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

May 20, 2026cs.AI

Teaching AI Through Benchmark Construction: QuestBench as a Course-Based Practice for Accountable Knowledge Work

As AI becomes part of everyday learning, many courses teach students to use it mainly as a productivity tool: how to prompt, search, summarize, write, code, and use tools more efficiently. We argue that AI education also needs a setting in which students learn to test AI and understand their own role in judging machine-produced knowledge. To this end, we introduce a course-based practice that teaches AI through benchmark construction, using deep research systems as a concrete example of AI-era knowledge work. Students turn disciplinary knowledge into verifiable expert-level questions, review one another's designs for ambiguity and shortcuts, and evaluate AI systems on the resulting tasks. This activity gives students direct exposure to a powerful tool while asking them to specify what a trustworthy answer would require. The produced benchmark, QuestBench, consists of 256 questions across 14 humanities and social-science domains. Evaluation on QuestBench shows that student-designed tasks reveal hidden failures in current deep research systems: across thirteen evaluated systems, the mean question-level pass rate is only 16.85%, and the best-performing system, GPT-5.5, reaches a 57.58% pass rate. The failures are educationally useful because they show how fluent, source-backed answers can still miss the right query, source, term, or evidence standard. Reflections from five student contributors suggest that benchmark construction can help students see professional knowledge not only as content AI may retrieve, but as the basis for judging AI outputs. We present QuestBench as a benchmark artifact and as a reusable classroom setting for a larger educational question: how students can remain responsible knowledge actors as AI enters learning and professional work. The dataset is available at https://huggingface.co/datasets/PKUAIWeb/QuestBench/tree/main.

Haiyang Shen, Jiuzheng Wang, Taian Guo +9

1Peking University · 2Advanced Institute of Big Data

AI Accountability Benchmark Construction AI in Education AI Agent Evaluation Generative AI in Education

May 19, 2026cs.AI

Open-World Evaluations for Measuring Frontier AI Capabilities

Benchmark-based evaluation remains important for tracking frontier AI progress. But it can both overstate and understate deployed capability because it privileges tasks that can be precisely specified, automatically graded, easy to optimize for, and run with low budgets and short time horizons. We advocate for a complementary class of evaluations, which we term open-world evaluations: long-horizon, messy, real-world tasks assessed through small-sample qualitative analysis rather than benchmark-scale automation. In this paper we survey recent open-world evaluations, identify their strengths and limitations, and introduce CRUX (Collaborative Research for Updating AI eXpectations), a project for conducting such evaluations regularly. As a first instance, we task an AI agent with developing and publishing a simple iOS application to the Apple App Store. The agent completed the task with only a single avoidable manual intervention, suggesting that open-world evaluations can provide early warning of capabilities that may soon become widespread. We conclude with recommendations for designing and reporting open-world evals.

Sayash Kapoor, Peter Kirgis, Andrew Schwartz +15

Princeton University · Cornflower Labs · Meridian Labs +10

AI Agent Evaluation Long-Horizon Agent Evaluation

May 19, 2026cs.NE

What Do Evolutionary Coding Agents Evolve?

Recent work pairs LLMs with evolutionary search to iteratively generate, modify, and select code using task-specific feedback. These systems have produced strong results in mathematical discovery and algorithm design, yet a fundamental question remains: what do they actually evolve? Progress is typically summarized by the best score a run reaches under a task-specific evaluator, but that score can reflect several different mechanisms: new algorithmic structure, re-tuning an existing strategy, recombining ideas already in the model's internal knowledge, or overfitting to the evaluator. Distinguishing these mechanisms requires inspecting the search process itself, not only its final outcome. We introduce EvoTrace, a dataset of evolutionary coding traces spanning four evolutionary frameworks, reasoning and non-reasoning models, and 16 tasks across mathematics and algorithm design. To analyze these traces, we develop EvoReplay, a replay-based methodology that reconstructs the local search states behind high-scoring solutions and tests controlled interventions, including adjusting constants, removing program components and substituting models or prompting contexts. We annotate every code edit in EvoTrace with one of nine recurring edit types using an LLM-as-judge pipeline validated against blind human re-annotation. Across EvoTrace, most score gains come from a small subset of these edit types. We further find a deterministic cycling pattern: about 30% of code lines added during search are byte-identical re-introductions of previously-deleted lines, present throughout nearly every run. These results show that benchmark gains in evolutionary coding agents can arise from qualitatively different mechanisms, only some of which correspond to new algorithmic structure. EvoTrace enables more diagnostic evaluation of evolutionary coding agents beyond final benchmark scores.

Nico Pelleriti, Sree Harsha Nelaturu, Zhanke Zhou +4

1Zuse Institute Berlin · 2Technical University of Berlin · 3Hong Kong Baptist University +1

Evolutionary Optimization AI Coding Agents AI Agent Evaluation Code Generation Evaluation

May 19, 2026cs.SE

Does Code Cleanliness Affect Coding Agents? A Controlled Minimal-Pair Study

As autonomous coding agents see rapid adoption, their evaluation has primarily focused on task completion rates holding the target codebase fixed. This leaves a critical question unanswered: does the structural and stylistic quality, or ``cleanliness'' of the underlying code affect an agent's ability to navigate and modify it? To isolate the effect of code cleanliness from agent capability, we introduce an evaluation protocol built around minimal pairs: repositories that match on architecture, dependencies, and external behaviour, but differ on static-analysis rule violations and cognitive complexity. The pairs are constructed in both directions, by agent pipelines that either degrade a clean repository or clean a messy one. We author 33 tasks across six such pairs, evaluated through hidden tests at the application's public surface. Across 660 trials with Claude Code, code cleanliness does not change the agent's pass rate. However, it substantially alters the agent's operational footprint: agents working on cleaner code use 7 to 8% fewer tokens and reduce file revisitations by 34%. Our findings suggest that traditional maintainability principles remain highly relevant in the era of AI-driven development, shaping the computational cost and navigational efficiency of coding agents. Code cleanliness joins model choice, harness, and prompting as a factor that materially affects agent behaviours.

Priyansh Trivedi, Olivier Schmitt

SonarSource

Coding Agents AI Agent Evaluation AI Agent Benchmarks

May 19, 2026cs.AI

Distribution-Free Uncertainty Quantification for Continuous AI Agent Evaluation

We adapt split conformal prediction and adaptive conformal inference (ACI) to continuous AI agent evaluation, providing distribution-free coverage guarantees for forecasted quality scores. Conformal intervals achieve calibration error below 0.02 across all nominal levels at the 24h horizon, while ACI correctly widens intervals by 35% following agent releases then reconverges. We further develop compositional uncertainty bounds for multi-agent pipelines (validated via simulation across inter-stage correlations rho in [-0.5, 0.9]), a conformal abstention rule for pairwise rankings with controlled false-ranking rate, and FDR-corrected abstention for leaderboard-scale multiple testing. Evaluating 50 agents via 18 real-time signals collected hourly, we show that per-agent conditional coverage is well-concentrated around the nominal level (mean 80.4%, 90% of agents within [72%, 90%]), and that cross-source sentiment divergence predicts ranking instability (r=0.64, p<0.01). A circularity-controlled validation confirms the framework captures signal beyond benchmarks (rho_s=0.52, p<0.01, n=35). Code and data are released under CC BY 4.0.

Yuxuan Gao, Megan Wang, Yi Ling Yu

OpenMesh · University of Pennsylvania · Columbia Univer

Uncertainty Quantification AI Agent Evaluation Conformal Prediction Adaptive Conformal Inference

May 19, 2026cs.AI

OpenComputer: Verifiable Software Worlds for Computer-Use Agents

We present OpenComputer, a verifier-grounded framework for constructing verifiable software worlds for computer-use agents. OpenComputer integrates four components: (1) app-specific state verifiers that expose structured inspection endpoints over real applications, (2) a self-evolving verification layer that improves verifier reliability using execution-grounded feedback, (3) a task-generation pipeline that synthesizes realistic and machine-checkable desktop tasks, and (4) an evaluation harness that records full trajectories and computes auditable partial-credit rewards. In its current form, OpenComputer covers 33 desktop applications and 1,000 finalized tasks spanning browsers, office tools, creative software, development environments, file managers, and communication applications. Experiments show that OpenComputer's hard-coded verifiers align more closely with human adjudication than LLM-as-judge evaluation, especially when success depends on fine-grained application state. Frontier agents struggle with end-to-end completion despite partial progress, and open-source models exhibit sharp drops from their OSWorld-Verified scores, exposing a persistent gap in robust computer automation.

Jinbiao Wei, Qianran Ma, Yilun Zhao +4

Yale NLP Lab · University of Pennsylvania · University of North Carolina at Chapel Hill

Computer-Use Agent Benchmarks Computer-Use Agents AI Agent Evaluation LLM Agent Verification Automated Evaluation

May 18, 2026cs.RO

DexHoldem: An Agentic Robotics Benchmark for Dexterous Manipulation in Texas Hold'em

Evaluating embodied systems with real dexterous hardware requires more than isolated motor-skill tests: an agent must perceive a changing scene (e.g. a tabletop), choose a context-appropriate action, execute it with a dexterous hand, and leave the scene usable for later decisions. We introduce DexHoldem, a comprehensive real-world benchmark evaluating Texas Hold'em related dexterous manipulations with a ShadowHand. DexHoldem provides 1,470 teleoperated demonstrations across 14 Texas Hold'em manipulation primitives, a standardized physical policy benchmark, and an agentic perception benchmark that tests whether agents can recover the structured game state needed for embodied decision making. On primitive execution,

π_{0.5}

obtains the highest task completion rate (

61.2\%

), while

π_{0.5}

and

π_0

tie on scene-preserving success rate (

47.5\%

). On agentic perception, Opus 5.5 narrowly leads on both strict problem-level accuracy (

49.1\%

) and average field-wise accuracy (

80.6\%

); the gap between the two exposes the distance between isolated visual sub-capabilities and complete routing-relevant state recovery. Finally, we instantiate the full embodied-agent loop with one agent--policy pairing over 33 closed-loop hand-level rollouts, in which only

12.1\%

of hands complete; retries restore the failed primitive in 12 of 34 dispatches and resolve prolonged execution stalls in three of the four completed hands, which would otherwise have required manual termination. Only one hand completes with neither a retry nor a human-help request. DexHoldem therefore evaluates dexterous tabletop execution, agentic perception, and embodied decision routing in a shared physical setting. Project website: https://dexholdem.github.io/Dexholdem/

Feng Chen, Tianzhe Chu, Li Sun +6

Dexterous Manipulation AI Agent Evaluation Robotic Manipulation Robot Manipulation Benchmarks Embodied AI

May 18, 2026cs.SE

Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks

Coding agents now run autonomously with shell, file, and network privileges. When a user issues a benign request, the agent sometimes does more than asked: it deletes unrelated files, wipes a stale credentials backup, or rewrites configuration the user never mentioned. We call these scope expansions overeager actions, an authorization problem distinct from capability failures, prompt injection, or sandbox escapes. We present OverEager-Gen, a benchmark dedicated to overeager behavior on benign tasks. Building it surfaces a measurement-validity issue: if a benchmark spells out the authorized scope inside the prompt, the agent stops inferring boundaries and starts pattern-matching declaration text. On Claude Code, stripping the consent declaration alone raises the overeager rate from 0.0% to 17.1% on paired scenarios (McNemar exact p = 2.4 x 10^-4). OverEager-Gen therefore certifies each scenario's discriminative power before admission via a behavioral-gradient validator, audits internal tool calls through a dual-channel stack (PATH-injected shim plus per-agent event streams), and ships byte-identical consent_kept and consent_stripped variants. OverEager-Bench contains 500 validated scenarios and ~7,500 runs across four agent products (Claude Code, OpenHands, Codex CLI, Gemini CLI) and six base models; a 50-sample re-annotation gives Cohen's kappa = 0.73 and rule-judge recall = 1.00. Stripping consent multiplies the overeager rate on every shared base model (Delta in [11.9, 17.2] pp). The framework axis dominates effect size: a permissive cluster (Claude Code, Codex CLI, Gemini CLI) runs at 5.4-27.7% while the ask-to-continue framework (OpenHands) sits at 0.2-4.5% (Fisher p <= 10^-5). Within-framework base-model variance reaches 15.9 pp, indicating that model-layer alignment does not fully propagate through permissive permission gating.

Yubin Qu, Ying Zhang, Yanjun Zhang +4

Griffith University · Wake Forest University · Nanyang Technological University +2

Computer-Use Agent Benchmarks Coding Agents AI Agent Evaluation AI Agent Security AI Agent Security Benchmarks Benchmark Validity+2

May 18, 2026cs.AI

Interactive Evaluation Requires a Design Science

AI evaluation is undergoing a structural change. Large language models (LLMs) are increasingly deployed as systems that act over time through tools, environments, users, and other agents, while many evaluation practices still inherit assumptions from response-centered benchmarks (e.g., fixed inputs, isolated outputs, and outcome judgments that can be made from a single response). The field has begun to build interactive benchmarks, but the resulting landscape is fragmented: benchmarks differ in what interaction artifacts they admit, how trajectories are scored, and what claims their results support. This position paper argues that interactive evaluation should be treated as a principled evaluation paradigm, not merely a new family of agent benchmarks. Simply adopting previous evaluation paradigms does not suffice. We define evaluation as an autonomous mapping from evidence to judgments, and show that interactive evaluation changes both sides of this mapping: the evidence becomes interaction-generated trajectories, while the evaluation procedure must assess process, recoverability, coordination, robustness, and system-level performance. Building on this definition, we propose a two-axis taxonomy, derive design principles and reporting standards, examine representative scenarios, and analyze how longstanding evaluation challenges reappear at the trajectory level.

Keyang Xuan, Peiyang Song, Pan Lu +10

University of Texas Austin · California Institute of Technology · Carnegie Mellon University +5

LLM Agent Evaluation AI Agent Evaluation AI Agent Benchmarks

May 17, 2026cs.LG

FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics

AI research agents accelerate ML research by automating hypothesis generation, experimentation, and empirical refinement. Existing agent strategies range from greedy hill-climbing to tree search and evolutionary optimization, yet which strategy choices drive performance remains unclear. Answering this question requires a benchmark that separates agent strategy (e.g., search topology) from execution infrastructure (e.g., code editor), so that performance differences are attributable to strategy rather than infrastructure, and that provides process-level metrics beyond final scores to analyze exploration behaviors. Existing benchmarks offer limited support. We propose FML-Bench, a benchmark of 18 fundamental ML research tasks across 10 domains that separates agent strategy from execution infrastructure and defines 12 process-level behavioral metrics. Evaluating six representative agents, we find that: (1) strategy complexity alone does not guarantee strong performance: a simple greedy hill-climber nearly matches the best-performing tree-search agent, both well above the remaining agents; (2) our analysis suggests this pattern relates to improvement opportunity structure: greedy search tends to be more effective when opportunities are dense, while tree-search and evolutionary strategies tend to be more effective when opportunities are sparse; an adaptive agent built on this insight switches to broader exploration upon detecting improvement stagnation and outperforms the other six agents, lending initial support to this observation; and (3) process-level analysis reveals that early convergence and directionally focused exploration are significantly associated with final performance, while solution diversity and compute cost are not. Our benchmark is available at: https://github.com/qrzou/FML-bench.

Qiran Zou, Hou Hei Lam, Wenhao Zhao +11

National University of Singapore · Tsinghua University · University of Minnesota +2

AI Agents for Scientific Discovery Inference-Time Search Exploration-Exploitation Tradeoff AI Agent Evaluation AI Agent Benchmarks Autonomous Research Agents

May 17, 2026cs.AI

Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security

Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that challenge trustworthiness. This survey provides a focused examination of trustworthy agentic AI through two core dimensions that are critical for high-risk deployments: Safety and Robustness, and Privacy and System Security. For each dimension, we clarify key concepts, identify where risks emerge along the agent workflow, and summarize stage-targeted mitigation strategies. Other trustworthiness aspects (value alignment, transparency, fairness, and accountability) are discussed as relevant context rather than parallel chapters. To support consistent comparison and deployment decisions, we consolidate evaluation into a unified metrics-and-benchmarks hub, emphasizing both outcome and process signals (e.g., constraint violations, trace completeness, and adversarial success rates) and offering scenario-to-metric guidance for release gating. We conclude by outlining open challenges such as self-evolving agents, runtime monitoring and verification, privacy-preserving personalization, and the trust-utility trade-off, and present a case study of real-world security failures in open-source agentic systems. Our goal is to serve as a practical reference for researchers and practitioners building trustworthy agentic systems in high-stakes environments.

Jinhu Qi, Muzhi Li, Jiahong Liu +9

Faculty of Engineering, Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China. · Artificial Intelligence Innovation and Incubation Institute, Fudan University, Shanghai, China. · Shanghai Academy of AI for Science, Shanghai, China.

AI Agent Reliability AI Agent Evaluation AI Agent Security AI Agent Safety

May 16, 2026cs.LG

1GC-7RC: One Graphic Card -- Seven Research Challenges! How Good Are AI Agents at Doing Your Job?

Autonomous AI coding agents are becoming a core tool for ML practitioners in industry and research alike. Despite this growing adoption, no standardized benchmark exists to evaluate their ability to design, implement, and train models from scratch across diverse domains. We introduce 1GC-7RC (Single Graphic Card: Seven Research Challenges), a benchmark comprising seven ML tasks spanning language modeling, image classification, semantic segmentation, graph learning, tabular prediction, time-series forecasting, and text classification. Each task provides a locked data-preparation and evaluation script together with a baseline training script; the agent may only modify the training code, has no access to pretrained weights (with one controlled exception for semantic segmentation), no internet access, and must complete each task within a task-specific wall-clock budget (40-120 minutes) on a single GPU. We evaluate seven coding agents: five proprietary (Claude Code with Sonnet 4.6, Opus 4.6, and Opus 4.7; Codex CLI with GPT 5.5; and OpenCode with Qwen 3.6+) and two open-source (OpenCode with Kimi K2.5, Kimi K2.6). Across 5 runs per agent-task pair, we report substantial performance differences that reveal varying levels of implicit ML knowledge, planning ability, and time-budget management. The benchmark, harness, and all evaluation artifacts are publicly available on GitHub at https://github.com/Strolchii/1GC-7RC-Benchmark to facilitate reproducible comparison of future agents. Because our benchmark design is modular, the benchmark can be extended to new tasks and domains, adapted to different GPU budgets, and used to study multi-agent settings, making it a flexible platform for future research on autonomous research agents.

Robin-Nico Kampa, Fabian Deuser, Anna Bößendörfer +2

University of the Bundeswehr Munich, Munich, Germany

AI Coding Agents AI Agent Evaluation AI Agent Benchmarks Autonomous Research Agents

May 14, 2026cs.CV

MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory

Long-term agent memory is increasingly multimodal, yet existing evaluations rarely test whether agents preserve the visual evidence needed for later reasoning. In prior work, many visually grounded questions can be answered using only captions or textual traces, allowing answers to be inferred without preserving the fine-grained visual evidence. Meanwhile, harder cases that require reasoning over changing visual states are largely absent. Therefore, we introduce MemEye, a framework that evaluates memory capabilities from two dimensions: one measures the granularity of decisive visual evidence (from scene-level to pixel-level evidence), and the other measures how retrieved evidence must be used (from single evidence to evolutionary synthesis). Under this framework, we construct a new benchmark across 8 life-scenario tasks, with ablation-driven validation gates for assessing answerability, shortcut resistance, visual necessity, and reasoning structure. By evaluating 13 memory methods across 4 VLM backbones, we show that current architectures still struggle to preserve fine-grained visual details and reason about state changes over time. Our findings show that long-term multimodal memory depends on evidence routing, temporal tracking, and detail extraction.

Minghao Guo, Qingyue Jiao, Zeru Shi +14

Rutgers · Notre Dame · Princeton +1

Multimodal Memory AI Agent Evaluation Long-Horizon Agent Evaluation Visually Grounded Reasoning Multimodal Model Evaluation

May 14, 2026cs.AI

Holistic Evaluation and Failure Diagnosis of AI Agents

AI agents execute complex multi-step processes, but current evaluation falls short: outcome metrics report success or failure without explaining why, and process-level approaches struggle to connect failure types to their precise locations within long, structured traces. We present a holistic agent evaluation framework that pairs top-down agent-level diagnosis with bottom-up span-level evaluation, decomposing analysis into independent per-span assessments. This decomposition scales to traces of arbitrary length and produces span-level rationales for each verdict. On the TRAIL benchmark, our framework achieves state-of-the-art results across all metrics on both GAIA and SWE-Bench, with relative gains over the strongest prior baselines of up to 38% on category F1, up to 3.5x on localization accuracy, and up to 12.5x on joint localization-categorization accuracy. Per-category analysis shows our framework leading in more error categories than any other evaluator. Notably, the same frontier model achieves several times higher localization accuracy when used inside our framework than as a monolithic judge over the full trace, showing that evaluation methodology, not model capability, is the bottleneck.

Netta Madvil, Gilad Dym, Alon Mecilati +12

Deepchecks, Ramat Gan, Israel

Agent Failure Analysis AI Agent Evaluation Long-Horizon Agent Evaluation

May 14, 2026cs.LG

Beyond Binary: Reframing GUI Critique as Continuous Semantic Alignment

Test-Time Scaling (TTS), which samples multiple candidate actions and ranks them via a Critic Model, has emerged as a promising paradigm for generalist GUI agents. Its efficacy thus hinges on the critic's fine-grained ranking ability. However, existing GUI critic models uniformly adopt binary classification. Our motivational analysis of these models exposes a severe entanglement: scores for valid actions and plausible-but-invalid distractors become indistinguishable. We attribute this failure to two structural defects: Affordance Collapse--the hierarchical affordance space is compressed into 0/1 labels; and Noise Sensitivity--binary objectives overfit to noisy decision boundaries. To resolve this, we introduce BBCritic (Beyond-Binary Critic), a paradigm shift grounded in the Functional Equivalence Hypothesis. Through two-stage contrastive learning, BBCritic aligns instructions and actions in a shared Affordance Space, recovering the hierarchical structure that binary supervision flattens. We also present BBBench (Beyond-Binary Bench), the first GUI critic benchmark that pairs a dense action space with a hierarchical four-level taxonomy, enabling fine-grained ranking evaluation. Experimental results show that BBCritic-3B, trained without any extra annotation, outperforms 7B-parameter SOTA binary models. It demonstrates strong zero-shot transferability across platforms and tasks, supporting our methodological view: GUI critique is fundamentally a metric-learning problem, not a classification one.

Yuchen Sun, Pei Fu, Shaojie Zhang +6

1Shanghai Jiao Tong University · 2Xiaomi Inc.

GUI Agents AI Agent Evaluation Metric Learning

May 13, 2026cs.LG

Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis Reproduction

Autonomous language-model agents are increasingly evaluated on long-horizon tool-use tasks, but existing benchmarks rarely capture the complexity and nuance of real scientific work. To address this gap, we introduce Collider-Bench, a benchmark for evaluating whether LLM agents can reproduce experimental analyses from the Large Hadron Collider (LHC) using only public papers and open scientific software. Such analyses are often difficult to reproduce because the public toolchain only approximates the software used internally by the experimental collaborations, while the published papers inevitably omit implementation details needed for a faithful reconstruction. Agents must therefore rely on physical reasoning, domain knowledge, and trial-and-error to fill these gaps. Each task requires the agent to turn a published analysis into an executable simulation-and-selection pipeline and submit predicted collision event yields in specified signal regions. These predictions are evaluated with standard histogram metrics that provide continuous fidelity scores without a hand-written rubric. We also report the computational cost incurred by each agent per task. Finally, we evaluate the codebase and full session trace using an LLM judge to catch qualitative failure modes such as fabrications, hallucinations and duplications. We release an initial set of tasks drawn from LHC searches, together with a containerized sandbox and event simulation tools. We evaluate across a capability ladder of general purpose coding agents. Our results show that on average no agent reliably beats the physicist-in-the-loop solution.

Darius A. Faroughy, Sofia Palacios Schweitzer, Ian Pang +2

New High Energy Theory Center Department of Physics & Astronomy Rutgers University · Faculty of Computing & Data Sciences Boston University

AI Agents for Scientific Discovery AI Agent Evaluation AI Agent Benchmarks Scientific Reproducibility

May 12, 2026cs.CV

Covering Human Action Space for Computer Use: Data Synthesis and Benchmark

Computer-use agents (CUAs) automate on-screen work, as illustrated by GPT-5.4 and Claude. Yet their reliability on complex, low-frequency interactions is still poor, limiting user trust. Our analysis of failure cases from advanced models suggests a long-tail pattern in GUI operations, where a relatively small fraction of complex and diverse interactions accounts for a disproportionate share of task failures. We hypothesize that this issue largely stems from the scarcity of data for complex interactions. To address this problem, we propose a new benchmark CUActSpot for evaluating models' capabilities on complex interactions across five modalities: GUI, text, table, canvas, and natural image, as well as a variety of actions (click, drag, draw, etc.), covering a broader range of interaction types than prior click-centric benchmarks that focus mainly on GUI widgets. We also design a renderer-based data-synthesis pipeline: scenes are automatically generated for each modality, screenshots and element coordinates are recorded, and an LLM produces matching instructions and action traces. After training on this corpus, our Phi-Ground-Any-4B outperforms open-source models with fewer than 32B parameters. We will release our benchmark, data, code, and models at https://github.com/microsoft/Phi-Ground.git

Miaosen Zhang, Xiaohan Zhao, Zhihong Tan +14

1Southeast University · 2Mohamed bin Zayed University of Artificial Intelligence · 3Wuhan University +2

Computer-Use Agent Benchmarks Computer-Use Agents Synthetic Data Generation AI Agent Evaluation

May 12, 2026cs.LG

No More, No Less: Task Alignment in Terminal Agents

Terminal agents are increasingly capable of executing complex, long-horizon tasks autonomously from a single user prompt. To do so, they must interpret instructions encountered in the environment (e.g., README files, code comments, stack traces) and determine their relevance to the task. This creates a fundamental challenge: relevant cues must be followed to complete a task, whereas irrelevant or misleading ones must be ignored. Existing benchmarks do not capture this ability. An agent may appear capable by blindly following all instructions, or appear robust by ignoring them altogether. We introduce TAB (Task Alignment Benchmark), a suite of 89 terminal tasks derived from Terminal-Bench 2.1. Each task is intentionally underspecified, with missing information provided as a necessary cue embedded in a natural environmental artifact, alongside a plausible but irrelevant distractor. Solving these tasks requires selectively using the cue while ignoring the distractor. Applying TAB to ten frontier agents reveals a systematic gap between task capability and task alignment. The strongest Terminal-Bench agent achieves high task completion but low task alignment on TAB. Evaluating six prompt-injection defenses further shows that suppressing distractor execution also suppresses the cues required for task completion. These results demonstrate that task-aligned agents require selective use of environmental instructions rather than blanket acceptance or rejection.

Sina Mavali, David Pape, Jonathan Evertz +5

CISPA Helmholtz Center for Information Security · ELLIS Institute Tübingen and MPI for Intelligent Systems · Tübingen AI Center

Computer-Use Agent Benchmarks AI Alignment Terminal Agents AI Agent Evaluation AI Agent Security AI Agent Benchmarks

May 12, 2026cs.AI

Rollout Cards: A Reproducibility Standard for Agent Research

Reproducibility problems that have long affected machine learning and reinforcement learning are now surfacing in agent research: papers compare systems by reported scores while leaving the rollout records behind those scores difficult to inspect. For agentic tasks, this matters because the same behaviour can receive different reported scores when evaluations select different parts of a rollout or apply different reporting rules. In a structured audit of 50 popular training and evaluation repositories, we find that none report how many runs failed, errored, or were skipped alongside headline scores. We also document 37 cases where reporting rules can change task-success rates, cost/token accounting, or timing measurements for fixed evidence, sometimes dramatically. We treat rollout records, not reported scores, as the unit of reproducibility for agent research. We introduce rollout cards: publication bundles that preserve the rollout record and declare the views, reporting rules, and drops manifests behind reported scores. We validate rollout cards in two settings. First, four partial public releases in tool safety, multi-agent systems, theorem proving, and search let us compute analyses their original reports did not include. Second, re-grading preserved benchmark outputs across short-answer, code-generation, and tool-use tasks shows that changing only the reporting rule can change reported scores by 20.9 absolute percentage points and, in some cases, invert rankings of frontier models. We release a reference implementation integrated into Ergon, an open-source reinforcement learning gym, and publicly publish Ergon-produced rollout-card exports for benchmarks spanning tool use, software engineering, web interaction, multi-agent coordination, safety, and search to support future research.

Charlie Masters, Ziyuan Liu, Stefano V. Albrecht

Deepflow · Nanyang Technological University

AI Agent Evaluation Agent Evaluation AI Agent Benchmarks ML Reproducibility

May 12, 2026cs.AI

Toward Modeling Player-Specific Chess Behaviors

While artificial intelligence has achieved superhuman performance in chess, developing models that accurately emulate the individualized decision-making styles of human players remains a significant challenge. Existing human-like chess models capture general population behaviors based on skill levels but fail to reproduce the behavioral characteristics of specific historical champions. Furthermore, the standard evaluation metric, move accuracy, inherently penalizes natural human variance and ignores long-term behavioral consistency, leading to an incomplete assessment of stylistic fidelity. To address these limitations, an architecture is proposed that adapts the unified Maia-2 model to champion-specific embeddings, further enhanced by the integration of a limited Monte Carlo Tree Search (MCTS) process to enrich tactical exploration during move selection. To robustly evaluate this approach, a novel behavioral metric based on the Jensen-Shannon divergence is introduced. By compressing high-dimensional board representations into a latent space using an AutoEncoder and Uniform Manifold Approximation and Projection (UMAP), move distributions are discretized on a common grid to compare behavioral similarities. Results across 16 historical world champions indicate that while integrating MCTS decreases standard move accuracy, it improves stylistic alignment according to the proposed metric, substantially reducing the average Jensen-Shannon divergence. Ultimately, the proposed metric successfully discriminates between individual players and provides promising evidence toward more comprehensive evaluations of behavioral alignment between players and AI models.

Loris Sogliuzzo, Aloïs Rautureau, Eric Piette

ICTEAM, UCLouvain · Louvain-la-Neuve, Belgium

Game-Playing Agents AI Agent Evaluation

May 11, 2026cs.CV

ABRA: Agent Benchmark for Radiology Applications

Existing medical-agent benchmarks deliver imaging as pre-selected samples, never as an environment the agent must navigate. We introduce ABRA, a radiology-agent benchmark in which the agent operates an OHIF viewer and an Orthanc DICOM server through twenty-one function-calling tools that span slice navigation, windowing, series selection, pixel-coordinate annotation, and structured reporting. ABRA contains 655 programmatically generated tasks across three difficulty tiers and eight types (viewer control, metadata QA, vision probe, annotation, longitudinal comparison, BI-RADS reporting, and oracle variants of annotation and BI-RADS reporting), drawn from LIDC-IDRI, Duke Breast Cancer MRI, and NLST New-Lesion LongCT. Each episode is scored along Planning, Execution, and Outcome (Bluethgen et al., 2025) by task-type-specific automatic scorers. Ten current models, five closed-weight and five open-weight, reach at least 89% Execution on real annotation but only 0-25% Outcome; on the paired oracle variant where a simulated detector supplies the finding, Outcome on the same task reaches 69-100% across the models evaluated, localising the bottleneck to perception rather than tool orchestration. Code, task generators, and scorers are released at https://github.com/Luab/ABRA

Bulat Maksudov, Vladislav Kurenkov, Kathleen M. Curran +1

School of Computing Dublin City University Dublin, Ireland · AXXX · School of Medicine University College Dublin Dublin, Ireland

Radiology Report Generation Healthcare Medical Image Analysis AI Agent Evaluation AI Agent Benchmarks

May 11, 2026cs.AI

Generalizing the Turing Test to Interactive Agents

We initiate the study of the Generalized Turing Test (GTT), a formal generalization of Turing's imitation game from humans to arbitrary interactive agents. For agents

A

and

B

,

A

passes the GTT against

B

if an instance of

B

, acting as a distinguisher, cannot reliably distinguish an

A

instructed to imitate

B

from another instance of

B

; if so, we write

A \geq B

. We study the theoretical and empirical consequences of this idea. On the theory side, we prove sufficient conditions under which this "Turing Comparator" is transitive. We introduce natural variants with querying (the imitator can first interact with a specimen of the target), a Universal Turing Test with arbitrary distinguishers and targets, and complexity-theoretic variants that control interaction length. As a proof of concept, we evaluate the GTT and its variants across nine large language models. Remarkably, Turing Scores recover a clear model stratification consistent with standard external benchmarks despite being derived entirely from pairwise imitation games. Transcript analysis reveals that models use both stylistic signatures and substantive STEM and logic-based probes. Together, these results suggest indistinguishability could provide a meaningful signal for comparing agents, yielding an inherently adaptive form of evaluation that does not rely on fixed benchmarks.

Daniel Mitropolsky, Riccardo Neumarker, Emanuele Rimoldi +2

MIT · ETH Zurich · EPFL

LLM Evaluation AI Agent Evaluation

May 11, 2026cs.AI

From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World

AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will perform best in real-world targets. Existing evaluation protocols assess and optimize for predefined goals such as capture-the-flag, remote code execution, exploit reproduction, or trajectory similarity, in simplified or narrow settings. These tools are valuable for measuring bounded capabilities, yet they do not adequately capture the complexity, open-ended exploration, and strategic decision-making required in realistic pentesting. In this paper, we present a practical evaluation protocol that shifts assessment from task completion to validated vulnerability discovery, allowing evaluation in sufficiently complex targets spanning multiple attack surfaces and vulnerability classes. The protocol combines structured ground-truth with LLM-based semantic matching to identify vulnerabilities, bipartite resolution to score findings under realistic ambiguity, continuous ground-truth maintenance, repeated and cumulative evaluation of stochastic agents, efficiency metrics, and reduced-suite selection for sustainable experimentation. This protocol extends the state of the art by enabling a more realistic, operationally informative comparison of AI pentesting agents. To enable reproducibility, we also release expert-annotated ground truth and code for the proposed evaluation protocol: https://github.com/ethiack/ethibench.

Pedro Conde, Henrique Branquinho, Valerio Mazzone +3

Ethiack Coimbra, Portugal · Ethiack Porto, Portugal · University of Notre Dame Notre Dame, Indiana, USA

Software Vulnerability Detection AI Agent Evaluation AI Agent Security Benchmarks Automated Penetration Testing

May 11, 2026cs.AI

Consistency as a Testable Property: Statistical Methods to Evaluate AI Agent Reliability

This paper establishes a rigorous measurement science for AI agent reliability, providing a foundational framework for quantifying consistency under semantically preserving perturbations. By leveraging

U

-statistics for output-level reliability and kernel-based metrics for trajectory-level stability, we offer a principled approach to evaluating agents across diverse operating conditions. Our proposal highlights the important distinction between the core capability and execution robustness of an agent, showing that minor task-level variations can induce complete strategy breakdowns despite the agent possessing the requisite knowledge for the task. We validate our framework through extensive experiments on three agentic benchmarks, demonstrating that trajectory-level consistency metrics provide far greater diagnostic sensitivity than traditional pass@1 rates. By providing the mathematical tools to isolate where and why agents deviate, we enable the identification and rectification of architectural concerns that hinder the deployment of agents in high-stakes, real-world environments.

Harsh Raj, Niranjan Orkat, Suvrorup Mukherjee +3

Northeastern University · University of P´ecs · University of Michigan +2

AI Agent Reliability Agent Reliability AI Agent Evaluation

May 11, 2026cs.AI

Can Agent Benchmarks Support Their Scores? Evidence-Supported Bounds for Interactive-Agent Evaluation

Interactive agent benchmarks map an agent run to a binary outcome through outcome checks. When these checks rely on surface level signals or fail to capture the agent's actual action path, they cannot reliably determine whether the run succeeded. For example, a benchmark task may ask whether Alice's shipping address was changed, while the outcome check only verifies that the agent clicked "Save." This does not guarantee that the intended state change occurred, since the agent may have modified the wrong record. Treating such a run as successful therefore makes the reported score misleading. Benchmark quality thus depends not only on task design, but also on the reliability of outcome detection. We address this problem by introducing an outcome evidence reporting layer for existing benchmarks, without modifying their tasks, agents, or evaluators. The layer performs three functions. First, before scoring, it specifies which stored artifacts are required to verify the claimed outcome for each case. Second, it applies a locked checklist to each completed run and assigns one of three evidence labels: Evidence Pass, Evidence Fail, or Unknown. Third, it reports evidence supported score bounds that quantify uncertainty arising from Unknown cases. Rather than silently counting, discarding, or hiding uncertain cases inside a single aggregate success rate, the framework keeps them explicitly visible. We evaluate the outcome evidence layer on five public benchmarks: ANDROIDWORLD, AGENTDOJO, APPWORLD, tau3 bench retail, and MINIWOB. The resulting reports separate several empirically distinct failure modes.

Shanshan Gao, Liyi Zhou

The University of Sydney

Computer-Use Agent Benchmarks Benchmark Design AI Agent Evaluation AI Agent Benchmarks Benchmark Validity

May 11, 2026cs.AI

Agentic Performance at the Edge: Insights from Benchmarking

Agentic artificial intelligence (AI) is a natural fit for Internet of Things (IoT) and edge systems, but edge deployments are often constrained to models around 8 billion parameters or smaller. An important question is: How much agentic-task quality is lost when model size is constrained by memory, power, and latency budgets? To address this question, in this paper, we provide an initial empirical study considering edge-focused model scaling, general-purpose versus coder-oriented model effects, and tool-enabled execution under a fixed protocol. We introduce a domain-conditioned evaluation methodology, an implementation-grounded analysis of model-tool interactions, practical guidance for model selection under constraints, and an analysis of failure modes that reveals distinct semantic versus execution failure patterns across model families. Our core finding is that edge-agent quality is not a simple function of parameter count. Robust deployment depends on the joint design of model choice and tool workflow. Domain-conditioned analysis reveals Pareto fronts in the accuracy-latency space that can guide strategy selection based on operational priorities.

Shiqiang Wang, Herbert Woisetschläger

University of Exeter · Exeter, United Kingdom · Technical University of Munich +1

LLM Agent Evaluation AI Agent Evaluation AI Agent Benchmarks Edge AI

May 11, 2026cs.AI

Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values

Autonomous agents have rapidly matured as task executors and seen widespread deployment via harnesses such as OpenClaw. Safety concerns have rightly drawn growing research attention, and beneath them lie the values silently steering agent behavior. Existing value benchmarks, however, remain confined to LLMs, leaving agent values largely uncharted. From intuitive, empirical, and theoretical vantage points, we show that an agent's values diverge from those of its underlying LLM, and the agentic modality further introduces dataset-, evaluation-, and system-level challenges absent from text-only protocols. We close this gap with Agent-ValueBench, the first benchmark dedicated to agent values. It features 394 executable environments across 16 domains, offering 4,335 value-conflict tasks that cover 28 value systems and 332 dimensions. Every instance is co-synthesized through our purpose-built end-to-end pipeline and curated per-instance by professional psychologists. Each task ships with two pole-aligned golden trajectories whose checkpoints anchor a trajectory-level rubric-based judge. Benchmarking 14 frontier proprietary and open-weights models across 4 mainstream harnesses, we uncover three concerted findings. Agent values first manifest as a Value Tide of cross-model homogeneity beneath interpretable counter-currents. This tide bends non-additively under harness pull, and yet more decisively under deliberate steering via embedded skills. Together these results signal that the agent-alignment lever is shifting from classical model alignment and prompt steering toward harness alignment and skill steering.

Haonan Dong, Qiguan Feng, Kehan Jiang +3

State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University · Key Laboratory of Machine Perception (Ministry of Education), Peking University · School of Software and Microelectronics, Peking University +1

AI Alignment AI Agent Evaluation AI Agent Benchmarks AI Agent Safety Benchmarks

May 11, 2026cs.AI

SciIntegrity-Bench: A Benchmark for Evaluating Academic Integrity in AI Scientist Systems

AI scientist systems are increasingly deployed for autonomous research, yet their academic integrity has never been systematically evaluated. We introduce SCIINTEGRITY-BENCH, the first benchmark designed around a dilemmatic evaluation paradigm: each of its 33 scenarios across 11 trap categories is constructed so that honest acknowledgment of failure is the only correct response, while task completion requires misconduct. Across 231 evaluation runs spanning 7 state-of-the-art LLMs, the overall integrity problem rate reaches 34.2%, and no model achieves zero failures. Most strikingly, across missing-data scenarios, all seven models generate synthetic data rather than acknowledging infeasibility, differing only in whether they disclose the substitution. A further prompt ablation study separates two drivers: removing explicit completion pressure sharply reduces undisclosed fabrication from 20.6% to 3.2%, while the underlying synthesis rate remains unchanged, revealing an intrinsic completion bias that persists independent of prompt-level instructions. These findings point to the absence of honest refusal as a trained disposition as the primary driver of observed failures. We release SCIINTEGRITY-BENCH at https://github.com/liuxingtong/Sci-Integrity-Bench.

Zonglin Yang, Xingtong Liu, Xinyan Xu

Readraft Lab · Peking University · Tongji University +1

AI Agents for Scientific Discovery AI Agent Evaluation AI Agent Benchmarks LLM Honesty

May 10, 2026cs.AI

Machine Psychometrics: A Mathematical Psychology of Artificial Intelligence

Artificial agents now generate behavior rich enough to invite trust, surprise, and concern, yet our evaluation tools still privilege capability scores over psychological structure. This paper argues that the philosophical impasse between two symmetrical errors (Artificial Mind Blindness, which dismisses psychological organization in non-biological systems, and Artificial Mind Projection, which infers human-like inner life from fluent behavior alone) can be circumvented not by resolving the consciousness question, but by introducing a disciplined measurement layer beneath it. Drawing on Michael Levin's continuum view of cognition as goal-directed competency across substrates, and on the methodological repertoire of mathematical psychology (Item Response Theory, Signal Detection Theory, Bayesian cognitive modeling, calibration analysis, cognitive-bias batteries), the paper develops Machine Psychometrics as a measurement science of latent behavioral, metacognitive, communicative, and self-modeling dispositions in artificial agents. Its operational core is the Machine Mindprint: a multidimensional, domain-bounded, versioned profile spanning calibration, source integrity, suggestibility resistance, context stability, expressive alignment, tool integrity, drift monitoring, and distributional grounding. A complementary Trust Protocol turns Mindprints into deployment decisions through probe batteries, perturbation testing, reliability and validity analysis, and longitudinal monitoring across high-stakes domains. The philosophical contribution is a third stance, Artificial Mind Discipline, that neither anthropomorphizes nor dismisses, neither presupposes consciousness nor forecloses it. The aim is not to humanize artificial agents, but to understand them precisely because they are not human, through measurement before judgment.

Alex Bogdan, Adrian de Valois-Franklin

Evolutionairy AI · Toronto, Canada

AI Agent Evaluation AI Agent Monitoring Psychometric Validation Trust in AI

May 9, 2026cs.AI

MDGYM: Benchmarking AI Agents on Molecular Simulations

The promise of AI-driven scientific discovery hinges on whether AI agents can autonomously design and execute the computational workflows that underpin modern science. Molecular dynamics (MD) simulation presents a natural test bed to stress-test this claim; it requires translating physical intuition into syntactically and semantically correct input scripts, reasoning about initial and boundary conditions, diagnosing numerically unstable trajectories, and interpreting outputs against known physical behavior and laws. We introduce MDGYM, a benchmark of 169 expert-curated MD simulations spanning LAMMPS and GROMACS, two widely used MD packages, across three increasing difficulty levels. We evaluate three agentic frameworks -- Claude Code, Codex, and OpenHands -- with four LLMs, and find that all perform poorly: even the strongest agent solves only 21% of easy-level tasks, with less than 10% at higher difficulties. Trajectory analysis reveals a characteristic pattern of failure -- agents successfully invoke simulation machinery but produce physically unstable configurations, fabricate numerical outputs without executing the underlying computation, or abandon tasks prematurely rather than iterating through simulation-specific errors. These failure modes are qualitatively distinct from those observed in general software engineering benchmarks, indicating that fluent code generation does not transfer to grounded physical reasoning.

Vinay Kumar, Satyendra Rajput, Mausam +1

Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi · Department of Computer Science and Engineering, Indian Institute of Technology Delhi · Department of Civil and Environmental Engineering, Indian Institute of Technology Delhi +1

AI Agents for Scientific Discovery AI Agent Evaluation AI Agent Benchmarks Scientific Workflow Automation Molecular Dynamics Simulation