, a goal-conditioned reward framework that decomposes the session-level reward into conversational quality, scientific rigor, and structural efficiency. We also introduce SciQuality, a pairwise evaluation of multi-turn research conversations grounded in 300 held-out scientific papers and scored on six dimensions: methodological soundness, justification, logical consistency, factual correctness, novelty, and responsiveness. Fine-tuned on 8.62K synthetic research conversations, CollabSciReM is preferred on SciQuality over a science-agnostic reward baseline trained on the same data for all four Llama and Qwen models, including a 65.3% win rate at matched response length. For the 7B and 8B models, CollabSciReM outperforms the science-agnostic reward baseline on the primary metric in 8 of 10 single- and multi-turn benchmark settings. In a blind study, domain experts rated CollabSciReM significantly higher on novelty than the general-reward variant and reported fewer hallucinated responses than both the general-reward variant and the base model.

We present the system description for our submission towards the Key Point Analysis Shared Task at ArgMining 2021. Track 1 of the shared task requires participants to develop methods to predict the match score between each pair of arguments and keypoints, provided they belong to the same topic under the same stance. We leveraged existing state of the art pre-trained language models along with incorporating additional data and features extracted from the inputs (topics, key points, and arguments) to improve performance. We were able to achieve mAP strict and mAP relaxed score of 0.872 and 0.966 respectively in the evaluation phase, securing 5th place on the leaderboard. In the post evaluation phase, we achieved a mAP strict and mAP relaxed score of 0.921 and 0.982 respectively. All the codes to generate reproducible results on our models are available on Github.

Existing multi-LLM collaboration systems often encounter scalability challenges when integrating new LLMs and tasks, leading to suboptimal performance. To address this, we propose SMCS, a Scalable Multi-LLM Collaboration System designed to effectively coordinate multiple open-source LLMs. The system consists of two core components: a Retrieval-based Prior Selection (RPS) module, which dynamically selects the most suitable LLMs for each input, and an Exploration-Exploitation-Driven Posterior Enhancement (EPE) module, which fosters response diversity and selects high-quality outputs through a hybrid scoring mechanism. Experiments on eight mainstream benchmarks validate the effectiveness of our system: by integrating fifteen open-source LLMs, SMCS outperforms prevailing closed-source LLMs, e.g., GPT-4.1(+5.36%) and GPT-o3-mini(+5.28%) across multiple tasks. Remarkably, it even exceeds the average of best results on different datasets with open-source LLMs (+2.86%), significantly advancing the empirical performance frontier of open-source collaboration. The code is released at https://github.com/magent4aci/SMCS.

When humans collaborate with AI agents on long-horizon tasks, what happens to the agents' contributions? For solving long-horizon tasks, humans place greater importance on ongoing interaction with AI agents (e.g., revising plans) than on an agent's ability to complete the task in a single attempt. However, most agentic benchmarks have focused more on automation. Strong performance on such benchmarks does not imply effective real-world collaboration. Professional workflows offer a useful setting, as they often involve interdependent steps. To address this gap, we introduce Kolab, a new dataset of 115+ hours of screen recordings of 50 professionals from 40 occupations collaborating with agents on realistic, long-horizon problems. Kolab also contains participants' collaboration and output quality judgments. Our analysis reveals diverse collaboration patterns, highlighting the importance of when and how professionals coordinate with agents. A collaborative agent must do two things that automation benchmarks never test: anticipate whether experts will adopt, modify, or reject its contribution once it leaves the chat window to guide its next steps, and assess collaboration quality from the unfolding workflow without constant expert feedback. Our benchmark operationalizes both: (1) forecasting how professionals use agent contributions at diverse workflows, and (2) verifying their judgments of collaboration satisfaction and output quality. Findings show that frontier models, both agentic and non-agentic, overestimate collaboration with experts and struggle to distinguish between high- and low-quality collaboration. Longer workflow context does not consistently improve these predictions. As frontier agents cannot yet understand long-horizon collaboration with experts, we position Kolab as a valuable dataset for studying human-agent collaboration grounded in real professional workflows.

Autonomous research agents produce competitive solutions and professional-looking manuscripts, yet their outputs contain verifiability failures undetectable by surface-level evaluation: fabricated citations, unreproducible scores, and method descriptions that diverge from the implementation. We address this through three contributions. First, Chain-of-Evidence (CoE), a verifiability framework requiring every claim to be traceable to its evidence source. Second, ScientistOne, an end-to-end autonomous research system that maintains evidence chains by construction throughout literature review, solution discovery, and paper writing. Third, CoE Audit, a post-hoc audit whose four integrity checks -- score verification, specification violation, reference verification, and method-code alignment -- apply uniformly to all systems. Across 75 papers spanning five systems and five frontier research tasks, every baseline exhibits at least one systematic failure mode: hallucinated reference rates reach 21%, score verification passes in as few as 42% of papers, and method-code alignment ranges from 20% to 80%. ScientistOne achieves zero hallucinated references (0/337), perfect score verification (12/12), and the highest method-code alignment (14/15), while matching or exceeding human expert performance on all five tasks. ScientistOne further generalizes to six additional tasks spanning medical imaging, fine-grained recognition, 3D perception, and language modeling, achieving state-of-the-art on Parameter Golf and gold medals on MLE-Bench tasks where baselines fail entirely.

Large Language Models are typically trained with next-turn rewards, limiting their ability to optimize for long-term interaction. As a result, they often respond passively to ambiguous or open-ended user requests, failing to help users reach their ultimate intents and leading to inefficient conversations. To address these limitations, we introduce CollabLLM, a novel and general training framework that enhances multiturn human-LLM collaboration. Its key innovation is a collaborative simulation that estimates the long-term contribution of responses using Multiturn-aware Rewards. By reinforcement fine-tuning these rewards, CollabLLM goes beyond responding to user requests, and actively uncovers user intent and offers insightful suggestions-a key step towards more human-centered AI. We also devise a multiturn interaction benchmark with three challenging tasks such as document creation. CollabLLM significantly outperforms our baselines with averages of 18.5% higher task performance and 46.3% improved interactivity by LLM judges. Finally, we conduct a large user study with 201 judges, where CollabLLM increases user satisfaction by 17.6% and reduces user spent time by 10.4%.

Reward models are a bottleneck for reinforcement learning in embodied AI. Long-horizon robotic manipulation requires scalable vision feedback beyond handcrafted rewards or task-specific annotations. Existing open-source VLM reward judges like RoboReward adopt simple 1--5 trajectory progress scoring, lacking pairwise preferences for RLHF, DPO and Bradley-Terry frameworks, while failing to optimize video scene understanding. Augmenting RoboReward with pairwise comparison and video-QA supervision causes inconsistency between pairwise preferences and pointwise scores, introducing training noise and hurting downstream performance---an issue aggregation methods such as TrustJudge cannot resolve. To address this, we propose TrustRoboReward, a multi-paradigm reward modeling framework equipped with Preference-Ordered Isotonic Score Editing (POISE). We construct a unified four-paradigm dataset with trajectory progress scoring (Score-A), video-QA answer quality scoring (Score-B), and their pairwise counterparts (Pair-A, Pair-B). Pairwise labels align better with human judgment than pointwise scores, inspiring us to calibrate pointwise scores to avoid score-pair reversals against pairwise preferences. POISE rectifies pointwise scores and eliminates cross-paradigm reversal conflicts unresolved by TrustJudge. Theoretically, POISE reduces score-pair reversal conflicts from 20.15% to 0%, whereas TrustJudge retains 20.46% conflicts on the same corpus. Evaluated on our benchmark, Qwen3-VL-4B trained with POISE achieves an overall reward score of 77.96%, nearly matching GPT-5-mini (78.09%, gap 0.13%) and outperforming the strongest RoboReward-4B baseline by 10.13%. It also lifts test-time score-pair consistency to 71.90%, exceeding RoboReward-4B (57.26%) and GPT-5-mini (68.09%). Integrating TrustJudge aggregation during inference boosts the overall score to 78.57%, surpassing the GPT-5-mini teacher model.

Comprehensively understanding and accurately predicting the performance of large language models across diverse downstream tasks has emerged as a pivotal challenge in NLP research. The pioneering scaling law on downstream works demonstrated intrinsic similarities within model families and utilized such similarities for performance prediction. However, they tend to overlook the similarities between model families and only consider design factors listed in the original scaling law. To overcome these limitations, we introduce a novel framework, Collaborative Performance Prediction (CPP), which significantly enhances prediction accuracy by leveraging the historical performance of various models on downstream tasks and other design factors for both model and task. We also collect a collaborative data sourced from online platforms containing both historical performance and additional design factors. With the support of the collaborative data, CPP not only surpasses traditional scaling laws in predicting the performance of scaled LLMs but also facilitates a detailed analysis of factor importance, an area previously overlooked.

Benchmarks play a central role in the development and governance of models, yet it is often unclear whether they actually measure the concepts they purport to measure (e.g., reasoning, refusal). We adapt convergent and discriminant validity from the social sciences into an approach for interrogating AI benchmarks, applying it to 56 capability and safety benchmarks across 53 models. We label benchmarks with substantively similar purported concepts to a shared assigned concept, and ask whether model rankings on benchmarks with the same assigned concept correlate more strongly than rankings on benchmarks with different assigned concepts. We ask analogous questions at the item level using item response theory (IRT) models. We find that correlations between model rankings on benchmarks with the same assigned safety concepts are often weak, suggesting these concepts may be conceptualized inconsistently across benchmarks. For assigned capability concepts (e.g., reasoning, knowledge), model rankings are often as strongly correlated among benchmarks with the same assigned concept as between benchmarks with different assigned concepts, suggesting these capability concepts may not discriminate well from one another. In some cases, benchmarks that share design elements (e.g., score format) correlate more strongly than benchmarks with the same assigned concept. Finally, some individual benchmarks correlate more strongly with benchmarks assigned a different concept than with benchmarks sharing their own assigned concept, suggesting they may measure a different concept than they purport to. For example, BBQ-accuracy correlates more strongly with benchmarks labeled reasoning than with benchmarks that share its assigned concept, bias. To support future empirical work on benchmark validity, we release our extensive dataset of model outputs and scores at the item- and benchmark-level.

The trajectory of AI development suggests that we will increasingly rely on agent-based systems composed of independently developed agents with different information, privileges, and tools. The success of these systems will critically depend on effective collaboration among these heterogeneous agents, even under partial observability. Despite intense interest, few empirical studies have evaluated such agent-agent collaboration at scale. We propose a collaborative maze-solving benchmark that (i) isolates collaborative capabilities, (ii) modulates problem complexity, (iii) enables scalable automated grading, and (iv) imposes no output-format constraints, preserving ecological plausibility. Using this framework, we evaluate 32 leading open- and closed-source models in solo, homogeneous, and heterogeneous pairings. Our results reveal a "collaboration gap": models that perform well solo often degrade substantially when required to collaborate. Collaboration can break down dramatically; for instance, small distilled models that solve mazes well alone may fail almost completely in certain pairings. We find that starting with the stronger agent often improves outcomes, motivating a "relay inference" approach where the stronger agent leads before handing off to the weaker one, closing much of the gap. Our findings argue for (1) collaboration-aware evaluation, (2) training strategies developed to enhance collaborative capabilities, and (3) interaction design that reliably elicits agents' latent skills, guidance that applies to AI-AI and human-AI collaboration.

Multi-agent cooperative tasks require different agents to execute a joint action simultaneously, and each agent's action affects both the observations and responses of the other agents. Hence, a world model is needed to predict the team return resulting from the joint actions of all agents. A naive extension directly applies a single-agent world model to each agent's action when predicting the team return step by step. However, such an extension fails to capture the dependencies among the simultaneous actions of multiple agents. We propose Multi-Agent World-Action Model (MA-WAM), a test-time planning framework that enables a frozen multi-agent flow policy to evaluate futures of candidate joint actions. To our knowledge, MA-WAM is the first test-time world-model planner for multi-agent flow policies. MA-WAM predicts the consequences of each joint action according to cross-agent dependencies and enables efficient candidate scoring. Across 30 offline multi-agent reinforcement learning (MARL) settings on MAMuJoCo, SMAC, and MPE, MA-WAM achieves mean relative gains of 22.0% over direct execution and 25.6% over uniform action selection. Under the standard evaluation protocol on an A100 GPU, MA-WAM adds 12.1 ms, accounting for 2.5% of the measured generation-and-scoring time.

Can AI systems trained on the scientific record up to a fixed point in time forecast the scientific advances that follow? Such a capability could help researchers identify collaborators and impactful research directions, and anticipate which problems and methods will become central next. We introduce PreScience -- a scientific forecasting benchmark that decomposes the research process into four interdependent generative tasks: collaborator prediction, prior work selection, contribution generation, and impact prediction. PreScience is a carefully curated dataset of 98K recent AI-related research papers, featuring disambiguated author identities, temporally aligned scholarly metadata, and a structured graph of companion author publication histories and citations spanning 502K total papers. We develop baselines and evaluations for each task, including LACERScore, a novel LLM-based measure of contribution similarity that outperforms previous metrics and approximates inter-annotator agreement. We find substantial headroom remains in each task -- e.g. in contribution generation, frontier LLMs achieve only moderate similarity to the ground-truth (GPT-5, averages 5.6 on a 1-10 scale). When composed into a 12-month end-to-end simulation of scientific production, the resulting synthetic corpus is systematically less diverse and less novel than human-authored research from the same period.

Many peer-review venues are using algorithms to assign submissions to reviewers. The crux of such automated approaches is the notion of the "similarity score" -- a numerical estimate of the expertise of a reviewer in reviewing a paper -- and many algorithms have been proposed to compute these scores. However, these algorithms have not been subjected to a principled comparison, making it difficult for stakeholders to choose the algorithm in an evidence-based manner. The key challenge in comparing existing algorithms and developing better algorithms is the lack of publicly available gold-standard data. We address this challenge by collecting a novel dataset of similarity scores that we release to the research community. Our dataset consists of 477 self-reported expertise scores provided by 58 researchers who evaluated their expertise in reviewing papers they have read previously. Using our dataset, we compare several widely used similarity algorithms and offer key insights. First, all algorithms exhibit significant error, with misranking rates between 12%-30% in easier cases and 36%-43% in harder ones. Second, most specialized algorithms are designed to work with titles and abstracts of papers, and in this regime the SPECTER2 algorithm performs best. Interestingly, classical TF-IDF matches SPECTER2 in accuracy when given access to full submission texts. In contrast, off-the-shelf LLMs lag behind specialized approaches.

Repository-level performance-optimization benchmarks such as GSO, SWE-Perf and SWE-fficiency evaluate coding agents by applying patches to real repositories and comparing runtime against unoptimized baselines and official reference patches. Their leaderboard scores are increasingly used as evidence of coding-agent progress, but those scores can conflate runtime instability, benchmark-specific scoring rules, and how many tasks are already solved by at least one public submission. We audit these issues across the three benchmarks. First, we replay the official reference patches for 740 code optimization tasks across four common types of Google Cloud machines. Most benchmark tasks can be replayed, but their reference patches satisfy the original benchmark validity rules in every cross-machine replay for only 39/102 GSO tasks, 11/140 SWE-Perf tasks, and 411/498 SWE-fficiency tasks; SWE-Perf is especially fragile because many reference patches produce close-to-zero runtime changes. Second, we show that public submission rankings depend strongly on the benchmark scoring rule. Among eight public submissions shared by GSO and SWE-fficiency, the official rankings disagree on 9 of 28 pairwise submission comparisons, and SWE-fficiency's leaderboard scoring rule assigns the worst ten tasks overly high score weights of 58.5%-82.8%. Third, looking across 10 public submissions for each task, we find that at least one submission matches or beats the reference patch on 85.3% (384/450) of replay-valid GSO and SWE-fficiency tasks, and beats the unoptimized base code on 99.8% (449/450). Our study complements leaderboard scores by identifying tasks with more reliable performance signals, quantifying per-task score contributions, and exposing the remaining performance gaps that are hidden by aggregate rankings.

With the advent of highly capable instruction-tuned neural language models, benchmarking in natural language processing (NLP) is increasingly shifting towards pairwise comparison leaderboards, such as LMSYS Arena, from traditional global pointwise scores (e.g., GLUE, BIG-bench, SWE-bench). This paper empirically investigates the strengths and weaknesses of both global scores and pairwise comparisons to aid decision-making in selecting appropriate model evaluation strategies. Through computational experiments on synthetic and real-world datasets using standard global metrics and the popular Bradley-Terry model for pairwise comparisons, we found that while global scores provide more reliable overall rankings, they can underestimate strong models with rare, significant errors or low confidence. Conversely, pairwise comparisons are particularly effective for identifying strong contenders among models with lower global scores, especially where quality metrics are hard to define (e.g., text generation), though they require more comparisons to converge if ties are frequent. Our code and data are available at https://github.com/HSPyroblast/srw-ranking under a permissive license.

Coopetition refers to simultaneous cooperation and competition among actors wherein actors 'cooperate to grow the pie and compete to split it up.' Modern socio-technical systems are characterized by strategic coopetition wherein actors concomitantly cooperate to create value and compete to capture it. While conceptual modeling languages such as i* provide rich qualitative representations of strategic dependencies, they lack mechanisms for quantitative analysis of dynamic trade-offs. Conversely, classical game theory offers mathematical rigor but strips away contextual richness. This report bridges this gap by developing computational foundations that formalize two critical dimensions of coopetition: interdependence and complementarity. We ground interdependence in i* structural dependency analysis, translating depender-dependee-dependum relationships into quantitative interdependence coefficients via a structured translation framework. We formalize complementarity following Brandenburger and Nalebuff's Added Value concept, modeling synergistic value creation with validated parameterization. We integrate structural dependencies with bargaining power in value appropriation and introduce a game-theoretic formulation where Nash Equilibrium incorporates structural interdependence. Validation combines over 22,000 experimental trials across power and logarithmic specifications with the Samsung-Sony S-LCD joint venture (2004-2011). Under strict historical alignment scoring, logarithmic specifications achieve 58/60 compared to power functions (46/60), producing realistic 41% cooperation increases aligning with documented S-LCD patterns while power functions produce 166% increases exceeding realistic bounds. Statistical significance confirmed at p < 0.001, Cohen's d > 9.

Relevance and fairness are two major objectives of recommender systems (RSs). Recent work proposes measures of RS fairness that are either independent from relevance (fairness-only) or conditioned on relevance (joint measures). While fairness-only measures have been studied extensively, we look into whether joint measures can be trusted. We collect all joint evaluation measures of RS relevance and fairness, and ask: How much do they agree with each other? To what extent do they agree with relevance/fairness measures? How sensitive are they to changes in rank position, or to increasingly fair and relevant recommendations? We empirically study for the first time the behaviour of these measures across 4 real-world datasets and 4 recommenders. We find that most of these measures: i) correlate weakly with one another and even contradict each other at times; ii) are less sensitive to rank position changes than relevance- and fairness-only measures, meaning that they are less granular than traditional RS measures; and iii) tend to compress scores at the low end of their range, meaning that they are not very expressive. We counter the above limitations with a set of guidelines on the appropriate usage of such measures, i.e., they should be used with caution due to their tendency to contradict each other and of having a very small empirical range.

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.

Qualitative research faces a critical reliability challenge: traditional inter-rater agreement methods require multiple human coders, are time-intensive, and often yield moderate consistency. We present a multi-perspective validation framework for LLM-based thematic analysis that combines ensemble validation with dual reliability metrics: Cohen's Kappa (κ) for inter-rater agreement and cosine similarity for semantic consistency. Our framework enables configurable analysis parameters (1-6 seeds, temperature 0.0-2.0), supports custom prompt structures with variable substitution, and provides consensus theme extraction across any JSON format. As proof-of-concept, we evaluate three leading LLMs (Gemini 2.5 Pro, GPT-4o, Claude 3.5 Sonnet) on a psychedelic art therapy interview transcript, conducting six independent runs per model. Results demonstrate Gemini achieves highest reliability (κ= 0.907, cosine=95.3%), followed by GPT-4o (κ= 0.853, cosine=92.6%) and Claude (κ= 0.842, cosine=92.1%). All three models achieve a high agreement (κ> 0.80), validating the multi-run ensemble approach. The framework successfully extracts consensus themes across runs, with Gemini identifying 6 consensus themes (50-83% consistency), GPT-4o identifying 5 themes, and Claude 4 themes. Our open-source implementation provides researchers with transparent reliability metrics, flexible configuration, and structure-agnostic consensus extraction, establishing methodological foundations for reliable AI-assisted qualitative research.

While Large Language Models (LLMs) excel on standardized medical exams, high scores often fail to translate to high-quality responses for real-world medical queries. Current evaluations rely heavily on multiple-choice questions, failing to capture the unstructured, ambiguous, and long-tail complexities inherent in genuine user inquiries. To bridge this gap, we introduce QuarkMedBench, an ecologically valid benchmark tailored for real-world medical LLM assessment. We compiled a massive dataset spanning Clinical Care, Wellness Health, and Professional Inquiry, comprising 20,821 single-turn queries and 3,853 multi-turn sessions. To objectively evaluate open-ended answers, we propose an automated scoring framework that integrates multi-model consensus with evidence-based retrieval to dynamically generate 220,617 fine-grained scoring rubrics (~9.8 per query). During evaluation, hierarchical weighting and safety constraints structurally quantify medical accuracy, key-point coverage, and risk interception, effectively mitigating the high costs and subjectivity of human grading. Experimental results demonstrate that the generated rubrics achieve a 91.8% concordance rate with clinical expert blind audits, establishing highly dependable medical reliability. Crucially, baseline evaluations on this benchmark reveal significant performance disparities among state-of-the-art models when navigating real-world clinical nuances, highlighting the limitations of conventional exam-based metrics. Ultimately, QuarkMedBench establishes a rigorous, reproducible yardstick for measuring LLM performance on complex health issues, while its framework inherently supports dynamic knowledge updates to prevent benchmark obsolescence.

LLM-based multi-agent collaboration is increasingly used to solve complex tasks by dividing work among specialized agents and integrating complementary expertise. Yet existing systems and evaluations largely rest on an implicit perfect-colleague assumption: collaborators provide correct and complete information and respond promptly to requests. In realistic teamwork, however, collaborators may return information that does not answer the intended question, provide insufficient detail to support a decision, or fail to respond to a request. To separate task-solving competence from the ability to recover an unreliable evidence-gathering process, we introduce the Unreliable Colleagues Benchmark (UnCoBench), which organizes behavioral failures through Misaligned, Incomplete, and Missed settings. The main agent need to verify contextual correctness, diagnose information gap and track unresolved dependencies in order to obtain the correct evidence for solving the task. We also introduce a verifiable and scalable automated generation pipeline that pairs LLM-based scenario generation with executable checks of answer uniqueness and role necessity. Results across ten models show that similar reliable-setting performance can result in different robustness to unreliable evidence. Trace analysis reveals frequent omissions of corrective follow-up, and the recovery behavior involves inefficient waiting and redundant queries. These findings show that robust collaboration requires not only sound reasoning, but also targeted action to diagnose evidence failures, recover relevant information, and integrate it into decisions. Our data and source code are available at https://github.com/iNLP-Lab/UnCoBench.

Graph-augmented retrieval combines dense similarity with graph-based relevance signals such as Personalized PageRank (PPR), but these scores have different distributions and are not directly comparable. We study this as a score calibration problem for heterogeneous retrieval fusion in multi-hop question answering. Our method, PhaseGraph, maps vector and graph scores to a common unit-free scale using percentile-rank normalization (PIT) before fusion, enabling stable combination without discarding magnitude information. Across MuSiQue and 2WikiMultiHopQA, calibrated fusion improves held-out last-hop retrieval on HippoRAG2-style benchmarks: LastHop@5 increases from 75.1% to 76.5% on MuSiQue (8W/1L, p=0.039) and from 51.7% to 53.6% on 2WikiMultiHopQA (11W/2L, p=0.023), both on independent held-out test splits. A theory-driven ablation shows that percentile-based calibration is directionally more robust than min-max normalization on both tune and test splits (1W/6L, p=0.125), while Boltzmann weighting performs comparably to linear fusion after calibration (0W/3L, p=0.25). These results suggest that score commensuration is a robust design choice, and the exact post-calibration operator appears to matter less on these benchmarks.

Can LLM agents make contributions to frontier computer science R&D? We introduce FrontierCS 2, a benchmark of 48 open-ended tasks. We take a paper and the code its authors released and delete the paper's contribution. The deleted code becomes the human reference that sets the bar. Earlier open-ended benchmarks give each agent a problem statement and grade one program after the run. FrontierCS 2 places the agent inside a research environment. The agent inherits a working repository and may submit a patch at any point. For each patch, a judge returns a development-suite score but keeps the evaluator, the held-out final suite and the reference private, and grades the final submission on that suite against the reference. The tasks span 13 domains, from machine-learning systems and high-performance computing to databases, security and robotics. Beyond these 48 tasks, FrontierCS 2 keeps a private set of more than 100 tasks, to be announced in the future. We evaluate 12 agents. The best one is Claude Opus 5.5, passing 58% of its runs. No run passes on 16 tasks. A higher score is not the same as a pass: most runs that beat the reference on the combined final score still fall short on some metric or workload. On a shared capability scale for agents and tasks, the median task is roughly as difficult as what the strongest agent can handle.

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.

Large language models (LLMs) are currently applied to scientific paper evaluation by assigning an absolute score to each paper independently. However, since score scales vary across conferences, time periods, and evaluation criteria, models trained on absolute scores are prone to fitting narrow, context-specific rules rather than developing robust scholarly judgment. To overcome this limitation, we propose shifting paper evaluation from isolated scoring to collaborative ranking. In particular, we design Comparison-Native framework for Paper Evaluation (CNPE), integrating comparison into both data construction and model learning. We first propose a graph-based similarity ranking algorithm to facilitate the sampling of more informative and discriminative paper pairs from a collection. We then enhance relative quality judgment through supervised fine-tuning and reinforcement learning with comparison-based rewards. At inference, the model performs pairwise comparisons over sampled paper pairs and aggregates these preference signals into a global relative quality ranking. Experimental results demonstrate that our framework achieves an average relative improvement of 21.8\% over the strong baseline DeepReview-14B, while exhibiting robust generalization to five previously unseen datasets. https://github.com/ECNU-Text-Computing/ComparisonReview{Code}.

Background: Agent skills are increasingly deployed as modular, reusable capability units in AI agent systems. Medical research agent skills require safeguards beyond general-purpose evaluation, including scientific integrity, methodological validity, reproducibility, and boundary safety. This study developed and preliminarily evaluated a domain-specific audit framework for medical research agent skills, with a focus on reliability against expert review. Methods: We developed MedSkillAudit (skill-auditor@1.0), a layered framework assessing skill release readiness before deployment. We evaluated 75 skills across five medical research categories (15 per category). Two experts independently assigned a quality score (0-100), an ordinal release disposition (Production Ready / Limited Release / Beta Only / Reject), and a high-risk failure flag. System-expert agreement was quantified using ICC(2,1) and linearly weighted Cohen's kappa, benchmarked against the human inter-rater baseline. Results: The mean consensus quality score was 72.4 (SD = 13.0); 57.3% of skills fell below the Limited Release threshold. MedSkillAudit achieved ICC(2,1) = 0.449 (95% CI: 0.250-0.610), exceeding the human inter-rater ICC of 0.300. System-consensus score divergence (SD = 9.5) was smaller than inter-expert divergence (SD = 12.4), with no directional bias (Wilcoxon p = 0.613). Protocol Design showed the strongest category-level agreement (ICC = 0.551); Academic Writing showed a negative ICC (-0.567), reflecting a structural rubric-expert mismatch. Conclusions: Domain-specific pre-deployment audit may provide a practical foundation for governing medical research agent skills, complementing general-purpose quality checks with structured audit workflows tailored to scientific use cases.

Leaderboards rank frontier models on independent axes but do not reveal whether capabilities reinforce or trade off across releases -- and at the frontier, this interaction is the more informative signal. We decompose paired SWE-bench and GPQA Diamond scores into a population coupling trend and per-release residual (h-field) that diagnoses capability emphasis and identifies which measurement or stress test is most informative next. Across 34 models from 10 labs (2024--2026), capabilities cooperate (r = +0.72, p < 10^{-6}), but cooperation varies by lab and over time: DeepSeek reversed from reasoning-rich to coding-first (h: +11.2 to -4.7, 15.9-pp swing); Google maintains consistent reasoning emphasis; Anthropic oscillates between coding excursions and recovery. Cooperation is not static -- it cascades. Six open-weight architectures confirm a second capability transition at 30--72B, and SWE-bench is now saturating while HLE and instruction-following retain discriminatory spread -- signaling the next axis rotation. We provide a three-level playbook (locate, diagnose, rotate), a per-lab measurement-priority table, and seven falsifiable predictions with timestamped criteria for the next 12 months of frontier releases. Per-lab coupling slopes vary 5times (Google 1.15 vs. DeepSeek 0.23), quantifying how efficiently each recipe converts coding gains into reasoning. Five April 2026 releases confirm the diagnostic out of sample (r rises from +0.72 to +0.75). An interactive dashboard provides phase classification with actionable recommendations, h-field diagnostics, per-lab coupling trajectories, ODE-based scaling predictions, benchmark rotation guidance, self-steering demo, and live tracking of all seven predictions: https://zehenlabs.com/cape/.

We introduce DoGBENCH (Documentation Generation Benchmark), to our knowledge, the first benchmark for generating and maintaining real user-facing software documentation. It asks whether an agent can produce documentation that experienced technical writers would accept in review. The benchmark contains 292 items from open source projects, including Helm, PostHog, and Mautic. Each item gives the agent a pre-change repository and a trigger, such as a code pull request or a reported documentation gap. The agent must first decide whether the documentation needs an update. For items that need one, the agent must produce an acceptable patch in one attempt. For items that do not need updates, the agent must abstain. Task-specific rubrics, validated with project maintainers, score each patch on accuracy, completeness, reader guidance, placement, and repository conventions. The composite score combines patch quality with correct abstention, and a score of 100 means an agent meets every requirement for the task. Scores should not be interpreted as a percentage of an expert's capability. We evaluated seven agents. The highest-scoring agent reached 47.3 out of 100 on the 117-item held-out split. In a separate audit of 1,267 patches, the most common failure modes were task-completion gaps (45.5%), technical inaccuracies (36.6%), and incomplete conceptual or reference coverage (32.5%). Analysis of the corresponding trajectories identified three key patterns associated with these failures: (1) describing interfaces without examining how readers use them (36.0%), (2) missing decisive evidence and filling the gaps with plausible assumptions (33.1%), and (3) stopping after finding the first plausible documentation surface and leaving other affected pages stale (30.1%).

This paper presents a comprehensive study on resume classification to reduce the time and labor needed to screen an overwhelming number of applications significantly, while improving the selection of suitable candidates. A total of 6,492 resumes are extracted from 24,933 job applications for 252 positions designated into four levels of experience for Clinical Research Coordinators (CRC). Each resume is manually annotated to its most appropriate CRC position by experts through several rounds of triple annotation to establish guidelines. As a result, a high Kappa score of 61% is achieved for inter-annotator agreement. Given this dataset, novel transformer-based classification models are developed for two tasks: the first task takes a resume and classifies it to a CRC level (T1), and the second task takes both a resume and a job description to apply and predicts if the application is suited to the job T2. Our best models using section encoding and multi-head attention decoding give results of 73.3% to T1 and 79.2% to T2. Our analysis shows that the prediction errors are mostly made among adjacent CRC levels, which are hard for even experts to distinguish, implying the practical value of our models in real HR platforms.

AI agents are reshaping the workspace, leading to drastic change of how humans work. Despite the considerable potential of human-agent collaboration both in preserving human agency and generating economic value, this paradigm remains largely absent from occupational task evaluation, hindered by the difficulty of gathering real human data and accounting for inter-human variability. We introduce CollabSkill, a framework for evaluating human-agent collaboration on real-world occupational tasks. CollabSkill pairs real human workers with AI agents on tasks matched to their occupational background, collecting data that capture the complexity of economically valuable tasks and the usage patterns of real workers. To account for inter-human variability, CollabSkill employs a Bayesian skill rating system to disentangle and quantify the skill contributions of both humans and AI agents. Drawing on over 1,500 prompts from 386 working sessions contributed by 93 human workers, our analysis yields insights on two fronts: on the agent side, rankings on CollabSkill diverge meaningfully from those of existing fully autonomous benchmarks where Codex leads, with Claude Code ranking first; on the human side, CollabSkill reveals that practical experience emerges as the primary driver of collaboration skill, with hands-on collaboration meaningfully shifting workers' AI literacy. Together, we hope CollabSkill enables the community to invest in systematic evaluation of human-agent collaboration and spurs development efforts aimed at building AI agents that genuinely augment human workers.

Human intelligence thrives on the concept of cognitive synergy, where collaboration and information integration among different cognitive processes yield superior outcomes compared to individual cognitive processes in isolation. Although Large Language Models (LLMs) have demonstrated promising performance as general task-solving agents, they still struggle with tasks that require intensive domain knowledge and complex reasoning. In this work, we propose Solo Performance Prompting (SPP), which transforms a single LLM into a cognitive synergist by engaging in multi-turn self-collaboration with multiple personas. A cognitive synergist refers to an intelligent agent that collaborates with multiple minds, combining their individual strengths and knowledge, to enhance problem-solving and overall performance in complex tasks. By dynamically identifying and simulating different personas based on task inputs, SPP unleashes the potential of cognitive synergy in LLMs. We have discovered that assigning multiple, fine-grained personas in LLMs elicits better problem-solving abilities compared to using a single or fixed number of personas. We evaluate SPP on three challenging tasks: Trivia Creative Writing, Codenames Collaborative, and Logic Grid Puzzle, encompassing both knowledge-intensive and reasoning-intensive types. Unlike previous works, such as Chain-of-Thought, that solely enhance the reasoning abilities in LLMs, SPP effectively elicits internal knowledge acquisition abilities, reduces hallucination, and maintains strong reasoning capabilities. Code, data, and prompts can be found at: https://github.com/MikeWangWZHL/Solo-Performance-Prompting.git.

AI evaluations are widely used for testing and understanding progress. However, the diverse evaluators bring with them inconsistencies that challenge analysis and comparison. First, results are saved in incompatible formats, scattered across leaderboards, papers, blog posts, evaluation harness logs, and custom repositories. Second, results are created by different evaluation frameworks, which produce divergent scores for nominally identical evaluations and record metadata inconsistently, hindering comparison, cross-community evaluation science, cost reduction, and reuse. We introduce Every Eval Ever, the first shared schema and community-crowdsourced repository for AI evaluation results. The schema standardizes how evaluations are represented in a unified, single JSON document. It is source-agnostic by design, ingesting results from evaluation harnesses and papers alike, and optionally stores per-instance outputs for fine-grained analysis. We contribute: (i) a community-governed metadata schema with a companion instance-level schema, the first standardization effort of its kind; (ii) automatic converters from popular formats, evaluation harnesses, and leaderboards to the unified schema; and (iii) a crowdsourced community database hosted on Hugging Face, currently spanning to date 22,235 models, 2,273 unique benchmarks, and 31 evaluation formats.

Large Language Models (LLMs) vary in their abilities on a range of tasks. Initiatives such as the Open LLM Leaderboard aim to quantify these differences with several large benchmarks (sets of test items to which an LLM can respond either correctly or incorrectly). However, high correlations within and between benchmark scores suggest that (1) there exists a small set of common underlying abilities that these benchmarks measure, and (2) items tap into redundant information and the benchmarks may thus be considerably compressed. We use data from n > 5000 LLMs to identify the most informative items of six benchmarks, ARC, GSM8K, HellaSwag, MMLU, TruthfulQA and WinoGrande (with d=28,632 items in total). From them we distill a sparse benchmark, metabench, that has less than 3% of the original size of all six benchmarks combined. This new sparse benchmark goes beyond point scores by yielding estimators of the underlying benchmark-specific abilities. We show that these estimators (1) can be used to reconstruct each original individual benchmark score with, on average, 1.5% root mean square error (RMSE), (2) reconstruct the original total score with 0.8% RMSE, and (3) have a single underlying common factor whose Spearman correlation with the total score is r = 0.93.

Software engineering (SE) is increasingly collaborative, with developers working together on shared complex codebases. Effective collaboration in shared environments requires participants -- whether humans or AI agents -- to stay on the same page as their environment evolves. When a collaborator's understanding diverges from the current state -- what we term the out-of-sync challenge -- the collaborator's actions may fail, leading to integration issues. In this work, we introduce SyncMind, a framework that systematically defines the out-of-sync problem faced by large language model (LLM) agents in collaborative software engineering (CSE). Based on SyncMind, we create SyncBench, a benchmark featuring 24,332 instances of agent out-of-sync scenarios in real-world CSE derived from 21 popular GitHub repositories with executable verification tests. Experiments on SyncBench uncover critical insights into existing LLM agents' capabilities and limitations. Besides substantial performance gaps among agents (from Llama-3.1 agent <= 3.33% to Claude-3.5-Sonnet >= 28.18%), their consistently low collaboration willingness (<= 4.86%) suggests fundamental limitations of existing LLM in CSE. However, when collaboration occurs, it positively correlates with out-of-sync recovery success. Minimal performance differences in agents' resource-aware out-of-sync recoveries further reveal their significant lack of resource awareness and adaptability, shedding light on future resource-efficient collaborative systems. Code and data are openly available on our project website: https://xhguo7.github.io/SyncMind/.

The remarkable success of Large Language Models (LLMs) has ushered natural language processing (NLP) research into a new era. Despite their diverse capabilities, LLMs trained on different corpora exhibit varying strengths and weaknesses, leading to challenges in maximizing their overall efficiency and versatility. To address these challenges, recent studies have explored collaborative strategies for LLMs. This paper provides a comprehensive overview of this emerging research area, highlighting the motivation behind such collaborations. Specifically, we categorize collaborative strategies into three primary approaches: Merging, Ensemble, and Cooperation. Merging involves integrating multiple LLMs in the parameter space. Ensemble combines the outputs of various LLMs. Cooperation} leverages different LLMs to allow full play to their diverse capabilities for specific tasks. We provide in-depth introductions to these methods from different perspectives and discuss their potential applications. Additionally, we outline future research directions, hoping this work will catalyze further studies on LLM collaborations and paving the way for advanced NLP applications.

Existing multi-agent benchmarks primarily test in competitive settings, short-horizon interactions under 20 steps, or simply aggregate individual performance, failing to isolate and highlight genuine collaboration capabilities of LLM-based agents. We introduce AgentWorld, a benchmark of 100 human-annotated tasks (with 100 augmented variants) for evaluating long-horizon, multi-agent collaboration. Tasks span 50+ interaction rounds across a rich MMORPG sandbox and require 3-20 agents with asymmetric roles and abilities to coordinate through communication, joint planning, and resource sharing under a blackbox setting where each agent acts independently without access to others' internal states. To quantify collaboration effectiveness in addition to conventional binary task success, we propose Causal Collaboration Effectiveness (CCE), a graph-based metric that traces causal dependencies between agent actions and measures what fraction of a team's effort actually contributed to the outcome. Experiments with Gemini 3 Flash, Claude Haiku 4.5, GPT-5 Mini, and DeepSeek R1-70B show that even the best model achieves only 52.0% task success, with systematic failure modes including communication breakdowns, role confusion, and inability to maintain shared plans across rounds. AgentWorld is fully open-source.

Recently, using a powerful proprietary Large Language Model (LLM) (e.g., GPT-4) as an evaluator for long-form responses has become the de facto standard. However, for practitioners with large-scale evaluation tasks and custom criteria in consideration (e.g., child-readability), using proprietary LLMs as an evaluator is unreliable due to the closed-source nature, uncontrolled versioning, and prohibitive costs. In this work, we propose Prometheus, a fully open-source LLM that is on par with GPT-4's evaluation capabilities when the appropriate reference materials (reference answer, score rubric) are accompanied. We first construct the Feedback Collection, a new dataset that consists of 1K fine-grained score rubrics, 20K instructions, and 100K responses and language feedback generated by GPT-4. Using the Feedback Collection, we train Prometheus, a 13B evaluator LLM that can assess any given long-form text based on customized score rubric provided by the user. Experimental results show that Prometheus scores a Pearson correlation of 0.897 with human evaluators when evaluating with 45 customized score rubrics, which is on par with GPT-4 (0.882), and greatly outperforms ChatGPT (0.392). Furthermore, measuring correlation with GPT-4 with 1222 customized score rubrics across four benchmarks (MT Bench, Vicuna Bench, Feedback Bench, Flask Eval) shows similar trends, bolstering Prometheus's capability as an evaluator LLM. Lastly, Prometheus achieves the highest accuracy on two human preference benchmarks (HHH Alignment & MT Bench Human Judgment) compared to open-sourced reward models explicitly trained on human preference datasets, highlighting its potential as an universal reward model. We open-source our code, dataset, and model at https://github.com/kaistAI/Prometheus.

The quality of training data fundamentally determines the capabilities of large language models (LLMs), yet no unified benchmark exists to measure how well LLMs, agents, and data-centric workflows actually prepare training data end to end. We view LLM-driven data preparation as comprising two complementary capabilities: data construction, which transforms raw sources into supervised training data, and data quality evaluation, which predicts the training value of candidate datasets before downstream training; throughout, "quality" refers to downstream training utility rather than surface-level textual properties. We introduce DataPrep-Bench, the first unified benchmark that jointly evaluates both capabilities under a shared downstream-grounded protocol over six domains and multiple base models. For data construction, methods consume identical raw sources and are scored by fine-tuning a base model on their outputs jointly with Dolly-15k; alongside this track we release Data-Construction-Skill, a skill-guided agent that lifts the Dolly-only baseline by nearly 20 points absolute on Llama-3.1-8B Finance and is competitive with the strongest agent- and DataFlow-based methods in knowledge-extraction-dense domains. For data quality evaluation, scoring functions are scored by Pearson correlation with downstream performance on a shared candidate pool; we release the Distributional Alignment Score (DAS), a distribution-based evaluator that uses MMD between a candidate dataset and a domain proxy. DAS attains the strongest cross-model correlation in four of six domains and is the only metric clearing r > 0.70 simultaneously in Math, Science, and Medical, outperforming existing quality-, diversity-, and heuristic-based evaluators. DataPrep-Bench provides a unified, downstream-grounded framework for measuring progress on both capabilities as co-equal targets of LLM-driven data preparation.

Agent benchmarks are increasingly used to compare large language models (LLMs) and guide deployment decisions, yet benchmark scores are meaningful only if they measure model capability rather than properties of the evaluation pipeline. We identify a double measurement confound: execution-critical decisions are performed by a fixed scaffold instead of the model, while the scorer evaluates outputs using criteria that may not reflect task correctness. We unify these issues within a measurement-theoretic framework that characterizes when benchmark scores can be interpreted as evidence of model capability, and instantiate it with an audit-and-repair protocol that (i) transfers execution-critical decisions from the scaffold to the model, (ii) replaces shape-based evaluation with seeded ground-truth scoring, and (iii) reports reliability beyond the mean through worst-case and tail-risk metrics. Experiments on ComtradeBench show that the joint intervention transforms a nearly flat leaderboard into a reliability spectrum that distinguishes both average performance and robustness across seeds. Applying the audit to existing benchmarks further shows that scorer validity is benchmark-specific, whereas scaffold ownership is an uncontrolled axis wherever we probed it. Our results suggest that benchmark scores should be interpreted together with their scaffolding level, scoring criterion, and reliability profile, providing a practical framework for more valid evaluation of LLM agents.

Scientific coding agents receive equations, boundary conditions, and output requirements in writing, then must assess the programs they revise. Rules to Tools (R2T) supplies prepared executable checks of public scientific requirements. Matched SciCode repair groups share written checks, starting programs, model, and budgets; the tool group receives a callable implementation. Across two task-ID cohorts, complete repair is 26/30 with text and 29/30 with the prepared checks. Three task IDs favor tools, one favors text, and eleven tie. The eight-ID cohort scores 13/16 versus 15/16, with a task-cluster bootstrap 95% interval of [-12.5, 43.75] percentage points for the difference. The larger shared-definition SciCode cohort ties at 13/24 per group. Five development-exposed tasks with alternate starting programs score 3/10 versus 7/10. The tool group favors tasks 17, 77, and 11; initial checks flag task 17 and report no violation for tasks 77 and 11. Task 37 favors text and has no initial reported violation. A fresh source-through-Python arm also reaches 15/16, matching the dedicated command's aggregate. In a matched PDE comparison, detailed text scores 23/24 and checks score 24/24, with 31.2% lower reported model output for checks. Agent-side output savings vary by cohort, while public CPU use rises in both task-ID cohorts. These results measure task-dependent repair outcomes and agent-side costs with prepared checks.

Multi-agent systems built from large language models are deployed widely, yet how much performance is lost when two LLMs must coordinate rather than act alone remains unclear. We formulate the collaboration tax as the team-decentralisation loss of a two-player cooperative game with private information, with two propositions characterising its sign and its equivalence to a max-superadditivity violation. We operationalise this definition on 32 solo-tractable tasks grouped by source of grounding friction and measure it on 11 models from 7 providers. The tax is structured along two no-exception axes: a category ordering across every model and a monotonic decrease with capability. The proximate mechanism is not a reasoning deficit but a four-stage conversational cascade in which agents make ungrounded claims, fail to query the partner, skip integrating both views, and accept the answer without re-derivation. The tax is mechanically predictable from conversation features and partly tractable: a prompt intervention targeting all four stages closes a substantial fraction of the gap, with the dominant bottleneck differing across categories. In heterogeneous pairs the tax is pulled toward the stronger partner rather than the additive midpoint, empirically realising the max-superadditivity violation predicted by our framework. Together these results recast collaboration in LLM systems as a measurable, predictable, and partly tractable cost.

Recent advances in human preference alignment have significantly enhanced multimodal generation and understanding. A key approach is training reward models to guide preference optimization. However, existing models are often task-specific, limiting their adaptability across diverse visual applications. We also argue that jointly learning to assess multiple tasks may foster a synergistic effect, where improved image understanding enhances image generation assessment, and refined image evaluation benefits video assessment through better frame analysis. To this end, this paper proposes UnifiedReward, the first unified reward model for multimodal understanding and generation assessment, enabling both pairwise ranking and pointwise scoring, which can be employed for vision model preference alignment. Specifically, (1) we first develop UnifiedReward on our constructed large-scale human preference dataset, including both image and video generation/understanding tasks. (2) Then, it is utilized to automatically construct high-quality preference pair data based on the vision models, fine-gradually filtering their outputs through pair ranking and point sifting. (3) Finally, these data are used for their preference alignment through Direct Preference Optimization (DPO). Experimental results demonstrate that joint learning to assess diverse visual tasks can lead to substantial mutual benefits and we apply our pipeline to both image and video understanding/generation tasks, significantly improving the performance in each domain.

Machine unlearning in Vision-Language Models (VLMs) is required for compliance with the General Data Protection Regulation (GDPR), yet current evaluation practices are inconsistent. We present the first systematic study of metric reliability in multimodal unlearning. Five standard metrics, Forget Accuracy (FA), Retain Accuracy (RA), Membership Inference Attack (MIA), Activation Distance (AD), and JS divergence (JS), yield conflicting method rankings across three VQA benchmarks (MLLMU-Bench, UnLOK-VQA, MMUBench). Kendall tau analysis over 36 unlearned LLaVA-1.5-7B models reveals two opposing clusters, {FA, RA, MIA} and {AD, JS}, with tau_FA_AD = -0.26, reproduced on BLIP-2 OPT-2.7B. Agreement is lower in multimodal VQA (average tau = 0.086) than in unimodal classification (average tau = 0.158; difference = 0.072), indicating that dual image-and-text pathways amplify inconsistency. We introduce the Unified Quality Score (UQS), a composite metric with weights derived from each metric's Spearman correlation with the oracle distance d(M_hat, M_star), where M_star is the oracle model retrained only on the retain set. RA shows the strongest reliability (rho = 0.484, p = 0.003), while FA is negatively correlated (rho = -0.418, p = 0.011). UQS yields stable rankings under 100 random weight perturbations (tau = 0.647 +- 0.262). We release the benchmark, 36 checkpoints, and an interactive leaderboard. Code and pre-computed results are available at https://github.com/neurips26/UnifiedUnl.

Model merging combines multiple fine-tuned checkpoints into a single model without additional training, offering an attractive approach to reusing models and efficiently improving performance. However, it remains unclear whether the advantages reported for settings where all merged experts have distinct roles and are tuned on clearly separated tasks also hold in settings where the merged experts do not have clearly distinct roles, but are trained on overlapping or even conflicting objectives. To evaluate this setting, we present a large-scale, systematic evaluation of "in-the-wild" model merging of heterogeneous experts, that may have been trained on overlapping or conflicting objectives. Concretely, we evaluate six state-of-the-art merging methods, including recent subspace methods, across four open-weight LLMs, twelve fine-tuned checkpoints per base model, and sixteen standard LLM benchmarks. Evaluating through standardized benchmarks, we measure both the probability that a model merged from a heterogeneous set of experts outperforms the base model and we measure relative gains over the best individual checkpoint. Our results show that the oldest and simplest method, Task Arithmetic, is the only approach that reliably yields performance gains on LLMs in this "in-the-wild" setting. Other interference-aware and subspace merging methods typically do not result in notable improvements over the base model. Our findings indicate that current merging techniques mostly do not enable extracting useful weight updates from heterogeneous and potentially conflicting versions. This motivates the design of LLM-specific merging algorithms and merging-aware fine-tuning methods.

Resolving team conflicts requires not only task-specific competence, but also social intelligence to find common ground and build consensus. As AI agents increasingly collaborate on complex work, they must develop coordination capabilities to function as effective teammates. Yet we hypothesize that current agents lack these capabilities. To test this, we introduce CooperBench, a benchmark of over 600 collaborative coding tasks across 12 libraries in 4 programming languages. Each task assigns two agents different features that can be implemented independently but may conflict without proper coordination. Tasks are grounded in real open-source repositories with expert-written tests. Evaluating state-of-the-art coding agents, we observe the curse of coordination: agents achieve on average 30% lower success rates when working together compared to performing both tasks individually. This contrasts sharply with human teams, where adding teammates typically improves productivity. Our analysis reveals three key issues: (1) communication channels become jammed with vague, ill-timed, and inaccurate messages; (2) even with effective communication, agents deviate from their commitments; and (3) agents often hold incorrect expectations about others' plans and communication. Through large-scale simulation, we also observe rare but interesting emergent coordination behavior including role division, resource division, and negotiation. Our research presents a novel benchmark for collaborative coding and calls for a shift from pursuing individual agent capability to developing social intelligence.

While LLM-based agents excel at individual tasks, effective collaboration with realistic human partners remains challenging. Most of the existing conversation-level collaborative studies lack grounded interaction and behavioral execution, motivating the need for cooperative game environments that enable contextualized and immersive collaboration. To this end, this paper proposes CollabBench, a benchmark for evaluating and training collaborative agents in cooperative games. CollabBench features a Diverse Player Profile Simulation pipeline to model varied players behaviors, and a Collaborative Agentic Training paradigm that unifies reasoning, communication, and action via agentic rollouts, optimized with a hybrid reward balancing task efficiency and affective adaptation. We further extend classic environments to CWAH-MultiPlayer and Cook-MultiPlayer for systematic evaluation under diverse personalities. Experiments with efficiency and affective metrics show that our trained models outperform base models, achieving 19.5% higher efficiency and 24.4% improved affective performance. Further analysis reveals key collaborative limitations of existing models and offers insights for future collaborative training.

In this paper we show that reporting a single performance score is insufficient to compare non-deterministic approaches. We demonstrate for common sequence tagging tasks that the seed value for the random number generator can result in statistically significant (p < 10^-4) differences for state-of-the-art systems. For two recent systems for NER, we observe an absolute difference of one percentage point F1-score depending on the selected seed value, making these systems perceived either as state-of-the-art or mediocre. Instead of publishing and reporting single performance scores, we propose to compare score distributions based on multiple executions. Based on the evaluation of 50.000 LSTM-networks for five sequence tagging tasks, we present network architectures that produce both superior performance as well as are more stable with respect to the remaining hyperparameters.

Coding-agent evaluation has progressed from resolving individual issues to carrying out long-horizon development, yet task completion is still largely assessed within a single codebase. In software ecosystems, many features and bug fixes require coordinated changes across multiple repositories. We introduce WideSWE to evaluate coding agents on such cross-repository tasks. Mining and reviewing changes across 103 software ecosystems yields 120 real-world tasks, balanced between 60 bug fixes and 60 features. We derive prompts from related issues and pull requests. We systematically review and adapt hidden tests to support diverse correct implementations while preserving required behavior and regression checks. Across seven agent configurations, full task success ranges from 10.83% to 42.50%, with the configuration pairing Codex CLI with GPT-5.6-sol achieving the highest rate. Trajectories show agents failing to identify necessary changes, recognizing changes but leaving them unfinished, or modifying the required repositories without fully satisfying the request. To examine whether working on one repository at a time can alleviate these difficulties, we compare it with joint execution under identical prompts. Independent execution mainly recovers omitted work and is less effective at correcting previously attempted but unsuccessful implementations. Joint execution can use information from related repositories to guide implementation and verification. Code is available at https://github.com/ZJU-ACES-ISE/WideSWE.

Collective intelligence depends not only on what team members know, but also on how they organize their work. When the structure of a solution is unknown, useful roles and divisions of labor cannot be specified in advance; teams must learn from experience how to organize reasoning as it unfolds. Human teams routinely adapt this way, while existing AI agent teams rely on fixed protocols, explicit task decomposition, or routing. We introduce Self-Organizing Agent Teams (SAT), fixed teams of AI agents that learn reusable strategies from prior collaborations to organize roles, conversational phases, participation, and information flow. These strategies enable what we call collaborative computation: agents exchange, challenge, repair, and synthesize partial reasoning into solutions no member produced independently. In two independent settings, we learn teamwork strategies that transfer unchanged to unseen benchmarks, using only 15 mathematics and 25 graduate-level knowledge problems. Across five mathematics and physics benchmarks, self-organizing teams average 66.7% accuracy, versus 48.8% for their strongest member, 58.7% for compute-matched inference by that agent, and 59.0% for a perfect router over members' independent answers; on AIME 2026, they exceed this router by 13.4 points. Because gains vary across benchmarks, we ask when self-organizing collaboration helps. Across eight benchmarks, demonstrability (the organizational-psychology construct of whether a team can distinguish correct from incorrect reasoning) strongly tracks improvement over the strongest member (Spearman ρ=0.90, p=0.005): teams benefit most when correct reasoning can be recognized once it appears. More broadly, these results suggest that organization itself can become an agent capability: agent teams can learn how to reason together and produce solutions their members could not reach independently.

Agent skill libraries are becoming routable software assets: a retrieved skill can contribute instructions, scripts, resource bindings, and execution assumptions to an agent. This makes retrieval failures more specific than broad irrelevance. A system can find the right capability family yet expose the wrong same-capability representative. We study this failure as same-capability risk-exposure retrieval. Each benchmark unit pairs a helpful skill with a query-specific risky sibling that shares the capability family but differs on an execution-controlling contract, such as the required resource, precondition, procedure, or artifact. We introduce SameCapRisk-Bench, an auditable benchmark with 1,190 skill-risk units and 1,686 evaluation query cases: 694 marked-sibling units under public library pressure and 496 hard role-flip units where the same two skills swap helpful/risky roles across paired queries. The release records admission evidence, cue/leakage checks, source hashes, family relations, and fixed candidate pools. The benchmark reports helpful ranking together with harmful sibling rate (HSR@K), the top-K exposure of the marked risky sibling. On this benchmark, public SkillRouter, SkillRet, and R3-Skill retrieve helpful skills at high Recall@3 (0.848--0.888) but also expose marked risky siblings frequently (HSR@3 0.346--0.372). A fully public score-and-cluster pipeline lowers HSR@3 to 0.128--0.182, with Recall@3 of 0.713--0.776. Under a benchmark-trained reference scorer, public text-cluster and controlled resolvers reach HSR@3 0.012 and 0.007; the latter attains Recall@3 0.833. Skill retrieval should therefore report both capability matching and same-family risk exposure, with HSR serving as a targeted exposure certificate for fixed skill libraries.

We present the contribution of the Unbabel team to the WMT 2020 Shared Task on Metrics. We intend to participate on the segment-level, document-level and system-level tracks on all language pairs, as well as the 'QE as a Metric' track. Accordingly, we illustrate results of our models in these tracks with reference to test sets from the previous year. Our submissions build upon the recently proposed COMET framework: We train several estimator models to regress on different human-generated quality scores and a novel ranking model trained on relative ranks obtained from Direct Assessments. We also propose a simple technique for converting segment-level predictions into a document-level score. Overall, our systems achieve strong results for all language pairs on previous test sets and in many cases set a new state-of-the-art.

In passage reranking, response ranking and multi-document question answering, LLMs can score several candidate documents or responses together in one prompt, each still receiving its own score. Such scorers are selected on ranking quality, but their scores determine a decision: what a score threshold retains, a reader answers, or which chosen/rejected pair enters preference training. Because the candidates share that prompt, reordering them changes their scores. The same query over the same candidates should still yield the same decision. However, equal ranking quality does not imply equal decisions: on passage reranking, five trained scorers within 0.010 nDCG@10 retain sets that overlap by only 0.66-0.84 when reordered. No prompt-time change we test resolves that dependence: the only one that improves ranking quality does not measurably improve decision stability. We introduce order-consistency SFT (OC-SFT), which attenuates it in the weights by penalizing disagreement between a candidate's scores across orderings. It holds ranking quality and leads every decision-stability measure among trained scorers on all three tasks. It is also more stable on 12 base models than order-averaged distillation, which trains on labels averaged across permutations. One OC-SFT permutation retains sets that overlap more than ten averaged off-the-shelf permutations. A comparison of such scorers should therefore report what a threshold retains and a reader answers, not ranking quality alone. Code is available at https://github.com/thomsonreuters/presentation-dependence.

Production large language-model (LLM) agents are increasingly deployed not as lone problem-solvers but as managers: a main model creates specialized subagents, delegates work, and orchestrates their parallel, asynchronous returns through dynamic workflows. Whether one model can actually run such a team is largely unmeasured: existing benchmarks score a policy's own task-solving or a fixed multi-agent system's emergent behavior, but none isolate the management ability of the single LLM acting as leader. We introduce ClawArena-Team, a benchmark of 41 multi-turn, multimodal, multi-directory scenarios spanning 258 evaluation rounds and 72 staged updates that measures this management ability. The main agent is deliberately constrained: it natively perceives only text and directly accesses only part of the workspace. It commands a fixed, locally served subagent pool, so score differences reflect management skill, not raw capability. All scoring is execution-based with no LLM judge: an overall score -- the Subagent-Management Score (SMS) -- multiplies task correctness by a least-privilege and modality-routing factor. Across twelve proprietary, community-hosted, and self-hosted models, experiments show that the management bottleneck is privilege granting rather than perception (no model exceeds 50% workspace-permission precision); that cost and management quality are decoupled (API cost spans over 100 times while the overall score spans under 4 times, with the cheapest open models on the Pareto frontier); and that most leaderboard scores cluster within a 9.9-point band while orchestration behaviors diverge by more than an order of magnitude. Code is available at https://github.com/aiming-lab/ClawArena.

As LLM benchmarks saturate, the evaluation community has pursued two strategies to increase difficulty: escalating knowledge demands (GPQA, HLE) or removing knowledge entirely in favor of abstract reasoning (ARC-AGI). The first conflates memorization with capability; the second divorces reasoning from the practical contexts in which it matters. We take a different approach. The Grounded Integration Measure (GIM) is a benchmark of 820 original problems (615 public, 205 private) where difficulty comes from integration; individual problems require coordinating multiple cognitive operations (constraint satisfaction, state tracking, epistemic vigilance, audience calibration) over broadly accessible knowledge, so that reasoning stays grounded in realistic tasks without being gated on specialized expertise. Each problem is an original expert-authored composition, majority with rubric-decomposed scoring (median 6 independently judged criteria). A balanced public--private split provides built-in contamination diagnostic. We calibrate a continuous response 2-parameter logistic (2PL) IRT model over >200k prompt-response pairs across 28 models, producing robust ability estimates that correctly order test-configurations even when raw accuracy is distorted by errors or missing data, addressing a common challenge in benchmark reporting. Using this framework, we present a comprehensive leaderboard spanning 22 models and 47 test-configurations (unique model, thinking-level pairs), and conduct what is to our knowledge the most extensive published study of how test-time compute trades off against model capability on a fixed benchmark: 11 models swept across 35 test-configurations. We observe that within-family configuration choices, such as thinking budget and quantization, matter as much as model selection. We release the evaluation framework, calibrated IRT parameters, and all public problems.

Behaviour-Driven Development (BDD) suites accumulate step-text duplication whose maintenance cost is established in prior work. Existing detection techniques require running the tests (Binamungu et al., 2018-2023) or are confined to a single organisation (Irshad et al., 2020-2022), leaving a gap: a purely static, paraphrase-robust, step-level detector usable on any repository. We fill the gap with cukereuse, an open-source Python CLI combining exact hashing, Levenshtein ratio, and sentence-transformer embeddings in a layered pipeline, released alongside an empirical corpus of 347 public GitHub repositories, 23,667 parsed .feature files, and 1,113,616 Gherkin steps. The step-weighted exact-duplicate rate is 80.2 %; the median-repository rate is 58.6 % (Spearman rho = 0.51 with size). The top hybrid cluster groups 20.7k occurrences across 2.2k files. Against 1,020 pairs manually labelled by the three authors under a released rubric (inter-annotator Fleiss' kappa = 0.84 on a 60-pair overlap), we report precision, recall, and F1 with bootstrap 95 % CIs under two protocols: the primary rubric and a score-free second-pass relabelling. The strongest honest pair-level number is near-exact at F1 = 0.822 on score-free labels; the primary-rubric semantic F1 = 0.906 is inflated by a stratification artefact that pins recall at 1.000. Lexical baselines (SourcererCC-style, NiCad-style) reach primary F1 = 0.761 and 0.799. The paper also presents a CDN-structured critique of Gherkin (Cognitive Dimensions of Notations); eight of fourteen dimensions are rated problematic or unsupported. The tool, corpus, labelled pairs, rubric, and pipeline are released under permissive licences.

Rubric-based evaluation is widely used in LLM benchmarks and training pipelines for open-ended, less verifiable tasks. While prior work has demonstrated the effectiveness of rubrics using downstream signals such as reinforcement learning outcomes, there remains no principled way to diagnose how a rubric itself fails from such aggregated or downstream signals alone. To address this gap, we introduce RIFT: RubrIc Failure mode Taxonomy, a taxonomy for systematically characterizing failure modes in rubric composition and design. RIFT consists of eight failure modes organized into three high-level categories: Reliability Failures, Content Validity Failures, and Consequential Validity Failures. RIFT is developed using grounded theory by iteratively annotating rubrics drawn from five diverse data sources spanning general instruction following, code generation, creative writing, and expert-level deep research, until no new failure modes are identified. We evaluate the consistency of the taxonomy by measuring agreement among independent human annotators, observing fair agreement overall (87% pairwise agreement and 0.64 average Cohen's kappa). Finally, to support scalable diagnosis, we propose automated rubric quality metrics and show that they align with human failure-mode annotations, achieving up to 0.925 F1.

Detectors of alignment failures screen deployed language models and score alignment benchmarks. Most are generative judges that spend a decoding pass on every criterion, and classifiers that read token probabilities, such as Llama Guard, still score one fixed label per call. Jev, a model trained with reinforcement learning for calibrated decisions (RLCD), answers many typed questions about one input with calibrated probabilities in a single call. Whether it detects alignment failures has not been measured. We present RLCDAlignBench, which benchmarks Jev on ten alignment failures: sycophancy, jailbreaks, deception, prompt injection, hallucination, privacy violation, social bias, reward hacking, concealing uncertainty, and power seeking. It spans 44 benchmarks and five target models, labelled by each benchmark's scorer and, on two, by humans. Many of these failures are relational, defined against a reference, such as the user's belief or an injected instruction, that the response alone does not reveal. Our key idea is therefore to vary what Jev is asked separately from what it sees: the question's wording and answer type on one side, the fields of the input on the other. A single generic question reaches a median AUROC of 0.886 zero-shot and beats supervised baselines on most benchmarks. Question wording matters little, while context matters more, mostly through fields that encode the label. Jev matches the reference scorer's agreement with human labels, surfaces label defects in existing benchmarks, and costs 63x less than LLM-judge scorers. Code and data: https://github.com/sumleo/RLCDAlignBench.

Leaderboards rank long-horizon agents by their final outputs. Yet a higher score alone does not establish whether two systems are comparable or which stage accounts for the difference. Unequal evidence, inputs, or budgets can affect scores, and statistical corrections do not remove this mismatch. We introduce compositional controllability to address these questions. A comparison window covers one stage, several stages, or the whole agent. Our central result bounds the gap between observed and controlled score differences using only nuisance outside the window. This yields an admissibility test applied before scores are inspected. Inadmissible comparisons are refused. For admissible pairs, an ordering is certified only when the score gap exceeds the combined sampling and nuisance radii; otherwise, it remains undecided. These decisions give each system a rank interval. We introduce BioLitBench, a benchmark of 2,042 biomedical articles represented as structured claim graphs. Among seven published pipelines, a conventional statistical analysis declares a winner in 14 of 21 pairwise comparisons. Yet the top-ranked system alone received the target review's bibliography. To isolate pipeline performance, our test requires matched inputs and a fixed backbone model. It refuses 11 of the 21 comparisons, including every comparison involving the top-ranked system. Seven of the 14 conventional conclusions fall within these refused pairs. The same comparison windows support stage-level training. We train SCRIBE on Qwen3.8-27B using rewards measured at each stage's exit. Under matched evidence, SCRIBE achieves a certified rank interval of [1,2], with certified advantages over all evaluated published pipelines and the evaluated Claude and OpenAI agents. Under same pool, SCRIBE matches the strongest published retriever and is certified above three published pipelines.

We introduce Tencent WorkBuddy Bench, a multi-domain evaluation suite for coding agents; this report documents its construction methodology, scoring protocol, and a cross-model leaderboard. At its core is a unified evaluation framework for constructing and running distribution-informed coding-agent tasks across four work domains - Code, Web, Office, and Security. Rather than adapting public issue text, every task is reverse-engineered from a real commit, pull request, or business scenario and rewritten as a short, colloquial, role-played request, so that a task's prompt is not recoverable by web-searching the underlying issue, pull request, or commit thread. Because the dataset is released openly - task directories, environment images, evaluation harness, tests, and reference solutions - contamination resistance rests on this construction together with dataset versioning rather than on secrecy. The four subsets - repository-level engineering, front-end development, office and business workflows, and red-/blue-team security - probe complementary facets of real work, each with its own verification style. All are packaged in a uniform task-directory format and run, under a uniform and reproducible protocol, on two agent harnesses (CodeBuddy Code and Claude Code); the full open release makes the benchmark reproducible end to end and directly auditable, since any third party can re-run each task and inspect its content. Because each subset uses a different scoring instrument, scores are not comparable across subsets and the suite reports no suite-wide average. We report a cross-model leaderboard across several model families.

The Shapley value is one of the most widely used measures of feature importance partly as it measures a feature's average effect on a model's prediction. We introduce joint Shapley values, which directly extend Shapley's axioms and intuitions: joint Shapley values measure a set of features' average contribution to a model's prediction. We prove the uniqueness of joint Shapley values, for any order of explanation. Results for games show that joint Shapley values present different insights from existing interaction indices, which assess the effect of a feature within a set of features. The joint Shapley values provide intuitive results in ML attribution problems. With binary features, we present a presence-adjusted global value that is more consistent with local intuitions than the usual approach.

Objective. Clinical AI documentation systems require evaluation methodologies that are clinically valid, economically viable, and sensitive to iterative changes. Methods requiring expert review per scoring instance are too slow and expensive for safe, iterative deployment. We present a case-specific, clinician-authored rubric methodology for clinical AI evaluation and examine whether LLM-generated rubrics can approximate clinician agreement. Materials and Methods. Twenty clinicians authored 1,646 rubrics for 823 clinical cases (736 real-world, 87 synthetic) across primary care, psychiatry, oncology, and behavioral health. Each rubric was validated by confirming that an LLM-based scoring agent consistently scored clinician-preferred outputs higher than rejected ones. Seven versions of an EHR-embedded AI agent for clinicians were evaluated across all cases. Results. Clinician-authored rubrics discriminated effectively between high- and low-quality outputs (median score gap: 82.9%) with high scoring stability (median range: 0.00%). Median scores improved from 84% to 95%. In later experiments, clinician-LLM ranking agreement (tau: 0.42-0.46) matched or exceeded clinician-clinician agreement (tau: 0.38-0.43), attributable to both ceiling compression and LLM rubric improvement. Discussion. This convergence supports incorporating LLM rubrics alongside clinician-authored ones. At roughly 1,000 times lower cost, LLM rubrics enable substantially greater evaluation coverage, while continued clinical authorship grounds evaluation in expert judgment. Ceiling compression poses a methodological challenge for future inter-rater agreement studies. Conclusion. Case-specific rubrics offer a path for clinical AI evaluation that preserves expert judgment while enabling automation at three orders lower cost. Clinician-authored rubrics establish the baseline against which LLM rubrics are validated.

We study cost-efficient collaboration between strong and weak language models for repository-level code generation, where the weak model handles simpler tasks at lower cost, and the most challenging tasks are delegated to the strong model. While many works propose architectures for this task, few analyze performance relative to cost. We evaluate a broad spectrum of collaboration strategies: context-based, pipeline-based, and dynamic, on GitHub issue resolution. Our most effective collaborative strategy achieves equivalent performance to the strong model while reducing the cost by 40%. Based on our findings, we offer actionable guidelines for choosing collaboration strategies under varying budget and performance constraints. Our results show that strong-weak collaboration substantially boosts the weak model's performance at a fraction of the cost, pipeline and context-based methods being most efficient. We release the code for our work at https://github.com/shubhamrgandhi/codegen-strong-weak-collab.

This work provides an in-depth analysis of the relation between the different types of collaboration and research productivity, showing how both are influenced by some personal and organizational variables. By applying different cross-lagged panel models, we are able to analyze the relationship among research productivity, collaboration and their determinants. In particular, we show that only collaboration at intramural and domestic level has a positive effect on research productivity. Differently, all the forms of collaboration are positively affected by research productivity. The results can favor the reexamination of the theories related to these issues, and inform policies that would be more suited to their management.

Evaluating long-form responses to research queries heavily relies on expert annotators, restricting attention to areas like AI where researchers can conveniently enlist colleagues. Yet, research expertise is widespread: survey articles synthesize knowledge distributed across the literature. We introduce ResearchQA, a resource for evaluating LLM systems by distilling survey articles from 75 research fields into 21K queries and 160K rubric items. Each rubric, derived jointly with queries from survey sections, lists query-specific answer evaluation criteria, i.e., citing papers, making explanations, and describing limitations. Assessments by 31 Ph.D. annotators in 8 fields indicate 96% of queries support Ph.D. information needs and 87% of rubric items should be addressed in system responses by a sentence or more. Using our rubrics, we are able to construct an automatic pairwise judge obtaining 74% agreement with expert judgments. We leverage ResearchQA to analyze competency gaps in 18 systems in over 7.6K pairwise evaluations. No parametric or retrieval-augmented system we evaluate exceeds 70% on covering rubric items, and the highest-ranking agentic system shows 75% coverage. Error analysis reveals that the highest-ranking system fully addresses less than 11% of citation rubric items, 48% of limitation items, and 49% of comparison items. We release our data to facilitate more comprehensive multi-field evaluations.

Simulated evaluation is increasingly used alongside real-world evaluation of robot policies because it is cheaper and easier to repeat; however, its value depends on how closely its outcomes track the real robot's. We test whether our reconstruction pipeline, combining metrically scaled object geometry, authored physical parameters and scene reconstruction, reduces disagreement between simulated and real robot scores relative to a default open-source recipe. We constructed two simulated versions of one bimanual robot cell: an authored reconstruction, using object geometry at estimated metric scale, projected textures, authored physics and our own scene splat; and a baseline, referred to as the default reconstruction, using the open-source recipe of a generative single-image mesh, engine-default physics and a Gaussian-splat scene. Both reconstructions use the same object photographs and scene video. Two policies ran five tasks each, giving ten task-policy pairs, which we call cells; each cell was run twenty times in each reconstruction with all other settings held fixed. Both reconstructions were scored against the same real trials, graded by a third-party evaluator. Pearson correlation between the ten simulated and real cell means is r = 0.90 for the authored reconstruction and 0.51 for the default. Mean score error is 6.97 percentage points for the authored reconstruction and 17.54 for the default, a reduction of 10.56 percentage points. These results show that improving the quality of the environment reconstruction through higher visual fidelity, authored physics and metric scale makes the simulation more faithful to the real world and narrows the sim-to-real gap. We release the harness, the per-trial scores, every reported run's configuration, and the assets and scenes of both reconstructions.

Multi-agent coding has emerged as an increasingly active direction in software engineering, where complex development tasks are decomposed across multiple specialized agents working on different parts of the problem. Despite the shift from individual problem solving to distributed collaboration, multi-agent systems still lack a direct measure of collaboration and are largely evaluated through task-level outcomes inherited from single-agent coding, conflating individual coding capability with cross-agent coordination. We introduce AsynCodeBench, a dependency-centric benchmark for asynchronous multi-agent software engineering that represents each task with an explicit dependency graph and executable Dependency Checkers. Through this dependency-tracking process, we propose two complementary measures: Asynchronous Dependency Pass Rate (ADPR), which measures how many cross-agent dependencies are ultimately satisfied, and Dependency Resolution Step (DRS), which measures when each dependency first becomes satisfied during execution. AsynCodeBench comprises 19 tasks from real-world repositories, exposing 52 directed dependencies as explicit units for evaluating cross-agent collaboration. Experiments across model families, scales, and generations reveal a clear gap between coding and collaboration capability: improvements in coding performance do not necessarily translate into stronger collaboration, and task-level metrics can diverge substantially from dependency-level collaboration measures. Dependency-trajectory analysis further reveals that successful coordination often emerges not gradually, but through concentrated bursts in which many dependencies become resolved over a short portion of the execution trajectory, a pattern we term a hopping window.

Recent advances in Text-to-3D (T23D) generative models have enabled the synthesis of diverse, high-fidelity 3D assets from textual prompts. However, existing challenges restrict the development of reliable T23D quality assessment (T23DQA). First, existing benchmarks are outdated, fragmented, and coarse-grained, making fine-grained metric training infeasible. Moreover, current objective metrics exhibit inherent design limitations, resulting in non-representative feature extraction and diminished metric robustness. To address these limitations, we introduce T23D-CompBench, a comprehensive benchmark for compositional T23D generation. We define five components with twelve sub-components for compositional prompts, which are used to generate 3,600 textured meshes from ten state-of-the-art generative models. A large-scale subjective experiment is conducted to collect 129,600 reliable human ratings across different perspectives. Based on T23D-CompBench, we further propose Rank2Score, an effective evaluator with two-stage training for T23DQA. Rank2Score enhances pairwise training via supervised contrastive regression and curriculum learning in the first stage, and subsequently refines predictions using mean opinion scores to achieve closer alignment with human judgments in the second stage. Extensive experiments and downstream applications demonstrate that Rank2Score consistently outperforms existing metrics across multiple dimensions and can additionally serve as a reward function to optimize generative models. The project is available at https://cbysjtu.github.io/Rank2Score/.

Despite growing enthusiasm for Multi-Agent Systems (MAS), where multiple LLM agents collaborate to accomplish tasks, their performance gains across popular benchmarks remain minimal compared to single-agent frameworks. This gap highlights the need to analyze the challenges hindering MAS effectiveness. In this paper, we present the first comprehensive study of MAS challenges. We analyze five popular MAS frameworks across over 150 tasks, involving six expert human annotators. We identify 14 unique failure modes and propose a comprehensive taxonomy applicable to various MAS frameworks. This taxonomy emerges iteratively from agreements among three expert annotators per study, achieving a Cohen's Kappa score of 0.88. These fine-grained failure modes are organized into 3 categories, (i) specification and system design failures, (ii) inter-agent misalignment, and (iii) task verification and termination. To support scalable evaluation, we integrate MASFT with LLM-as-a-Judge. We also explore if identified failures could be easily prevented by proposing two interventions: improved specification of agent roles and enhanced orchestration strategies. Our findings reveal that identified failures require more complex solutions, highlighting a clear roadmap for future research. We open-source our dataset and LLM annotator.

Large language model (LLM) coding agents have advanced test generation across diverse programming tasks. However, the common practice of evaluating tests against a single reference solution overlooks alternative valid implementations and can overstate test quality. We introduce TestPrism, comprising 300 test tasks from 17 sources and 3000 candidate implementations, evenly split between valid and invalid solutions. Its primary metric, Joint Success Function, requires the generated tests to fail on the initial program state, accept every valid candidate, and reject every invalid candidate. Across fourteen baseline coding agent configurations, Joint Success Function reaches only 28.00%, whereas single reference success reaches 59.67%. Our analysis reveals missed behaviors, unsupported assertions, and faulty test construction. To address these weaknesses, we introduce TestHelix, which combines heterogeneous synthesis of test and repair pairs with peer cross validation and recursive self improvement (RSI). Across two models, TestHelix improves Joint Success Function by 8.67 to 9.00 percentage points over the native harness comparators in the TestHelix evaluation

Evaluating software agents on a full benchmark is expensive. A small task subset can preserve agent rankings while yielding inaccurate scores. Historical responses provide useful structure, but tasks with identical source responses can have different outcomes for a new target agent. We introduce Hierarchical Score Posterior Recovery (HSPR), which combines source-fitted response factors with uncertain group success rates. Observed target outcomes update the posteriors over the target latent state and group rates; posterior-guided acquisition selects subsequent tasks. Its score-based criterion equals the expected one-step reduction in full-score posterior variance. Observed successes and posterior-predictive counts for unqueried tasks yield a full-score posterior. The final estimate uses its median with source-selected calibration. At a 10% task budget on four task banks from the SWE-bench family, HSPR achieves the lowest mean absolute error (MAE) on three banks and the lowest maximum absolute error (MaxErr) on all four among the methods compared. Removing group uncertainty or replacing adaptive queries increases macro MAE in the respective controls. Macro MAE decreases across 5-20% budgets.

In collaborative data sharing and machine learning, multiple parties aggregate their data resources to train a machine learning model with better model performance. However, as the parties incur data collection costs, they are only willing to do so when guaranteed incentives, such as fairness and individual rationality. Existing frameworks assume that all parties join the collaboration simultaneously, which does not hold in many real-world scenarios. Due to the long processing time for data cleaning, difficulty in overcoming legal barriers, or unawareness, the parties may join the collaboration at different times. In this work, we propose the following perspective: As a party who joins earlier incurs higher risk and encourages the contribution from other wait-and-see parties, that party should receive a reward of higher value for sharing data earlier. To this end, we propose a fair and time-aware data sharing framework, including novel time-aware incentives. We develop new methods for deciding reward values to satisfy these incentives. We further illustrate how to generate model rewards that realize the reward values and empirically demonstrate the properties of our methods on synthetic and real-world datasets.

We propose Collab-REC, a multi-agent framework designed to counteract popularity bias and enhance diversity in tourism recommendations. In our setting, three LLM-based agents: Personalization, Popularity, and Sustainability, generate city suggestions from complementary perspectives. A non-LLM moderator then merges and refines these proposals via multi-round negotiation, ensuring each agent's viewpoint is incorporated while penalizing spurious or repeated responses. Extensive experiments on European city queries using LLMs from different sizes and model families demonstrate that Collab-REC enhances diversity and overall relevance compared to a single-agent baseline, surfacing lesser-visited locales that are often overlooked. This balanced, context-aware approach addresses over-tourism and better aligns with user-provided constraints, highlighting the promise of multi-stakeholder collaboration in LLM-driven recommender systems. Code, data, and other artifacts are available here: https://github.com/ashmibanerjee/collab-rec, while the prompts used are included in the appendix.

Obtaining high-quality generations in modern LLMs has largely been framed as a selection problem: identifying a single winning generation from a diverse pool of N samples, the Best-of-N (BoN). Yet, this approach is inherently zero-sum, discarding diverse and potentially useful information from the pool. Instead, we explore a collaborative setup, where all candidates can potentially contribute to the final winning generation. To this end, we propose Fusion-of-N (FusioN): a method that uses a general LLM judge to synthesize the most informative elements of each sample into a single final answer. We compare FusioN to BoN in two settings, (i) test-time scaling, where we sample and aggregate from a single model at test-time (ii) synthetic data generation, where we fuse samples from a pool of diverse teachers to improve a student model. We extensively benchmark both setups across 11 languages, 3 diverse tasks and varying model scales. Across the bench, FusioN consistently outperforms BoN showing versatility and robustness both in test-time scaling and in downstream gains from synthetic data generation. We also perform extensive analysis on FusioN, where it shows surprising strengths and robustness under challenging settings. These results show that we should shift how we think about evaluating and utilizing LLM generations from a monolithic measure of quality, to embracing their polylithic nature. This shift allows us to integrate diverse strengths, unlock latent potential, and achieve improvements that were previously inaccessible through selection alone.

Multiple agents may often conflict in an organization: for example, one coding agent changes an interface in a repository, but another continues to develop on the old version where existing tests become stale. A conversation can resolve the episode, but when the participants change, what makes the lesson continue to govern the team? We introduce Relic, which turns recurring collaboration failures into organization-owned, executable protocols. Members reflect on visible work, propose rules, and govern their adoption. Adopted protocols bind triggers, responsibilities, required evidence, and execution consequences to the runtime, while remaining open to revision and retirement. In one traced case, repeated integration friction produces an interface-review rule that governs later pull requests and is revised as work continues. Across 360 controlled runs over ten software workloads and three models, Relic raises complete-contract delivery from 14.06% to 19.76% (+5.71 percentage points) over a matched structured team without the protocol lifecycle, improving all four verified production endpoints in every model stratum. Under fresh-member transfer, behavioral correctness is 25.4% with no inherited protocol, 34.6% with the same rules provided as readable text, and 41.2% with executable bindings, a +6.5-point advantage over text alone. On the full CooperBench benchmark, after excluding broken benchmark pairs, Relic achieves 367/477 (76.9%), establishing the best reported result among peer-structured systems. On the fixed 48-pair same-model subset, Relic also exceeds Solo (29/48 vs. 26/48), reversing the coordination loss exhibited by the official peer baseline. Together, these results show how collaboration experience can become persistent organizational state that remains useful beyond the members who created it.

Can AI agents organize scientific investigations that lead to well-supported conclusions? To evaluate this capability, we introduce PhysClosureBench, a benchmark of 50 expert-verified, goal-specified research tasks spanning strong-field, attosecond, and neighboring physics areas. Each task specifies the research objective and essential scientific constraints, while leaving the agent to organize the investigation and determine how to generate and validate the evidence needed to answer the question. A 20-criterion Atomic Score measures local scientific accomplishment, while Research Closure (RC0--RC4) assesses how fully the investigation resolves the specified research question based on whether its indispensable evidence requirements and applicable scope conditions are satisfied. We evaluate seven frontier LLMs, where Claude-Opus-5 achieves the highest mean Atomic Score (6.29/10) but reaches RC4 in only 32.7% of attempts. Across the benchmark, 36.2% of attempts scoring at least 8/10 still fall short of RC4, while all seven models reach RC4 on substantially fewer tasks in all three runs than in at least one. Case-level analysis further illustrates how misinterpretation of generated results and unresolved physical applicability limits can lead to incomplete closure. Together, these results reveal a persistent gap between AI agents' local scientific accomplishments and their ability to achieve complete research closure.

We introduce PaperBench, a benchmark evaluating the ability of AI agents to replicate state-of-the-art AI research. Agents must replicate 20 ICML 2024 Spotlight and Oral papers from scratch, including understanding paper contributions, developing a codebase, and successfully executing experiments. For objective evaluation, we develop rubrics that hierarchically decompose each replication task into smaller sub-tasks with clear grading criteria. In total, PaperBench contains 8,316 individually gradable tasks. Rubrics are co-developed with the author(s) of each ICML paper for accuracy and realism. To enable scalable evaluation, we also develop an LLM-based judge to automatically grade replication attempts against rubrics, and assess our judge's performance by creating a separate benchmark for judges. We evaluate several frontier models on PaperBench, finding that the best-performing tested agent, Claude 3.5 Sonnet (New) with open-source scaffolding, achieves an average replication score of 21.0\%. Finally, we recruit top ML PhDs to attempt a subset of PaperBench, finding that models do not yet outperform the human baseline. We https://github.com/openai/preparedness{open-source our code} to facilitate future research in understanding the AI engineering capabilities of AI agents.

Rubric-augmented verification guides reward models with explicit evaluation criteria, yielding more reliable judgments than single-model verification. However, most existing methods require costly rubric annotations, limiting scalability. Moreover, we find that rubric generation is vulnerable to a failure of cooperation; low-quality rubrics actively mislead reward models rather than help. Inspired by the principle of cooperative communication, we propose Cooperative yet Critical reward modeling (C2), a framework that significantly improves reward model judgments by having the reward model critically collaborate with a rubric generator trained solely from binary preferences. In C2, we synthesize helpful and misleading rubric pairs by measuring how each rubric shifts the reward model toward or away from the correct preference. Using these contrastive pairs, we train a cooperative rubric generator to propose helpful rubrics, and a critical verifier to assess rubric validity before making its judgment, following only rubrics it deems helpful at inference time. C2 outperforms reasoning reward models trained on the same binary preferences, with gains of up to 6.5 points on RM-Bench and 6.0 points length-controlled win rate on AlpacaEval 2.0. Without external rubric annotations, C2 enables an 8B reward model to match performance achieved with rubrics from a 4times larger model. Overall, our work demonstrates that eliciting deliberate cooperation in rubric-augmented verification makes reward models more trustworthy in a scalable way.

We investigate methods for combining multiple self-supervised tasks--i.e., supervised tasks where data can be collected without manual labeling--in order to train a single visual representation. First, we provide an apples-to-apples comparison of four different self-supervised tasks using the very deep ResNet-101 architecture. We then combine tasks to jointly train a network. We also explore lasso regularization to encourage the network to factorize the information in its representation, and methods for "harmonizing" network inputs in order to learn a more unified representation. We evaluate all methods on ImageNet classification, PASCAL VOC detection, and NYU depth prediction. Our results show that deeper networks work better, and that combining tasks--even via a naive multi-head architecture--always improves performance. Our best joint network nearly matches the PASCAL performance of a model pre-trained on ImageNet classification, and matches the ImageNet network on NYU depth prediction.

In the era of large language models, model merging is a promising way to combine multiple task-specific models into a single multitask model without extra training. However, two challenges remain: (a) interference between different models and (b) heterogeneous data during testing. Traditional model merging methods often show significant performance gaps compared to fine-tuned models due to these issues. Additionally, a one-size-fits-all model lacks flexibility for diverse test data, leading to performance degradation. We show that both shared and exclusive task-specific knowledge are crucial for merging performance, but directly merging exclusive knowledge hinders overall performance. In view of this, we propose Twin-Merging, a method that encompasses two principal stages: (1) modularizing knowledge into shared and exclusive components, with compression to reduce redundancy and enhance efficiency; (2) dynamically merging shared and task-specific knowledge based on the input. This approach narrows the performance gap between merged and fine-tuned models and improves adaptability to heterogeneous data. Extensive experiments on 12 datasets for both discriminative and generative tasks demonstrate the effectiveness of our method, showing an average improvement of 28.34% in absolute normalized score for discriminative tasks and even surpassing the fine-tuned upper bound on the generative tasks. (Our implementation is available in https://github.com/LZY-the-boys/Twin-Mergin.)

Multi-agent LLM systems are often expected to improve as team size increases, yet the scaling behavior may depend on task structure. Our central contribution is to introduce Steiner's taxonomy of group tasks as a framework for analyzing multi-agent LLM scaling and focusing the analysis on disjunctive and compensatory tasks. We model independently sampled agents as conditionally independent given the item, which yields their large-team limits: plurality voting converges to the model's modal answer, and averaging converges to the model's item-level bias. Across selected representative benchmarks, 13 open-weight models, and teams of up to 30 agents, we find qualitatively different scaling behavior. On disjunctive tasks, the probability that at least one agent is correct grows by 5-20 points with team size, but plurality voting over agents that answer directly realises almost none of this potential, as the model predicts to within 0.5 points on average. Multi-round revision raises accuracy considerably, yet the gain is nearly the same with one peer as with 29. In contrast, scaling provides little benefit on Fermi estimation, despite its natural suitability for aggregation: item-level biases shared across the samples of a model account for about 87% of the squared error, so averaging reduces error by only about 6%. Combining model families helps on Fermi estimation but does not surpass the strongest member on disjunctive tasks. These results show that task structure, together with the mechanism combining member outputs, is a fundamental determinant of team scaling.

Scientific paper evaluation often involves not only assessing a manuscript itself, but also relating it to contemporaneous research and prior literature. However, existing LLM-based methods typically model these signals separately and lack a unified mechanism for aggregating review evidence across papers. We propose GraphReview, a graph-based LLM framework that formulates paper evaluation as inference-time graph evidence expansion over a semantic paper graph. The graph jointly captures intrinsic quality, synchronic links among contemporaneous papers, and diachronic links to prior work. LLMs are used to estimate node-level quality priors and generate edge-level comparative evidence through pairwise paper comparisons, while Personalized PageRank integrates these structured signals for quality ranking, decision prediction, and review generation. To produce higher-quality graph evidence, we propose reward-induced maximum likelihood objectives for training the LLM backbones. Experiments show that GraphReview consistently outperforms the strongest baseline, achieving average improvements of 29.7% on decision and ranking metrics, including gains of 23.7% in Accuracy and 57.6% in Spearman's ρ. It also produces higher-quality review texts and generalizes effectively across time periods and conference venues.

Advancing beyond single monolithic language models (LMs), recent research increasingly recognizes the importance of model collaboration, where multiple LMs collaborate, compose, and complement each other. Existing research on this topic has mostly been disparate and disconnected, from different research communities, and lacks rigorous comparison. To consolidate existing research and establish model collaboration as a school of thought, we present MoCo: a one-stop Python library of executing, benchmarking, and comparing model collaboration algorithms at scale. MoCo features 26 model collaboration methods, spanning diverse levels of cross-model information exchange such as routing, text, logit, and model parameters. MoCo integrates 25 evaluation datasets spanning reasoning, QA, code, safety, and more, while users could flexibly bring their own data. Extensive experiments with MoCo demonstrate that most collaboration strategies outperform models without collaboration in 61.0% of (model, data) settings on average, with the most effective methods outperforming by up to 25.8%. We further analyze the scaling of model collaboration strategies, the training/inference efficiency of diverse methods, highlight that the collaborative system solves problems where single LMs struggle, and discuss future work in model collaboration, all made possible by MoCo. We envision MoCo as a valuable toolkit to facilitate and turbocharge the quest for an open, modular, decentralized, and collaborative AI future.

A large share of day-to-day work in professional domains happens inside PDF files: benefits packets, leases, datasheets, clinical guidelines, construction plans. Benchmarks for document AI have generally measured the required capabilities in isolation: OCR, layout analysis, chart reasoning, table QA, document VQA. A high score on any one of them does not necessarily reveal whether a model can answer a realistic question that someone in the field would actually ask about a specific PDF. GDP_pdf is a benchmark built to measure this directly. It consists of question-document pairs authored by working professionals in ten fields, and a candidate question was kept only when at least two frontier multimodal models failed it in a way that mattered: a wrong answer, missed decisive evidence, or a fabricated claim, rather than a superficial difference such as style. Each item comes with a rubric of atomic criteria, so we can report a graded rubric score as well as a strict task-level pass rate, and each item is tagged against a taxonomy of eleven capabilities in three tiers, spanning text extraction and grounding, table and chart comprehension, cross-referencing, spatial reasoning, and abstention on unsupported queries. We report results for seventeen frontier models on the 100-item benchmark: the best model passes only 30.7% of the items and the worst passes 2%. Most errors trace back to a small set of recurring loss patterns: misaligned tables, misread charts, skipped footnotes and exclusions, miscounted floor-plan symbols, scan noise, and amendments that supersede earlier text.

Large Language Models (LLMs) have shown promise in accelerating the scientific research pipeline. A key capability for this process is the ability to generate novel research ideas, and prior studies have found settings in which LLM-generated research ideas were judged as more novel than human-expert ideas. However, a good idea should not simply appear to be novel, it should also result in better research after being executed. To test whether AI-generated ideas lead to better research outcomes, we conduct an execution study by recruiting 43 expert researchers to execute randomly-assigned ideas, either written by experts or generated by an LLM. Each expert spent over 100 hours implementing the idea and wrote a 4-page short paper to document the experiments. All the executed projects are then reviewed blindly by expert NLP researchers. Comparing the review scores of the same ideas before and after execution, the scores of the LLM-generated ideas decrease significantly more than expert-written ideas on all evaluation metrics (novelty, excitement, effectiveness, and overall; p < 0.05), closing the gap between LLM and human ideas observed at the ideation stage. When comparing the aggregated review scores from the execution study, we even observe that for many metrics there is a flip in rankings where human ideas score higher than LLM ideas. This ideation-execution gap highlights the limitations of current LLMs in generating truly effective research ideas and the challenge of evaluating research ideas in the absence of execution outcomes.

Scientific peer review faces mounting strain as submission volumes surge, making it increasingly difficult to sustain review quality, consistency, and timeliness. Recent advances in AI have led the community to consider its use in peer review, yet a key unresolved question is whether AI can generate technically sound reviews at real-world conference scale. Here we report the first large-scale field deployment of AI-assisted peer review: every main-track submission at AAAI-26 received one clearly identified AI review from a state-of-the-art system. The system combined frontier models, tool use, and safeguards in a multi-stage process to generate reviews for all 22,977 full-review papers in less than a day. A large-scale survey of AAAI-26 authors and program committee members showed that participants not only found AI reviews useful, but actually preferred them to human reviews on key dimensions such as technical accuracy and research suggestions. We also introduce a novel benchmark and find that our system substantially outperforms a simple LLM-generated review baseline at detecting a variety of scientific weaknesses. Together, these results show that state-of-the-art AI methods can already make meaningful contributions to scientific peer review at conference scale, opening a path toward the next generation of synergistic human-AI teaming for evaluating research.

Measuring the creativity of large language models (LLMs) is essential for designing methods that can improve creativity and for enhancing our scientific understanding of this ability. To accomplish this, it has become common in recent years to administer tests of human creativity to LLMs. Although these tests provide a convenient and fully automated way to score "creativity," their validity as measures of machine creativity has not been established, and these tests already have limited validity as predictors of human creativity. To address this problem, we conduct the first large-scale, systematic study assessing the effectiveness of human creativity tests for predicting the creative achievement of LLMs across three target constructs: creative writing, divergent thinking, and scientific ideation. We find that the Divergent Association Task (DAT) and the Conditional DAT are the best predictors of creative writing and divergent thinking, respectively, but that test effectiveness varies significantly by construct, and no single test predicts all constructs well. Moreover, contrary to popular belief, no existing test reliably predicts scientific ideation ability. Motivated by this problem, we introduce the Divergent Remote Association Test (DRAT), a vocabulary-space test that assesses both convergent and divergent thinking in a single instrument. The DRAT is the first and only creativity test for LLMs that is a significant predictor of scientific ideation ability, demonstrating robustness across major design choices. Furthermore, the performance gain of the DRAT is not recoverable from any linear combination of the Divergent Association Task and the Remote Associates Test, indicating that assessing divergent and convergent thinking in the same test is essential to reliably predicting scientific ideation ability.

We introduce SWE-Game, a benchmark of 247 tasks grounded in 41 executable reference Godot games spanning 13 gameplay categories in 2D and 3D. Five task types cover development from a brief, implementation from a game design document, skeleton completion, repair of 83 injected-fault cases, and Godot-to-Unity porting. Reference materials specify the intended gameplay, while a shared instrumentation interface lets evaluator-owned drivers and probes execute actions and observe independently implemented games. Evaluation combines engine-state checks, certified reference-input replay, and agent-authored feature demonstrations to assess mechanic correctness, demonstrated playability, and behavioral restoration and preservation after repairs. Game-specific vision-language rubrics separately assess presentation. Across six models, Opus5 achieves the highest overall score in all five task types. Best overall scores remain below 60 out of 100 across the three construction tasks, with Brief-to-Game reaching 50.38. Analysis of reviewed submissions identifies requirement omissions and gameplay logic errors as predominant implementation problems. On human-labeled behaviors from 100 agent-built games, executable checks achieve 92.59% balanced accuracy, compared with 78.41% for a video-based VLM judge. Rubric-based visual scores reach a Spearman correlation of 0.829 with human ratings of 200 gameplay clips. Together, these results characterize current agent capabilities across game-development activities and support combining runtime evidence with visual assessment.

We introduce JP-TL-Bench, a lightweight, open benchmark designed to guide the iterative development of Japanese-English translation systems. In this context, the challenge is often "which of these two good translations is better?" rather than "is this translation acceptable?" This distinction matters for Japanese-English, where subtle choices in politeness, implicature, ellipsis, and register strongly affect perceived naturalness. JP-TL-Bench uses a protocol built to make LLM judging both reliable and affordable: it evaluates a candidate model via reference-free, pairwise LLM comparisons against a fixed, versioned anchor set. Pairwise results are aggregated with a Bradley-Terry model and reported as win rates plus a normalized 0-10 "LT" score derived from a logistic transform of fitted log-strengths. Because each candidate is scored against the same frozen anchor set, scores are structurally stable given the same base set, judge, and aggregation code.

LLM-generated reviews for scientific papers are gaining considerable traction and are even being officially piloted by major conferences. We have to assume that not only reviewers are using LLM-assistance, but also that authors use LLMs to revise their papers before submitting. In this work, we perform empirical experiments on papers from the 2025 ACL Rolling Review (ARR) to evaluate LLM reviews from both the author and the reviewer perspective. First, we identify a limited alignment of LLM reviews with human ones. In the best-case scenario, the alignment is reasonable. However, we also find that LLM-human alignment varies substantially across prompts and models. Finally, we investigate the scenario in which the author uses an iterative draft-revise workflow to improve the submission according to the LLM review. We find that this "gaming" of LLM reviews can be effective in specific scenarios, leading to a statistically significant increase of overall scores for up to 35\% of papers. We publish our code: https://github.com/uhh-hcds/reviewarcade.

Identifying significant references within the complex interrelations of a citation knowledge graph is challenging, which encompasses connections through citations, authorship, keywords, and other relational attributes. The Paper Source Tracing (PST) task seeks to automate the identification of pivotal references for given scholarly articles utilizing advanced data mining techniques. In the KDD CUP 2024, we design a recommendation-based framework tailored for the PST task. This framework employs the Neural Collaborative Filtering (NCF) model to generate final predictions. To process the textual attributes of the papers and extract input features for the model, we utilize SciBERT, a pre-trained language model. According to the experimental results, our method achieved a score of 0.37814 on the Mean Average Precision (MAP) metric, outperforming baseline models and ranking 11th among all participating teams. The source code is publicly available at https://github.com/MyLove-XAB/KDDCupFinal.

Fairness and relevance are two important aspects of recommender systems (RSs). Typically, they are evaluated either (i) separately by individual measures of fairness and relevance, or (ii) jointly using a single measure that accounts for fairness with respect to relevance. However, approach (i) often does not provide a reliable joint estimate of the goodness of the models, as it has two different best models: one for fairness and another for relevance. Approach (ii) is also problematic because these measures tend to be ad-hoc and do not relate well to traditional relevance measures, like NDCG. Motivated by this, we present a new approach for jointly evaluating fairness and relevance in RSs: Distance to Pareto Frontier (DPFR). Given some user-item interaction data, we compute their Pareto frontier for a pair of existing relevance and fairness measures, and then use the distance from the frontier as a measure of the jointly achievable fairness and relevance. Our approach is modular and intuitive as it can be computed with existing measures. Experiments with 4 RS models, 3 re-ranking strategies, and 6 datasets show that existing metrics have inconsistent associations with our Pareto-optimal solution, making DPFR a more robust and theoretically well-founded joint measure for assessing fairness and relevance. Our code: https://github.com/theresiavr/DPFR-recsys-evaluation

QMSum provides no scorer, making query-focused meeting summarization results difficult to compare. We rescore or generate 15 systems under one implementation. Through a common inference port, a released 406M Fusion-in-Decoder specialist loses 6.30 ROUGE-1 when moved from capped long input to 2,000-word retrieved spans. Fine-tuning it on this span regime recovers the loss. On test it scores 36.33 ROUGE-1 versus 35.41 for our 1.2B system; the meeting-cluster 95% interval for the difference is [-0.27, +2.22], so QMSum does not statistically separate them. The smaller system uses about one-third as many total parameters and less than half the peak inference memory. Within the fixed 1.2B base, span-regime fine-tuning adds 5.29 [+4.02, +6.56], while replacing the first 4,500 transcript words with 2,000 retrieved words adds 1.55 on test and 0.29 on validation. Separately, under one concise prompt and reference-overlap scorer, a released 406M specialist exceeds five proprietary hosted models by at least 6.2 ROUGE-1, but output length and absent human or factuality evaluation limit this ordering. Conclusions are limited to QMSum and automatic metrics.

Recursive self-improvement (RSI) relies on evaluation feedback to assess progress and guide further research, yet repeatedly running complex benchmarks is costly and slows iteration. Human experts reduce this cost by selecting benchmark subsets or designing compact suites. We ask whether AI agents can automate this design process and introduce EvalResearchBench (ERB), a benchmark for autonomous evaluation research. Given target materials, development references, candidate APIs, and fixed time and API budgets, an agent called the researcher selects or synthesizes tasks, implements graders, and revises them in pilot tests before freezing an executable evaluator for coding, co-work, and reasoning. We study 9 researchers and 13 candidate models and compare each frozen evaluator with 14 target benchmarks on score concordance and pairwise agreement. The best evaluators order about 75\% of candidate pairs as the targets do, below the 91\% ceiling set by disagreements among the targets. No researcher leads on every metric, and the best evaluator on development targets is not the best on sealed targets hidden from the researcher. A human-designed sample of public tasks remains a strong baseline, and the evaluator with the lowest recorded execution cost attains the highest pairwise agreement. Agents repair tasks and graders through pilot feedback, yet their evaluators can still truncate answers, exhaust the evaluation budget, or let a few questions dominate a domain score.

Chemistry evaluation has moved past multiple-choice probes toward open-ended expert problems, yet the benchmarks that define the current frontier still score answer endpoints alone. Such scoring conflates memorized facts with stepwise derivation, treats visual and textual inputs as interchangeable, and confounds long-horizon planning with stepwise execution. These blind spots prevent any diagnosis of where the reasoning chain breaks in a model. We present ChemArgus, a competition-level chemistry benchmark drawn from chemistry competition material, textbooks, and research papers, whose scoring replaces the answer endpoint with three measurement properties. Fine-grained scoring grades every subquestion point by point with partial credit, so a score lands at the level of the step rather than the outcome. Multimodal capability is priced on every problem containing a real image, paired with a controlled text description, so visual understanding is measured against text on identical tasks. Diagnostic attribution reads paired metrics that share one scoring unit and differ only in context construction, so a gap between two scores isolates a single cause, namely integration, propagation, or local reasoning. GPT-5.6-Sol scores 23.2% on unassisted whole-problem solving against 28.8% and 30.4% under the two sequential metrics, a gap measuring the integration burden. Through rubric partial credit and these cause-isolating score gaps, ChemArgus shows not only whether a model answers chemistry correctly but where its reasoning chain fails, so that every score it reports doubles as a diagnosis, a readout of the chain rather than a verdict, aiming to guide language models step by step on their path toward chemistry expertise, one corrected step at a time, each step priced by the rubric, point by point.

The development of state-of-the-art systems in different applied areas of machine learning (ML) is driven by benchmarks, which have shaped the paradigm of evaluating generalisation capabilities from multiple perspectives. Although the paradigm is shifting towards more fine-grained evaluation across diverse tasks, the delicate question of how to aggregate the performances has received particular interest in the community. In general, benchmarks follow the unspoken utilitarian principles, where the systems are ranked based on their mean average score over task-specific metrics. Such aggregation procedure has been viewed as a sub-optimal evaluation protocol, which may have created the illusion of progress. This paper proposes Vote'n'Rank, a framework for ranking systems in multi-task benchmarks under the principles of the social choice theory. We demonstrate that our approach can be efficiently utilised to draw new insights on benchmarking in several ML sub-fields and identify the best-performing systems in research and development case studies. The Vote'n'Rank's procedures are more robust than the mean average while being able to handle missing performance scores and determine conditions under which the system becomes the winner.

Many NLP tasks, such as summarization and extractive question answering, reduce to retrieving relevant content from documents under two constraints: coverage, retaining enough pertinent information to achieve some goal, and conciseness, removing as much irrelevant information as possible. Conformal prediction methods have been used to guarantee coverage, and must be optimized for conciseness through design of a score function. State-of-the-art scoring functions use hand-engineered LLM prompts asking the model to rate the importance of content, but manual prompt engineering is labor-intensive and task-specific. We introduce the Conformal Relevance framework which uses in-context learning example curation and ensembling to create a score function which maintains coverage while improving conciseness with minimal manual input. We demonstrate this framework's application on seven NLP tasks, and also theoretically study the impact of diversity for ensembled conformal scores, giving a complementarity condition that characterizes when ensembling improves worst-case sentence scores, and a saturation bound on ensemble improvement.

In this paper we introduce the SCoRe (Submodular Combinatorial Representation Learning) framework, a novel approach in representation learning that addresses inter-class bias and intra-class variance. SCoRe provides a new combinatorial viewpoint to representation learning, by introducing a family of loss functions based on set-based submodular information measures. We develop two novel combinatorial formulations for loss functions, using the Total Information and Total Correlation, that naturally minimize intra-class variance and inter-class bias. Several commonly used metric/contrastive learning loss functions like supervised contrastive loss, orthogonal projection loss, and N-pairs loss, are all instances of SCoRe, thereby underlining the versatility and applicability of SCoRe in a broad spectrum of learning scenarios. Novel objectives in SCoRe naturally model class-imbalance with up to 7.6\% improvement in classification on CIFAR-10-LT, CIFAR-100-LT, MedMNIST, 2.1% on ImageNet-LT, and 19.4% in object detection on IDD and LVIS (v1.0), demonstrating its effectiveness over existing approaches.

High-quality pre-training data is crutial for large language models, where quality captures factual reliability and semantic value, and diversity ensures broad coverage and distributional heterogeneity. Existing approaches typically rely on single or multiple-dimensional score-based selection. However, directly selecting top-scored data often degrades performance, and sampling from a broader range is required to recover results. The above non-monotonicity between dataset scores and downstream benchmark results reveals a fundamental bias: score-based methods collapse correlated dimensions, causing top-scored data to appear high-quality while systematically overlooking diversity. We argue that ensuring diversity requires decomposing correlated metrics into orthogonal feature dimensions, from which the top-scored data can be directly selected. Therefore, we proposed the Orthogonal Diversity-Aware Selection (ODiS) algorithm, which preserves both quality and diversity during data selection. First, ODiS evaluates data from multiple dimensions, covering language quality, knowledge quality, and comprehension difficulty. The multi-dimensional scores are then decorrelated via Principal Component Analysis (PCA), yielding orthogonal evaluation dimensions. For each dimension, a Roberta-based scorer is trained to regress the data onto PCA-projected scores, enabling scalable inference on large corpora. Finally, ODiS constructs the training dataset by selecting top-scored data within each orthogonal dimension, thereby ensuring both quality and diversity. Empirical results show that ODiS-selected data exhibit less than 2\% inter-dimension overlap, confirming orthogonality between dimensions. More importantly, models trained with ODiS-selected data significantly outperform other baselines on downstream benchmarks, highlighting the necessity of orthogonal, diversity-aware data selection for LLMs.

Large language models are increasingly deployed as autonomous agents executing multi-step workflows in real-world software environments. However, existing agent benchmarks suffer from three critical limitations: (1) trajectory-opaque grading that checks only final outputs, (2) underspecified safety and robustness evaluation, and (3) narrow modality coverage and interaction paradigms. We introduce Claw-Eval, an end-to-end evaluation suite addressing all three gaps. It comprises 300 human-verified tasks spanning 9 categories across three groups (general service orchestration, multimodal perception and generation, and multi-turn professional dialogue). Every agent action is recorded through three independent evidence channels (execution traces, audit logs, and environment snapshots), enabling trajectory-aware grading over 2,159 fine-grained rubric items. The scoring protocol evaluates Completion, Safety, and Robustness, reporting Average Score, Pass@k, and Pass^k across three trials to distinguish genuine capability from lucky outcomes. Experiments on 14 frontier models reveal that: (1) trajectory-opaque evaluation is systematically unreliable, missing 44% of safety violations and 13% of robustness failures that our hybrid pipeline catches; (2) controlled error injection primarily degrades consistency rather than peak capability, with Pass^3 dropping up to 24% while Pass@3 remains stable; (3) multimodal performance varies sharply, with most models performing poorer on video than on document or image, and no single model dominating across all modalities. Beyond benchmarking, Claw-Eval highlights actionable directions for agent development, shedding light on what it takes to build agents that are not only capable but reliably deployable.

Deep research (DR) agents address open-ended information needs through multi-step reasoning, long-horizon web search, and evidence synthesis. However, existing benchmarks primarily focus on academic research or synthetic tasks, leaving DR agents' capabilities in real-world life and professional productivity settings insufficiently evaluated. To bridge this gap, we introduce LifeSearch, a challenging benchmark comprising 203 Chinese and English tasks derived from real-user query seeds across 7 concrete life and productivity domains. With more than 4,500 hours of human annotation, we construct over 4,000 expert-written, fine-grained rubrics, covering both report-content criteria for coverage and accuracy and concrete criteria specifying values, units, dates, and URLs. We conduct extensive experiments on 12 advanced DR agents under a unified evaluation harness, systematically analyzing their performance patterns and failure modes. We find that even the best-performing frontier agent, GPT-5.6 Sol, achieves a score of only 63.4%, leaving substantial room for improvement on realistic life and professional DR tasks. We select the grading configuration by comparing candidate LLM judges against human rubric labels, and a human ranking study shows strong alignment between aggregate benchmark scores and human judgments (Spearman's ρ= 0.89, Kendall's τ= 0.81). LifeSearch provides a rigorous evaluation framework and foundation for advancing DR agents toward real-world life and productivity.

Agent systems often decompose a task across multiple roles, but these roles are typically specified by prompts rather than enforced by access controls. Without enforcement, a team pass rate can mask whether agents actually coordinated or whether one role effectively did another role's work. We present TeamBench, a benchmark with 851 task templates and 931 seeded instances for evaluating agent coordination under operating system-enforced role separation. TeamBench separates specification access, workspace editing, and final certification across Planner, Executor, and Verifier roles, so that no role can read the full requirements, modify the workspace, and certify the final answer. Prompt-only and sandbox-enforced teams reach statistically indistinguishable pass rates, but prompt-only runs produce 3.6 times more cases where the verifier attempts to edit the executor's code. Verifiers approve 49% of submissions that fail the deterministic grader, and removing the verifier improves mean partial score in the ablation. Team value is also conditional. Teams benefit when single agents struggle, but hurt when single agents already perform well. A 40-session human study under the same role separation shows that our benchmark exposes interaction patterns that pass rate misses. Solo participants work through the task directly, human participants paired with agents often collapse into quick approval, and human teams spend more effort coordinating missing information across roles.

Recent years have witnessed the great success of graph pre-training for graph representation learning. With hundreds of graph pre-training tasks proposed, integrating knowledge acquired from multiple pre-training tasks has become a popular research topic. In this paper, we identify two important collaborative processes for this topic: (1) select: how to select an optimal task combination from a given task pool based on their compatibility, and (2) weigh: how to weigh the selected tasks based on their importance. While there currently has been a lot of work focused on weighing, comparatively little effort has been devoted to selecting. This paper proposes a novel instance-level framework for integrating multiple graph pre-training tasks, Weigh And Select (WAS), where the two collaborative processes, weighing and selecting, are combined by decoupled siamese networks. Specifically, it first adaptively learns an optimal combination of tasks for each instance from a given task pool, based on which a customized instance-level task weighing strategy is learned. Extensive experiments on 16 graph datasets across node-level and graph-level downstream tasks have demonstrated that by combining a few simple but classical tasks, WAS can achieve comparable performance to other leading counterparts. The code is available at https://github.com/TianyuFan0504/WAS.

Rerankers decide which documents users and LLMs see, yet their standard metric, nDCG, relies on human relevance labels that are costly, sparse, noisy, and discretely graded. As rerankers approach each other in quality, nDCG on these labels therefore increasingly fails to separate them. LLM judges could supply dense labels. Relative judgments within one query tell even close candidates apart, yet their scores share no scale across queries. Absolute grades share one scale but are too coarse to distinguish documents of similar relevance. We propose Rubric-Calibrated Preferences (RCP), which combine both kinds of judgment. A listwise Bradley-Terry tournament orders each query's documents, and a rubric of yes/no criteria of increasing stringency provides an absolute standard. Item Response Theory (IRT), which scores test-takers based on their answers to common questions, then uses the shared criteria to put all queries' tournament scores on one scale. RCP's retrieval metric, RCP-nDCG, replaces nDCG's discrete labels with the resulting calibrated relevance probabilities. Against blind grades from 46 external annotators, calibration raises the correlation between a query's mean score and its mean human grade from 0.538 to 0.795. The probabilities rank a useful document above a non-useful one with probability 0.910 (AUC, chance 0.5), versus 0.651 for the benchmark labels. When the annotators' grades prefer one of two rerankers and exactly one metric agrees, that metric is RCP-nDCG in 72.4% of 185 comparisons (chance about 53%). On TREC-DL, RCP-nDCG sides with NIST assessors' grades on every reranker pair that these grades separate significantly. RCP-nDCG also resolves many of nDCG's ties and separates 1.9 times as many reranker pairs on NanoBEIR. Rubric calibration thus turns relative LLM judgments into dense relevance labels that are comparable across queries and agree with human judgment.

Large Language Models are versatile general-task solvers, and their capabilities can truly assist people with scholarly peer review as pre-review agents, if not as fully autonomous peer-review agents. While incredibly beneficial, automating academic peer-review, as a concept, raises concerns surrounding safety, research integrity, and the validity of the academic peer-review process. The majority of the studies performing a systematic evaluation of frontier LLMs generating reviews across science disciplines miss the mark on addressing the alignment/misalignment of reviews along with the utility of LLM generated reviews when compared against publication outcomes such as Citations, Hit-papers, Novelty, and Disruption. This paper presents an experimental study in which we gathered ground-truth reviewer ratings from OpenReview and used various frontier open-weight LLMs to generate reviews of papers to gauge the safety and reliability of incorporating LLMs into the scientific review pipeline. Our findings demonstrate the utility of frontier open-weight LLMs as pre-review screening agents despite highlighting fundamental misalignment risks when deployed as autonomous reviewers. Our results show that all models exhibit weak correlation with human peer reviewers (0.15), with systematic overestimation bias of 3-5 points and uniformly high confidence scores (8.0-9.0/10) despite prediction errors. However, we also observed that LLM reviews correlate more strongly with post-publication metrics than with human scores, suggesting potential utility as pre-review screening tools. Our findings highlight the potential and address the pitfalls of automating peer reviews with language models. We open-sourced our dataset D_{LMRSD} to help the research community expand the safety framework of automating scientific reviews.

We propose two new methods for multi-document financial question answering. First, a method that uses semantic tagging, and then, queries the index to get the context (RAG_SEM). And second, a Knowledge Graph (KG_RAG) based method that uses semantic tagging, and, retrieves knowledge graph triples from a graph database, as context. KG_RAG uses knowledge graphs constructed using a small model that is fine-tuned using knowledge distillation using a large teacher model. The data consists of 18 10K reports of Apple, Microsoft, Alphabet, NVIDIA, Amazon and Tesla for the years 2021, 2022 and 2023. The list of questions in the data consists of 111 complex questions including many esoteric questions that are difficult to answer and the answers are not completely obvious. As evaluation metrics, we use overall scores as well as segmented scores for measurement including the faithfulness, relevance, correctness, similarity, an LLM based overall score and the rouge scores as well as a similarity of embeddings. We find that both methods outperform plain RAG significantly. KG_RAG outperforms RAG_SEM in four out of nine metrics.

We propose SPARTA ALIGNMENT, an algorithm to collectively align multiple LLMs through competition and combat. To complement a single model's lack of diversity in generation and biases in evaluation, multiple LLMs form a "sparta tribe" to compete against each other in fulfilling instructions while serving as judges for the competition of others. For each iteration, one instruction and two models are selected for a duel, the other models evaluate the two responses, and their evaluation scores are aggregated through a adapted elo-ranking based reputation system, where winners/losers of combat gain/lose weight in evaluating others. The peer-evaluated combat results then become preference pairs where the winning response is preferred over the losing one, and all models learn from these preferences at the end of each iteration. SPARTA ALIGNMENT enables the self-evolution of multiple LLMs in an iterative and collective competition process. Extensive experiments demonstrate that SPARTA ALIGNMENT outperforms initial models and 4 self-alignment baselines across 10 out of 12 tasks and datasets with 7.0% average improvement. Further analysis reveals that SPARTA ALIGNMENT generalizes more effectively to unseen tasks and leverages the expertise diversity of participating models to produce more logical, direct and informative outputs.

Joint audio-video generation aims to synthesize realistic audio-video pairs that are both semantically aligned with text prompts and precisely synchronized. While existing joint audio-video generation models often require substantial training resources to improve fidelity, Inference-Time Scaling (ITS) has recently emerged as a promising training-free alternative in single-modality domains. However, extending ITS from a single modality to multimodal domains is non-trivial, as it requires balancing multiple heterogeneous objectives. In this paper, we present the first comprehensive study of ITS for joint audio-video generation. We first demonstrate that a multi-verifier framework is essential to address the limitations of single-objective guidance, including asymmetric performance trade-offs and verifier hacking. Through systematic analysis, we then identify an optimal multi-verifier combination that yields balanced improvements across all quality dimensions. Finally, to effectively aggregate diverse reward signals, we propose Adaptive Reward Weighting (ARW), a novel test-time optimization algorithm. ARW treats reward aggregation as an online optimization problem, utilizing learnable parameters to calibrate reward variances without requiring prior knowledge of reward distributions, thereby ensuring robust multi-objective selection. Experimental results on VGGSound and JavisBench-mini benchmarks demonstrate that our framework significantly enhances semantic alignment, perceptual quality, and audio-visual synchronization of generated outputs. Synthesized samples and code are available on the project page: https://jung-jaemin.github.io/ITS-AVGen-Proj.

Deep recommender systems (DRS) are intensively applied in modern web services. To deal with the massive web contents, DRS employs a two-stage workflow: retrieval and ranking, to generate its recommendation results. The retriever aims to select a small set of relevant candidates from the entire items with high efficiency; while the ranker, usually more precise but time-consuming, is supposed to further refine the best items from the retrieved candidates. Traditionally, the two components are trained either independently or within a simple cascading pipeline, which is prone to poor collaboration effect. Though some latest works suggested to train retriever and ranker jointly, there still exist many severe limitations: item distribution shift between training and inference, false negative, and misalignment of ranking order. As such, it remains to explore effective collaborations between retriever and ranker.

Evaluations of LLM systems routinely average over small prompt sets and report models as a ranked table. We ask how much confidence such a table deserves, using LLM-based prompt-structure inference as the case study: eight open model variants across five families and 8B to 675B parameters, caching disabled, 293 raw intermediate representations persisted. The measured phenomenon is unstable to begin with. Identical calls do not reliably recover identical structure, with mean node-set Jaccard from 0.39 to 0.96 and 72% of prompt-model cells never node-set-perfect. Auditing the evaluation weakens its conclusions further, and this is our main contribution. Under a joint cluster bootstrap over prompts, only the bottom of the ranking is firm: the two least reproducible models hold rank in 99% and 86% of replicates, the middle four in 27% to 48%, and the top two in 68% each, so the table identifies the worst model reliably but does not reliably identify the best. Two equally defensible rules for merging repeated campaigns change four of eight rows and move the study-wide headline by 7 percentage points. Checking the inferred structure against ground-truth annotations shows reproducibility cannot be read as accuracy. And four of the eight endpoints were withdrawn within ten weeks of measurement, so the study as specified can no longer be run. Small-sample LLM evaluations can therefore look far more definitive than their evidence supports. We recommend reporting rank stability, per-cell provenance, executed sensitivity comparisons, raw per-run outputs, and a measurement date alongside any ranking.