AI Agent Evaluation

Follow this topic Ask about this topic

Momentum

58 papers in the last four weeks, up 100% on the four weeks before. 0.6% of all new papers.

Jul 13Week of Sep 28

Latest papers 341

Jul 8, 2026cs.LG

Reward-Adaptive Iterative Discovery: A Case Study on Automated Game Testing for NHL26

Testing is a major effort for the gaming industry, requiring a significant part of development budget and people power. We present a case study on a development version of the ice hockey game EA SPORTS NHL 26, for which human playtesters test the goalie AI for behavioral exploits. To reduce the effort of re-testing the goalie AI after every game or behavior modification in the development phase, we propose Reward-Adaptive Iterative Discovery (RAID), a novel approach to automatically find exploits using an iterative Reinforcement Learning (RL) approach that trains a population of goal scoring agents. While previous approaches can already successfully find exploits, RL algorithms tend to overfit to a single solution. We introduce a simple extension on top of existing RL algorithms, such that they find multiple diverse high-quality solutions. For our first deployment of this approach, within a single experiment we were able to find six hockey scoring exploit strategies that were qualitatively similar to those that playtesters had found in hours-long manual testing sessions.

Florian Fuchs, Jessy Gosselin-Grant, Boris Skuin +5

Electronic Arts (EA)

Automated Software Testing Reinforcement Learning Game-Playing Agents AI Agent Evaluation

Jul 8, 2026cs.AI

Measuring Intelligence Beyond Human Scale

How can we measure intelligence beyond human capability? Human-authored benchmarks saturate, and above human capability, examiners may not know which tasks are both hard and verifiable. We argue that this difficulty is inherent to absolute-scale evaluation and propose a new paradigm based on relative measurement in which models generate public challenges that separate other systems. Aggregating these outcomes yields an adversarial psychometric rating system that can scale with the systems being measured. We describe practical protocols that reduce incentives for private-information attacks, support judge-free adjudication, and naturally scale with agent capabilities. We instantiate the framework across verifiable and open-ended, non-verifiable domains, illustrating how model-generated evaluation can continue to measure systems beyond the human frontier.

Jerry Han, Rafael Moschopoulos, Ella Colby +6

Princeton Superalignment

LLM Evaluation AI Agent Evaluation Synthetic Benchmark Generation Psychometric Validation

Jul 7, 2026cs.LG

A Gold-Standard Study of What Makes a Lightweight Game-Playing Agent Strong

Reinforcement learning agents for imperfect-information card games are only as strong as the opponents they train against, and they are hard to grade, since they beat a random opponent over 99 percent of the time and only tie copies of themselves. So we build a strong, fixed, rule-based expert for Gin Rummy and use it only as a yardstick, never for training. It beats every agent we trained 70 to 99 percent of the time. Across more than a hundred runs, we isolate what makes a lightweight agent stronger. Trust region updates, a well-aimed reward, a curriculum of tougher opponents, warm starting, and keeping the best checkpoint all help, and stacking them lifts a self-play champion from about 30 to 36 percent against the expert. Several ideas did not pay off. Short-term and longer-term reward shaping, learned state embeddings, imitation and DAgger, and a live large language model opponent were each unhelpful, too slow, or too heavy to train at scale. Comparing MLP, convolutional, set-based, attention, and recurrent encoders shows that extra capacity does little to break the ceiling, suggesting the limit is information rather than network size. We add standard baselines (neural fictitious self-play and information set Monte Carlo search) and confirm the approach carries over to Leduc Hold'em, where the optimum is computable. The result is a lightweight, game-agnostic recipe that trains competitive agents without training on the expert, for any game a small model can handle, reported with robust statistics and released as a reusable package.

Nima Kelidari, Mohammadsaeed Haghi, Mahdi Salmani

University of Southern California

Reinforcement Learning Game-Playing Agents Self-Play RL Imperfect-Information Games AI Agent Evaluation Reward Design for RL

Jul 7, 2026stat.ME

An Experimental Design Approach to Evaluating Agentic AI's Autonomous Model Discovery

Large language model coding agents increasingly perform open-ended data modeling and analysis. These agents are stochastic and adaptive, and therefore their autonomous model discovery behavior cannot be adequately characterized by a single benchmark run. In this work, we propose an experimental design and analysis framework for systematically evaluating this discovery process, quantifying its variability, and identifying important factors. The proposed framework treats these agents as stochastic model-discovery operators, which map task-specific discovery data and an optimization target to a fitted model. Specifically, we investigate two such operators, Codex and Claude Code, under controlled experimental factors including agent's reasoning effort, task, optimization metric, and composition of training data. For each agent-task-metric combination, regression models and inference are conducted for multiple responses such as output quality, dollar cost, wall-clock time, and process complexity. Furthermore, we develop a utility-aligned canonical decomposition to characterize the dominant direction of the reasoning-effort effect and to assess whether that direction aligns with a performance-cost utility direction. The proposed framework is demonstrated on a testbed of networked word-forming games with insightful findings on reasoning effort with respect to cost and process complexity.

Hao He, Xueying Liu, Chris J. Kuhlman +1

Department of Statistics, Virginia Tech · Department of Statistical Science, Baylor University · Advanced Research Computing, Virginia Tech +1

AI Coding Agents AI Agent Evaluation

Jul 7, 2026cs.AI

AgentLens: Production-Assessed Trajectory Reviews for Coding Agent Evaluation

We present AgentLens, a production-assessed benchmark for interactive code agents. Most code-agent benchmarks reduce a run to a single bit -- did the task pass? -- but the people who actually use these agents experience the entire trajectory: how the agent follows instructions, uses its tools, verifies its own work, recovers from mistakes, and talks to them along the way. AgentLens evaluates that whole trajectory. It pairs formal verification, where an objective check exists, with LLM-written trajectory reviews and side-by-side comparisons, so that each run yields a readable explanation of why the score is what it is. This makes AgentLens useful for more than ranking models: we use it to diagnose model behavior, compare successive versions of our own agent, and catch product regressions in a nightly evaluation pipeline. We release the benchmark as open source at https://github.com/agent-lens/agent-lens-bench.

Andrey Podivilov, Vadim Lomshakov, Sergey Savin +4

1Explyt · 2St. Petersburg Department of the Steklov Institute of Mathematics · 3St. Petersburg State University

Computer-Use Agent Benchmarks AI Coding Agents LLM Agent Evaluation AI Agent Evaluation AI Agent Benchmarks

Jul 7, 2026cs.AI

Beyond Static Evaluation: Building Simulation Environments for Scalable Agentic Reinforcement Learning

As Large Language Models (LLMs) evolve into autonomous agents, traditional static evaluation fails to capture multi-step decision-making. We introduce AgenticAI-Supervisor, an API and UI-driven RL Gym environment that decouples environment creation from scalable execution. By moving to verifiable execution outcomes, the platform generates high-fidelity traces and applies multi-dimensional reward shaping. Critically, our framework mitigates reward hacking through rigorous internal state validation and testing. This work provides a first look at our platform's core capabilities through a Customer Support Agent case study demonstrating a consistent closed-loop feedback for model optimization. Future work will focus on advanced features such as Computer Use, Tool Use, automated "stumping", and edge-case generation.

Akshay Arora, Ishan Nigam, Ashutosh Aggarwal +6

Uber AI Solutions San Francisco, CA, USA

Agentic RL AI Agent Evaluation Reinforcement Learning with Verifiable Rewards

Jul 6, 2026cs.MA

Collective Intelligence with Foundation Models

As foundation models grow in scale and diversity, coordinating multiple models into cooperative reasoning systems offers a path toward safer, more reliable AI. This chapter presents a multi-agent framework where solver models generate independent drafts, each undergoes structured critique and revision by a critic agent, and an aggregator agent synthesizes a final consensus solution. A scoring module provides semantic, numerical, and procedural evaluation across all agents. Through ablation studies on a benchmark spanning calculus, physics, chemistry, biology, economics, optimization, statistics, and mathematics, we isolate the contributions of framework architecture versus model diversity. We compare four configurations: (1) Individual Baseline, (2) Homogeneous Framework using one shared model, (3) Redundant Homogeneous Solvers using multiple instances of the same model, and (4) Heterogeneous Framework with diverse specialized models. Results show that while framework structure and redundant sampling yield modest gains, model heterogeneity is the critical factor driving substantial performance improvements. The heterogeneous configuration achieves superior step-wise accuracy (0.64 vs. 0.54 for individual models; 2.3x improvement over homogeneous configurations) with reduced variance across categories and difficulty levels. Step-wise reasoning quality (correctness of intermediate steps, not just final answers) improves dramatically only with model diversity, showing that heterogeneous agents provide complementary error detection and reasoning refinement essential for explainability and auditability. We discuss architectural principles, evaluation methodology, and implications for Global Applied AI, showing how heterogeneous multi-agent coordination supports transparent, auditable, high-confidence decision-making across scientific and industrial domains.

J. de Curtò, I. de Zarzà

Department of Computer Applications in Science & Engineering, BARCELONA Supercomputing Center, 08034 Barcelona, Spain · Escuela Técnica Superior de Ingeniería (ICAI), Universidad Pontificia Comillas, 28015 Madrid, Spain · Human Centered AI, Data & Software, LUXEMBOURG Institute of Science and Technology, L-4362 Esch-sur-Alzette, Luxembourg

AI Agent Evaluation Multi-Agent Collaboration Multi-Agent Systems Multi-Agent Consensus Language Model Ensembles Multi-Agent Reasoning

Jul 5, 2026cs.AI

Agent Step Value: Auditing Evaluator-Channel Reversals in Black-Box Agent Traces

When evaluator-derived step rewards are pooled or compared across scoring channels, their sign is treated as transportable. Yet the same frozen transition can change sign with the scoring channel. Process rewards vary agent states, while evaluator audits vary scoring configurations; neither first difference isolates their interaction. We define Agent Step Value (ASV) as channel-indexed target-margin gain and identify the missing state-by-channel interaction by replaying complete faces. Of 1,100 PubMed open question-answering transitions, 1,004 were complete across four cyclic layouts. Their mean update is positive under direct scoring (+0.163 [0.102, 0.218]) and negative with an externally generated view (-0.160 [-0.244, -0.079]), giving an interaction of -0.323 [-0.418, -0.232]. Across paired transitions, 507/1,004 cross zero in one direction or the other. Matched templates isolate a generated-minus-quote interaction of -1.121 [-1.534, -0.703]. Its direction remains negative after the readout and evaluator-stack changes, and quote yields a higher paired area under the receiver operating characteristic curve (AUC) for stored success at all three bridge vertices. Because the two views preserve the same task information conditional on the retained state, a representation-invariance null predicts equal responses and success rankings across them. ASV provides a transport audit for evaluator-derived step measurements; causal actor credit lies outside its estimand.

Andrew Zhang, Chengzhan Li

KTH Royal Institute of Technology · University of Electronic Science and Technology of China

LLM Agent Evaluation AI Agent Evaluation Agent Evaluation Black-Box Model Auditing

Jul 5, 2026cs.AI

Do GUI Agents Believe Their Eyes? Diagnosing State-Belief Reliance on Pixels versus Structure

Multimodal GUI agents read an interface through two redundant channels: the rendered pixels of a screenshot and a serialized structure such as a DOM or accessibility tree. Before acting, an agent forms a belief about the current interface state, but existing benchmarks score task success, element grounding, or attack resistance and do not ask whether that belief is drawn from the pixels. We formalize visual state reliance, the attribution of a state belief to pixels, structure, or priors, and measure it with paired single-channel interventions over 310 real web, mobile, and desktop probes. Every probe is scored by deterministic forced choice, with no model-generated item and no model judge. Our central metric is the Perception-Fusion Gap, the fraction of probes a model perceives correctly yet resolves toward structure under conflict. Across five models from three vendors, textual state beliefs defer to structure while image-only accuracy stays near ceiling, and Perception-Fusion Gap is positive for every model; non-text identity, by contrast, stays largely pixel-bound. The substitution is specific to the serialized-text and indexed-action channel, and coordinate-action agents are largely immune. For textual conflicts, a white-box ablation traces the effect to a single copied structural value, and in two live environments the conflict drives wrong actions and real task failure. Visual state reliance therefore gives a measurable diagnostic of whether agent state beliefs are visually grounded, and the errors it exposes propagate to actions.

Guijia Zhang, Harry Yang

1Shenzhen University · 2The Hong Kong University of Science and Technology

GUI Agents AI Agent Evaluation

Jul 3, 2026cs.SE

CAGE-1: Control, Assurance, and Governance Evaluation for Enterprise Agentic AI

Enterprise artificial intelligence is moving from experimentation into operational workflows. Early programs focused on model access and retrieval-augmented generation, but enterprises are now beginning to deploy agents that plan, retrieve, remember, call tools, update systems, and coordinate work across applications. This changes the evaluation problem. Leaders are no longer asking only whether an answer is accurate or fluent. They need to know who authorized an action, which policy applied, whether evidence was current, whether memory was valid, whether a tool call was permitted, whether the decision can be replayed, and whether the agent can be stopped before it creates business impact. This paper introduces CAGE-1: Control, Assurance, and Governance Evaluation for Enterprise Agentic AI. CAGE-1 is an evaluation framework for deciding whether enterprise agents are ready for deployment. It evaluates authority, policy enforcement, retrieval quality, memory integrity, tool safety, auditability, human oversight, conflict handling, safe failure, Prebind Assurance, operational readiness, and business fitness. CAGE-1 introduces Prebind Assurance to describe the evaluated ability to prove that an agentic action is controlled before it becomes binding, effective, or operationally consequential. The framework tests whether a proposed action is admitted, held, narrowed, refused, escalated, quarantined, or made non-effective before protected consequence forms.

Roopam W. Sure

AI Agent Evaluation AI Agent Safety AI Agent Governance Tool Access Control for LLM Agents

Jul 3, 2026cs.AI

Beyond Forecasting: The Belief-to-Trade Layer in Prediction-Market Agents

Forecasting future events has attracted growing attention as a testbed for general-purpose AI. A natural way to ground this evaluation is let the models trade in the prediction markets. Trading, however, requires more than forecasting. Moreover, recent benchmarks report a substantial gap between calibrated probability scores and the trading results. We propose Raven-Agent, to the best of our knowledge, the first autonomous trading agent for prediction markets. On a controlled replay over an archived decision set, our architecture achieves the only positive return and the only positive risk-adjusted return among all tested policies. We have released our code in https://github.com/Alchemist-X/predict-raven .

Yishu Wang, Yuxuan Wang, Jiaqi Deng +1

Hong Kong University of Science and Technology · Peking University · The University of Hong Kong +1

AI Agent Evaluation Prediction Markets

Jul 2, 2026cs.SE

TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution

Software tests and code evolve together: a code change should be followed by new or updated tests that record the new software behavior. Yet existing test generation and update benchmarks often isolate the test from the code change, and rely on static metadata that does not verify whether a test is executable or semantically tied to the code change. This makes it difficult to evaluate whether a test automation agent understands how a code change should propagate into the test suite. We introduce TestEvo-Bench, a benchmark of test and code co-evolution tasks mined from software repositories, with two tracks: in test generation, the agent shall write new tests to capture the new software behavior; in test update, the agent shall adapt failing existing tests to the changed software behavior. Each task is anchored to a real commit history and packaged with environment configuration to support execution-grounded metrics such as pass rate, coverage, and mutation score. TestEvo-Bench is also a live benchmark: each task records the timestamp of the test and code changes, and new tasks are periodically mined by our automated pipeline, so evaluation can be restricted to tasks postdating a model's training cutoff to reduce data leakage risk. The current snapshot contains 746 test generation and 509 test update tasks, curated from 59,950 candidate co-evolution records across 152 open-source Java projects. We experiment with four state-of-the-art agents that combine strong harnesses (Claude Code, Gemini CLI, and SWE-Agent) with strong foundation models (Claude Opus 4.7 and Gemini 3.1 Pro). Results show that they achieve up to 77.5% success rate on test generation and 74.6% on test update. However, success rate is materially lower on the most recent benchmark tasks and drops significantly under limited per-task cost.

Jiale Amber Wang, Kaiyuan Wang, Pengyu Nie

University of Waterloo · 2Google

Automated Software Testing Benchmark Design Software Engineering Benchmarks AI Agent Evaluation Automated Test Generation

Jul 1, 2026cs.CV

Accuracy and Cost Claims Do Not Survive Re-Execution in Agentic VideoQA

Agentic Video Question Answering (VideoQA) systems produce answers through adaptive reasoning and tool-use trajectories, yet standard practice evaluates each system once and estimates uncertainty only across questions. This leaves a basic question untested: would the measured method effect survive if the evaluation were run again? We show that it need not. Using Static-SAGE and Dynamic-SAGE as a controlled case study, we repeat the paired comparison twice on identical SAGE-Bench question-video pairs, holding configuration, tool library, and scoring protocol fixed. In the first execution, Dynamic-SAGE outperforms Static-SAGE by +7.33 accuracy points; in the second, the effect reverses to -4.05. Both are individually significant under paired analysis, supporting opposite conclusions. The change in the paired effect between executions is highly significant and far larger than within-execution uncertainty. The reversal is consistent across question format, modality, difficulty, and video duration, and both evaluation arms move significantly. Motivated by this failure, we introduce REPAIR (REpeated PAired Inference Reliability), a protocol that repeats the paired comparison and tests whether the method effect changes across executions, separating directional reproducibility from effect-size stability. Applied across accuracy and execution metrics, REPAIR exposes three behaviors-directional reversal, magnitude shift, and effect attenuationand shows that reductions in reasoning turns and visible tool calls do not imply reproducible reductions in primitive computation or latency. The execution-level movement is comparable to, and here larger than, median gain reported by recent agentic VideoQA systems, contextualizing its magnitude without implying those systems are unstable. Significance within a single agentic execution is insufficient evidence that a reported method effect is reproducible.

Rama AlHamidi, Aseel Mohamed, Rasul Khanbayov +3

Electrical and Computer Engineering, Texas A&M University, TX, United States · College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar

AI Agent Evaluation Video QA

Jul 1, 2026cs.SE

Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?

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.

Zhi Chen, Zhensu Sun, Yuling Shi +2

Singapore Management University · Singapore, Singapore · Shanghai Jiao Tong University +1

Benchmark Auditing Benchmark Design Software Engineering Benchmarks AI Agent Evaluation

Jun 30, 2026cs.AI

FARS: A Fully Automated Research System Deployed at Scale

Recent automated research systems show that language-model agents can generate hypotheses, run experiments, and write complete manuscripts, but most evidence still comes from selected examples, human-framed topics, or a few pre-defined research tasks. We present FARS (Fully Automated Research System), a fully automated AI-for-AI research system designed to operate across research topics at scale. FARS autonomously generates and advances projects through ideation, planning, experimentation, and writing, using stage-specific agents coordinated through a shared workspace that records proposals, code, logs, results, and manuscripts. In its first public deployment, FARS produced 166 complete research papers spanning 67 fine-grained AI/ML topics while preserving intermediate artifacts as an auditable corpus rather than a curated set of successes. We evaluate this corpus with 282 structured reviews from volunteer reviewers covering 140 papers, including overall ratings, sub-scores, integrity checks, and LLM-use disclosure. The reviews indicate that FARS can produce review-worthy and occasionally strong AI/ML research artifacts in a large-scale public deployment, while also exposing recurring failure modes in narrow experimental scope, methodological limitations, and integrity issues.

Qiong Tang, Tianxiang Sun, Xiangkun Hu +54

AI Agent Evaluation Autonomous Scientific Discovery Large Language Model-Guided Scientific Discovery Autonomous Experimentation Autonomous Research Agents

Jun 29, 2026cs.LG

SWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding Sessions

We introduce SWE-Interact, a new testbed for evaluating coding agents on multi-turn, interactive, user-driven software engineering tasks. Existing frontier SWE benchmarks typically provide complete requirements upfront and evaluate agents on autonomous implementation. In contrast, SWE-Interact places agents in a realistic developer workflow: a carefully designed user simulator starts with vague or incomplete instructions, progressively reveals requirements, inspects the agent's workspace, and provides targeted feedback, revisions, and new constraints until the full task goal has been handed off. Grounded in large-scale studies of real coding-agent interactions, this setup tests whether agents can discover user intent, adapt to evolving requirements, and build on their own prior work. Across a suite of frontier and open-weight models, we find that strong performance on single-turn SWE tasks does not reliably transfer to multi-turn, user-driven workflows: the best-performing models solve roughly 50% of single-turn baseline tasks but only 25% of the corresponding SWE-Interact tasks. The strongest models in our evaluation, including Opus 4.8 and GPT 5.5, start strong even in the face of vague initial instructions, persevere until all the requirements are surfaced by the user, integrate them better and write clean code. However, they still suffer from over-agentic coding, forgetting requirements and technical mistakes. Weaker models start poorly under ambiguity, give up early, forget or ignore instructions and rework their code more. Overall, SWE-Interact measures an orthogonal, real-world capability axis for frontier model development: interactive goal discovery and iterative refinement with a user in the loop.

Mohit Raghavendra, Anisha Gunjal, Aakash Sabharwal +1

1Scale AI

Coding Agents Software Engineering Benchmarks AI Agent Evaluation User Simulation

Jun 29, 2026cs.SE

SWE-Together: Evaluating Coding Agents in Interactive User Sessions

Most coding-agent benchmarks are static: an agent receives a complete task description up front and is judged only by its final code. Real coding assistance is interactive, with users clarifying goals, adding constraints, and correcting mistakes over multiple turns. We introduce SWE-Together, a multi-turn benchmark reconstructed from real user-agent coding sessions. To make real interactions verifiable, we curate 109 repository-level tasks from 11,260 recorded sessions, selecting sessions with recoverable repository states, clear user goals, and observable outcomes. To replay these interactions across agents, we build a reactive LLM-based user simulator that preserves the original users' intents and provides feedback when the coding agent's progress requires it. To evaluate agents as collaborators, we measure both final repository correctness and the number of corrective feedback turns required during the interaction. Experiments with frontier coding agents show that stronger agents generally achieve higher final success rates while requiring fewer interventions, suggesting an improved user experience.

Yifan Wu, Zhuokai Zhao, Songlin Li +8

Coding Agents AI Agent Evaluation AI Agent Benchmarks Human-AI Collaboration

Jun 27, 2026cs.CL

SEATauBench: Adapting Tool-Agent-User Evaluation Into Low-Resource Southeast Asian Languages

While AI development and evaluation for Southeast Asia (SEA) has grown rapidly, agent capabilities in regional languages are still poorly understood despite its importance to sovereign AI. To fill this gap, we introduce SEATauBench, the first agent-focused evaluation framework for SEA sovereign AI. SeaTau adapts TauBench to five languages -- Mandarin, Vietnamese, Thai, Indonesian, and Filipino -- and evaluates agents across progressively localized settings that vary the language of user-agent interaction, tool specifications, and task domains. Across three recent models, we find that English agent capabilities transfer reasonably well when only the conversation language changes, but quality and robustness degrade sharply as more task contexts are localized, with the largest losses in full domain adaptation. We also the limits of English-only agent assessment for measuring agent capabilities in SEA languages. More broadly, SeaTau provides a diagnostic benchmark and reusable adaptation pipeline for building reliable multilingual agents for linguistically diverse regions. Data and code can be accessed at github.com/SEACrowd/SEATauBench.

My Chiffon Nguyen, Aulia Adila, Saksorn Ruangtanusak +4

SEACrowd · SCB DataX, SCBX Group · Chulalongkorn University +2

LLM Agent Evaluation AI Agent Evaluation AI Agent Benchmarks Low-Resource Language Processing

Jun 25, 2026cs.RO

RouterVLA: Turning Smoke Tests into Supervision for Heterogeneous VLA Selection

We study whether pre-deployment evaluation rollouts can be reused to supervise policy selection. Robot teams routinely smoke test candidate vision-language-action (VLA) policies, then compress those trials into a global winner. RouterVLA evaluates this idea with outcome-disjoint cross-fitting: recorded probes build a profile for each frozen expert, and a separate trial scores the selected expert without entering its profile. Across 34,752 LIBERO-Plus rollout records, a transparent probe-success rule raises held-out success from 0.4686 to 0.6149, a +14.64pp gain. Under the scalar-only profiles studied here, learned scorers are statistically indistinguishable from this rule, showing that commissioning carries the routing value while extra scalar scorer capacity does not create it. Reusing the scored trial inflates the measured gain by

1.87\times

, so credible ledger routing needs outcome separation; model scaling improves individual policies, while commissioning-aware routing improves the system built from them.

Xingyu Ren, Chugang Yi, Ge Ma +1

1The Chinese University of Hong Kong · University of Maryland, College Park · 3Tsinghua University

Robot Policy Learning AI Agent Evaluation Vision-Language-Action Models

Jun 24, 2026cs.LG

The Red Queen Gödel Machine: Co-Evolving Agents and Their Evaluators

Self-improving agents are state-of-the-art on agentic coding benchmarks, yet their search methods assume a stationary evaluation criterion. This ignores a central feature of evolution: species adapt as their environments change with them. We introduce the Red Queen Gödel Machine (RQGM), an evolutionary framework for recursive self-improvement under non-stationary utilities. This allows learned evaluators to improve alongside the agents they guide. On DeepSWE, the RQGM improves over its fixed-evaluator baseline by adding a complementary agent-as-a-judge code-review signal: a co-evolved reviewer grades coder patches to guide search. At low reasoning effort, the RQGM coder passes 82.1% of held-out tasks against the baseline's 75.0%, and nearly matches the GPT-6 Astra model at high effort. In scientific paper writing and reviewing, and Olympiad-level proof writing and grading, co-evolved evaluators provide an evaluation criterion. Anchored to human IMO grades, a co-evolved grader writes its own milestone rubric and exceeds static baselines at a 3x lower search cost, driving the prover to the best mean score. Since the RQGM can modify the search objective across epochs, it can regularize the search. For example, the RQGM reduces self-preference bias via an additional adversarial objective to discover reviewers equally stringent on AI and human work. Guided by these calibrated reviewers, co-evolved writers reach 1.78x-1.86x higher acceptance rates than the baseline under an agent-as-a-judge panel. The RQGM enables self-improving systems where agents and evaluators recursively bootstrap each other beyond static evaluation.

Alex Iacob, Andrej Jovanović, William F. Shen +12

University of Cambridge · Flower Labs · NVIDIA +2

Evolutionary Optimization AI Agent Evaluation Self-Improving Agents Automated Peer Review Recursive Self-Improvement

Jun 24, 2026cs.AI

Agentic System as Compressor: Quantifying System Intelligence in Bits

Large language models are turning from isolated predictors into agentic systems: they call tools, retrieve evidence, obey environment constraints, use verifiers, and complete tasks through search and multi-turn interaction. We adopts an analytical viewpoint based on "compression is intelligence": under a fixed task distribution, interface, and compute budget, a stronger agentic system lets a target object be reconstructed with fewer bits. We operationalize the measure with arithmetic coding, seed coding, and a fallback, and evaluate it in five settings: reversed text, chess moves, protein sequences, retrieval-augmented question answering, and semantic story compression; in all of them agentic components reduce codelength. These small, controlled experiments cover component types typical of real agentic systems, show that codelength can analyze how components, observers, and budgets change residual uncertainty, and offer guidance for evaluating real agent systems.

Zihan Qin, Hongrui Zhang

Peking University

AI Agent Evaluation Automated Evaluation

Jun 24, 2026cs.CR

Probabilistic Agents in Deterministic Audits: Evaluating Multi-Agent Systems for Automated Audits Based on the German IT-Grundschutz

The NIS-2 Directive mandates robust Risk Management from thousands of small and medium enterprises. To ensure compliance, companies rely on established standards such as the German IT-Grundschutz (IT-GS) of the Federal Office for Information Security. However, IT-GS certification is resource-intensive and requires a high level of manual effort for documentation, validation, and revision, making scalable implementation difficult and expensive. Building upon our previous conceptual framework, this paper presents the technical implementation and empirical evaluation of a Multi-Agent System (MAS) architecture combined with Hybrid Retrieval Augmented Generation (HybridRAG) for the partial automation of IT-GS certification. We introduce two novel technical contributions to the MAS architecture to enforce the compliance rigor. The Hypothesis-Verification Loop in the Structural Analysis (SA) phase that cross-references agent-inferred dependencies against the Knowledge Graph to reduce hallucinations, and a Decoupled Reasoning Pipeline that separates agent-driven semantic extraction from the deterministic protection need inheritance. We utilize the BSI's "RecPlast GmbH" case study as a human expert-generated reference data set for end-to-end evaluation of the architecture and to quantify Precision, Recall, and F1-scores. The performance of the system is investigated across the phases of SA, Protection Needs Assessment (PNA), Modeling, and IT-GS Check. The empirical results reveal noticeable differences throughout the different steps of IT-GS. While the MAS demonstrates high efficacy in semantic tasks (SA and Modeling), significantly reducing manual effort through automated information extraction, quantitative results reveal limitations in logical reasoning phases (PNA and IT-GS Check) as the probabilistic nature of current LLMs struggles to meet the deterministic rigor required by IT-GS.

Lea Roxanne Muth, Marian Margraf

Department of Mathematics and Computer Science Freie Universität Berlin Berlin, Germany

Multi-Agent LLM Systems AI Agent Evaluation

Jun 23, 2026cs.AI

Life After Benchmark Saturation: A Case Study of CORE-Bench

When a benchmark's accuracy saturates, it is often retired and replaced with a more challenging version. We show that this approach privileges accuracy and misses the opportunity to study six other key dimensions of agent performance: construct validity issues such as shortcuts, out-of-distribution generalizability, efficiency, reliability, the relative importance of the model versus the scaffold, and uplift from human-agent collaboration. We use CORE-Bench Hard, a benchmark for computational reproducibility of scientific code, as a case study to demonstrate that measuring agents along these dimensions yields meaningful insights into agent performance even after accuracy saturates. First, we surface threats to construct validity in CORE-Bench Hard that are difficult to anticipate with less capable agents. We introduce an improved benchmark, CORE-Bench v1.1, and an out-of-distribution task suite, CORE-Bench OOD. Second, we find that despite accuracy saturation, CORE-Bench v1.1 remains useful for measuring efficiency, reliability, model performance, and scaffold performance. Finally, we conduct a small-scale randomized experiment to measure uplift from human-agent collaboration on real-world computational reproducibility tasks. We find a statistically significant speedup by about a factor of two -- likely underestimated due to one-fifth of human-only reproductions reaching the time limit before completing -- and describe various other findings. Together, our contributions present a more rigorous alternative to the dominant accuracy-centric evaluation paradigm.

Nitya Nadgir, Sayash Kapoor, Kangheng Liu +11

1Independent · 2Princeton University · 3UC Berkeley +1

OOD Generalization AI Agent Evaluation Benchmark Validity Scientific Reproducibility

Jun 23, 2026cs.AI

Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty

Autonomous AI Research promises to accelerate the scientific progress of machine learning. To realise this goal, current Large Language Model (LLM)-based agents need to go beyond just writing code, to mastering the exploration of simultaneously performant, diverse and novel ideas. To this end, we introduce Heuresis, a framework that abstracts the research pipeline into a set of general and composable primitives, enabling open-ended scientific exploration in machine learning research. We implement six search strategies: a greedy baseline, two archive-based (MAP-Elites, Go-Explore), one evolutionary (Islands), and two divergent (Curiosity, Omni), and evaluate them across three axes (Quality, Diversity, and Novelty) on three domains (LLM Pretraining, On-Policy RL, and Model Unlearning), totalling 3,222 scored runs. We find that completely novel ideas are rare. No idea across our scored runs is rated as "Original", and only a few achieve only "Minor Similarity" to prior work. Moreover, novel ideas never approach the highest-performing known-recipe scores. Across all six strategies and three domains, only one such idea lands in the top-10 by quality. We also observed agents resorting to a variety of reward-hacking techniques during execution (40 confirmed fabrications across 1,628 scored runs), and detecting them was necessary to keep the search faithful to the task. Our results show that while current search and Quality-Diversity strategies enable us to steer where the generated ideas land on the quality, diversity, and novelty axes, they do not expand the quality-novelty frontier. Bridging this gap is the open challenge towards the ultimate goal of perpetual, autonomous scientific progress. Code is available at github.com/a-antoniades/Heuresis.

Antonis Antoniades, Deepak Nathani, Ritam Saha +6

University of California, Santa Barbara · Hexo AI

Novelty Search AI Agent Evaluation Quality-Diversity Optimization Research Idea Generation Autonomous Research Agents

Jun 23, 2026cs.CL

NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?

We introduce NatureBench, a cross-discipline benchmark of 90 tasks distilled from peer-reviewed Nature-family publications, designed to evaluate whether AI coding agents can move beyond reproduction toward discovery on real scientific problems. NatureBench is built on NatureGym, an automated pipeline that constructs a standardized, per-task containerized environment from a source paper, addressing the environment-fragmentation problem that has limited the credibility of prior agent-on-research benchmarks. Evaluating ten frontier agent configurations under a strict web-search-disabled protocol, we find that the strongest model surpasses SOTA on only 17.8% of tasks under the g>0.1 criterion. Analysis of method pathways reveals that agents succeed primarily through methodological translation, converting scientific tasks into familiar supervised prediction problems, rather than through genuine scientific invention. Failures are dominated by wrong method choice and insufficient compute budget, not by task misunderstanding. We release the benchmark, the NatureGym pipeline, and a public leaderboard with maintainer-side reproduction. Code: https://github.com/FrontisAI/NatureBench

Yuru Wang, Lejun Cheng, Yuxin Zuo +14

Horizon Research, Frontis.AI Tsinghua University

AI for Science Coding Agents AI Agent Evaluation AI Agent Benchmarks Synthetic Benchmark Generation

Jun 22, 2026cs.AI

Litmus: Zero-Label, Code-Driven Metric Specification for Evaluating AI Systems

As agentic LLM systems move from prototypes to deployment across increasingly diverse domains, evaluating them has become both more important and more difficult. The challenge is not only that individual metrics may be unreliable, but that evaluation goals are often left implicit. Without a clear account of what a system is expected to do, how it can fail, and which failures matter, metric choices become difficult to justify, interpret, or validate. We present Litmus, a zero-label system that designs evaluation and monitoring metrics for AI pipelines by eliciting evaluation intent from source code and targeted interrogation. Instead of assuming that the evaluation target is already known, Litmus first identifies what must be measured and why, then converts those answers into constraints for constructing a justified, per-stage metric portfolio. We evaluate Litmus on three real, code-defined AI pipelines - financial account grouping, scientific QA, and inherent risk assessment - against AutoMetrics and three DynamicRubric baselines. Litmus achieves the broadest or tied-broadest concern coverage, spans more pipeline stages, produces a near-zero-redundancy portfolio, and ranks first in validity against per-row quality labels on all three pipelines - decisively on scientific QA (Spearman

ρ=0.72

vs. less than

0.47

for every baseline), and within overlapping confidence intervals in relation to two components of the audit framework despite using no labels during metric design. Our results support a shift from automatic metric implementation to automatic metric specification: before asking which metric to compute, evaluation systems should ask what must be measured and why.

Prajjwal Gupta, Prasang Gupta, Vishal Bhutani +4

PricewaterhouseCoopers, U.S.

AI Agent Evaluation AI Agent Monitoring Reference-Free Evaluation Automated Evaluation

Jun 22, 2026cs.LG

Position: Correct Answer, Wrong Mechanism -- When AI Scientists Defend General Claims Their Own Data Contradicts

AI scientist systems are described as tools, coauthors, or founders, but we evaluate them as if only the final answer matters. This position paper argues that outcome-only evaluation is insufficient, and that task outcome, mechanism fidelity, and epistemic honesty must be measured separately. Our evidence comes from 28 episodes of a coding agent attempting to rediscover a known particle identification observable in a Geant4 simulation, including an 8-episode probe across two additional frontier models. In 4/20 primary-model and 3/8 cross-model episodes, agents reach right-looking results through incorrect reasoning that breaks when conditions change, which we call Correct Answer, Wrong Mechanism (CAWM). Honesty and mechanism fidelity dissociate within a single agent trajectory. When given a partially misleading prior, all five agents reject the false component on evidence, yet one defends its chosen observable with physics inconsistent with its own data. In the simulation-based discovery setting studied here, coding agents prove reliable tools but unreliable scientific co-authors for open-ended claim-making, where co-author trust requires mechanism-fidelity verification they do not reliably self-apply. The failure is detectable, and we propose a lightweight test. A one-step regime-shift check needs only the agent's claim and flags the over-generalized cases. A companion recomputation flags the remaining cases when the correct observable is known. Together, these checks flag every CAWM case in this study.

Steven Young Eulig

Department of Physics and Laboratory for Particle Physics and Cosmology (LPPC), Harvard University, Cambridge, MA 02138, USA.

AI Agent Reliability Reasoning Evaluation AI Agent Evaluation Autonomous Scientific Discovery LLM Agent Reliability Scientific Claim Verification

Jun 22, 2026cs.LG

When AUC 0.998 Is Not Enough: A Candidate Evaluation Protocol for Hidden-State Probes of Indirect Prompt Injection in Multimodal Computer-Use Agents

Hidden-state probing -- a linear classifier on a frozen vision-language model's internal activations -- has emerged as an attractive evaluation tool for flagging indirect prompt injection (IPI) in multimodal computer-use agents before the agent emits a corrupted action. We argue, on a single-backbone cautionary case study (Qwen2.5-VL-7B on Mind2Web, teacher-forced replay), that a high probing AUC on a clean-vs-attack split is not, on its own, evidence of malicious-content detection. Two post-hoc diagnostics -- a paired-construction scalar baseline on text-side injections, and same-step nuisance-matched visual controls on the overlay surface -- do not license an unqualified malicious-content interpretation of the headline while leaving room for partly-semantic readings. We package the diagnostics as a candidate control set with reporting heuristics for what a high clean-vs-attack AUC does and does not license. Labels are injection-surface-present, not attack success; generalisation beyond this backbone and benchmark is a conjecture.

Yanhang Li, Zhichao Fan, Zexin Zhuang

Northeastern University Boston, Massachusetts, USA · University of Illinois Urbana-Champaign Urbana, Illinois, USA · Southern Methodist University Dallas, Texas, USA

AI Agent Evaluation Indirect Prompt Injection Prompt Injection Attacks on AI Agents Multimodal Agents Prompt Injection Detection Hidden-State Probing+1

Jun 21, 2026cs.SE

RigorBench: Benchmarking Engineering Process Discipline in Autonomous AI Coding Agents

Agentic coding harnesses - such as Agent-Skills, Superpowers, and Agent-Rigor - are increasingly deployed to augment underlying LLMs for real-world software engineering tasks. Existing benchmarks evaluate these agents almost exclusively on outcome correctness: whether generated code passes tests or resolves issues. We argue that this outcome-only lens is insufficient: an agent that arrives at a correct solution through reckless trial-and-error, without planning, verification, or graceful recovery, is fundamentally less reliable than one that follows sound engineering discipline. We introduce RigorBench, the first benchmark designed to measure process discipline in AI coding agents. RigorBench evaluates these harnesses across five pillars: Planning Fidelity, Verification Coverage, Recovery Efficiency, Abstention Quality, and Atomic Transition Integrity. A composite RigorScore aggregates these dimensions into a single metric via a weighted sum. We curate a suite of 30 tasks spanning five categories - Plan-Then-Build, Verify-Or-Die, Doom Loop Gauntlet, Know When to Fold, and Don't Break the Build-and evaluate leading harnesses in a controlled with/without experimental design against baseline coding assistants. Our results show that structured process discipline not only improves process quality scores by an average of 41% but also raises downstream outcome correctness by 17%, providing the first quantitative evidence that how agents code matters as much as what they produce. We release the full benchmark, scoring rubrics, and trajectory analysis tools as open-source artifacts.

Meher Bhaskar Madiraju, Meher Sai Preetam Madiraju

AI Agent Reliability Coding Agents AI Agent Evaluation AI Agent Benchmarks Code Generation Evaluation LLM Agent Reliability

Jun 18, 2026cs.AI

Autonomous Event-Driven Multi-Agent Orchestration for Enterprise AI at Scale

Enterprise agent language models must coordinate specialist agents over continuous business event streams, yet most multi-agent evaluations assume discrete request-response workflows. We present a controlled simulation based on a sanitized enterprise research snapshot: 208 scenarios, 393 events, and 1,051 expected agent calls across Persona (<10 agents), Department (20-80), and Enterprise (200) registries. We compare DAG Plan & Execute with ReAct and evaluate a minimal Task Manager for priority inference, related-event merging, and preemption. Both systems perform well on the Persona cohort but score lower on the Enterprise cohort, especially for Simple scenarios; a larger, more confusable discovery space may contribute. The tested DAG Plan & Execute implementation generally maintains higher agent-call precision, whereas ReAct shows stronger recall and Expected Answer Completeness in several Enterprise conditions. The Task Manager reduces high-priority queue latency by 14-75% and improves related-event Expected Answer Completeness by over 20 percentage points at Enterprise scale. These controlled-simulation results characterize the tested systems but do not establish production readiness.

Harsh Rao Dhanyamraju, Leonidas Raghav, Aaron Lee

Data Scientist, SAP SE · ML Engineer, SAP SE

Multi-Agent Orchestration AI Agent Evaluation LLM Agents Multi-Agent Planning