AI Agent Benchmarks

Follow this topic Ask about this topic

Momentum

148 papers in the last four weeks, up 185% on the four weeks before. 1.5% of all new papers.

Jul 13Week of Sep 28

Latest papers 1,013

Jul 29, 2026cs.AI

Automated Transcript Analysis for Detecting Flaws in Agentic Benchmarks

Capabilities of frontier models are often assessed using agentic benchmarks. To trust these results, benchmarks must accurately measure what they claim to and be free from invalidating flaws. Previous manual audits of benchmarks such as SWE-Bench-Verified have uncovered several validity issues in transcripts. However, manual review is difficult to scale, and it is unclear whether automated methods can reliably surface flaws that compromise benchmark validity. In this paper, we developed AI scanners to detect four types of validity issues: ground truth access, tool failure, guessing vulnerability, and answer format ambiguity. We produced grading rubrics for each to instruct human labeling, and evaluated the scanners against human labels on a held-out test set of Inspect Evals benchmarks. Our scanners identified several verified quality issues in five widely used benchmarks, including cases unlikely to be caught by random manual inspection. Not all cases were identified, and scanner performance varied substantially across benchmarks, criteria and models. We highlight several open challenges to be addressed to improve scanners for stronger quality assurance claims, including broader standardization gaps in the evaluation field that degrade scanner performance. Together, these results serve as a proof of concept for using automated transcript analysis to audit benchmark quality more broadly.

Jeff Mohl, Nelson Gardner-Challis, Magda Dubois +6

Independent · UK AI Security Institute · MARS +4

Benchmark Auditing AI Agent Benchmarks Benchmark Validity Automated Evaluation

Jul 29, 2026cs.AI

Skill Use or Skill Theater? Evaluating the Reasoning Backroom in Skill-Augmented Language Agents

Reusable skills are becoming a standard interface for extending language agents with task procedures. Yet evaluators usually infer skill use from visible reasoning or the agent's own attribution. These signals show what the agent appears to use, not whether the skill changed its decision. We ask whether skill-augmented agents exhibit a \textbf{Reasoning Backroom}, a systematic gap between stated skill use and intervention-measured influence. We introduce BACKTRACE, an evaluation framework that pairs each skill-conditioned answer with a matched no-skill counterfactual, intervenes on skill meaning, wording, identity, content, and assignment, and elicits attribution only after the answer is committed. We instantiate the framework as BACKROOMBench, a verified testbed spanning controlled logic and competition mathematics, multiple skill conditions, single-agent and multi-agent settings, and diverse model families. Our evaluation reveals a pervasive provenance failure. Across models and domains, stated skill use often remains stable while causal reliance and signed utility vary, producing both silent uptake and performative use. Behavioral effects follow procedural content more reliably than displayed skill identity, whereas stated attributions respond strongly to artifact availability. Observational detectors based on direct skill-use claims, text mentions, trace similarity, and an LLM judge do not identify which decisions actually depend on the skill. In multi-agent systems, skill influence can survive communication even after its source is lost, while no-skill teams still name skills and sources that were never supplied. These findings establish the Reasoning Backroom as a general AI provenance problem whose audit requires intervention.

Jinwei Hu, Yi Qi, Xinmiao Huang +3

School of Computer Science and Informatics, University of Liverpool, UK · Department of Computer Science, University of Leeds, UK · Department of Computer Science, Mohamed bin Zayed University of Artificial Intelligence, UAE

LLM Agent Evaluation AI Agent Benchmarks

Jul 29, 2026cs.AI

VAmoS Bench: Voice Agent Simulation Bench

Production voice agents span cascaded, speech-to-speech, and hybrid architectures. Voice-agent benchmarks typically measure component quality and conversational properties such as word error rate, latency, naturalness, and turn-taking. Fewer measure whether the agent handled a phone call correctly on its own. Contact centers refer to this as ``containment'': the share of phone calls the automated system resolves without handing off to a human. On some phone calls the right outcome is refusal or a redirect. To address this gap, we introduce VAmoS Bench, the Voice Agent Simulation Bench. It measures complete voice-agent systems end to end in a stateful customer-support task. The agent is Riley, a credit-card support representative for a fictional bank who can freeze, cancel, replace, or activate a card. Each of 100 scenarios supplies a simulated caller with a private goal and a seeded PostgreSQL backend. The platform uses each scenario to populate and activate an isolated simulation in which the caller reaches Riley over audio; roughly one-third apply adversarial pressure. The agent can use five tools that execute real SQL against the backend. Each scenario also defines binary assertions. A grader evaluates them against the complete trace of what the caller and agent said and what the agent did, including tool invocations, arguments, and returned rows. This catches an agent that claims to have changed a card without updating the database, as well as one that makes the right database change while disclosing protected information. This first benchmark version focuses on financial services. Its evaluation protocol supports an evolving leaderboard: additional voice agents can be evaluated on the same version, while later versions can expand the tasks and scenarios.

Joshua Meyer, Sahar Shayegan, Ritiz Tambi +5

Veris AI

Voice Agent Evaluation Customer Support Automation LLM Agent Evaluation AI Agent Benchmarks Tool-Using Agents Conversational Agents

Jul 29, 2026cs.AI

PAUSE: A User-Centric Benchmark for Personal AI Assistants in Unified Service Environments

Personal AI assistants are increasingly deployed as task-oriented, tool-augmented agents that operate within unified service environments to support everyday user activities. In realistic settings, such assistants must reason over persistent user state, respect user-specific configurations and permissions, and sustain long-horizon, constraint-aware interactions across multiple services. Existing benchmarks, however, often fragment service contexts or abstract away user state, limiting their ability to evaluate user-centric personal assistant behavior in realistic service settings. We introduce PAUSE, a user-centric benchmark for evaluating personal AI assistants in stateful, service-integrated environments. PAUSE captures core challenges of real-world assistant deployment by requiring agents to coordinate actions across heterogeneous user-owned resources while maintaining consistency with environment state, authorization constraints over multi-turn interactions. The benchmark incorporates explicit user-agent interaction via realistic user simulation, enabling evaluation beyond static tool execution. To support principled and reproducible evaluation, PAUSE adopts a multi-regime evaluation framework aligned with task characteristics. Open-ended service management tasks are assessed using semantic and trajectory-level behavioral metrics, while constraint-intensive tasks admit deterministic, state-based verification. Benchmark results show that even state-of-the-art proprietary models fail to reach 70% task completion on scenarios requiring stateful reasoning and configuration awareness, revealing consistent and interpretable failure patterns. Finally, we present a user-centric synthesis pipeline that enables scalable generation of coherent service environments, user configurations, and reliably annotated tasks, supporting benchmark extensibility and future research.

Haoyu Chen, Xirui Shi, Yuyao Wang +2

Electrical and Computer Engineering

Long-Horizon Agent Evaluation AI Agent Benchmarks Synthetic Benchmark Generation Personal AI Agents

Jul 29, 2026cs.CL

LayerRAG-Bench: A Cross-Layer Reliability Benchmark for Agentic Retrieval-Augmented Generation

Agentic retrieval-augmented generation systems can produce answers that appear grounded while failing at the evidence, tool-contract, authorization, or session-state layer. We introduce LayerRAG-Bench, a controlled cross-layer reliability benchmark with 8 enterprise domains, 240 tasks, 9 fault scenarios, 2 contract modes, and 38,880 live task-level records across nine models from OpenAI, Anthropic, and Gemini. Schema normalization raises schema-drift success from 0.000 to 0.913, but stale evidence, missing tool output, denied permissions, and wrong-session context are not recovered by schema normalization. Groundedness-only evaluation also produces substantial false positives under stale and wrong-session evidence. These results support a layer-specific evaluation principle: a reliability intervention should be credited for repairing its target layer without being mistaken for a universal fix.

Musa Shams

Independent Researcher

AI Agent Reliability Retrieval-Augmented Generation Tool-Augmented Language Model Agents Language Model Generation Evaluation AI Agent Benchmarks Agentic RAG+3

Jul 29, 2026cs.CL

APEX-Accounting

We introduce APEX-Accounting, a benchmark built by Mercor in partnership with Ramp, to assess whether frontier models can do the real work of accountants. Tasks include reconciling accounts, accruing expenses, posting transactions, and producing reports. The private eval set comprises 160 tasks, split across 10 worlds. Each world contains an accounting system, as well as spreadsheets, PDFs, and other files. Every task was authored and solved by experts in accounting and bookkeeping, who also wrote grading rubrics. Across nine frontier models, Claude-Fable-5 (Max) leads with 56.4% Mean Criteria@3, ahead of Muse-Spark-1.1 (xHigh) at 52.6%. No model scores more than 2.6% Pass^8 (GPT-5.6-Sol (Max+Pro)) and the highest Pass@8 is 21.5% (Muse-Spark-1.1 (xHigh)). We experiment with increasing the token budget from

1 to

50 and observe an instance of Simpson's paradox: scores increase as the token budget increases but within a given budget-constrained harness, scores are lower on tasks where the model spends more tokens. As APEX-Accounting is a closed benchmark, leaderboard evals can be run for any frontier model on request.

Julien Benchek, Austin Bennett, Jasmin Kern +8

1Mercor · 2Ramp

LLM Evaluation Business Process Automation AI Agent Benchmarks

Jul 29, 2026cs.LG

Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performance

Long-horizon benchmarks often show that agents fail more as tasks become longer. This observation is useful for deployment, but it does not by itself explain why failure occurs. More stages create more opportunities for ordinary errors to compound; longer tasks may also contain harder individual decisions or become harder as conversation history, tool outputs, and environment changes accumulate. We use trajectory-induced degradation to mean this last possibility: earlier execution makes later work harder. When the harmful accumulation is specifically the text visible to the model, it is often called context rot. In this position paper, we argue that to claim a "long-horizon failure", benchmarks must compare actual full-task success against a baseline prediction built from short, individual stages. We call the log-ratio between this prediction and actual success the horizon residual. The comparison must use the same agent configuration and specify in advance how stages, checkpoints, information, and budgets will be chosen. The residual shows that the full rollout differs from the chosen baseline; targeted experiments are still needed to explain why.

Chao Peng, Zhiheng Lyu, Peijie Dong +2

Tencent

Long-Horizon Agent Evaluation AI Agent Benchmarks

Jul 29, 2026cs.LG

Flat Score, Amplified Failures: How the Error Budget Masks Damage in Quantized LLM Agents

Post-training quantization to 4-bit weights is widely reported to be nearly lossless. We test this claim for multi-turn, tool-calling agents, where it now matters most. On

τ^2

-bench, across two open-weight model families in dense and MoE variants and two domains (eight cells, 456 episodes each, at 16-, 8-, and 4-bit weights), quantization indeed looks free on the standard metric. No cell shows a score change that survives multiple-comparison correction, and in the cell that carries the largest process damage, equivalence testing bounds the change within

\pm

7.5 points. The process tells a different story. Quantization amplifies the failure the model already exhibits at full precision (tool-name hallucination in telecom, with the same directional trend in retail entity errors) by up to 2.5

\times

in volume (+17.6 points per task), while creating essentially no new failures. The failure set is the same at every precision (rank correlation

\geq

0.94, 0.18% novel events). The score stays flat because the benchmark's ten-error budget absorbs the extra failures. Shrinking the budget to two errors re-exposes a score gap of 17 points, and it does so only in the one cell where quantization added error volume, exactly as the masking account predicts. A targeted error-repair prompt, run for five telecom models at every precision, removes the damage exactly and only where it lives. Both diagnostics, the per-channel error rate and success under a shrinking budget, come from logs benchmarks already collect; we suggest reporting them alongside task reward.

Jiwon Jang, Kisu Yang, Heuiseok Lim +1

VAIV Company · Seoul National University · Korea University

AI Agent Reliability Benchmark Design 4-Bit Quantization AI Agent Benchmarks LLM Tool Use Post-Training Quantization+1

Jul 29, 2026cs.SE

A First Look at Coding Agents' Compliance with AI Contribution Rules in Open-Source Communities

Open source communities have been flooded with AI-generated contributions. In defense, they have written contribution rules to regulate coding agents' behavior, spanning from a total ban, mandatory disclosure, to verification gates and human sign-offs. Yet, whether coding agents read and follow those rules, and behave in open source repositories, remains unknown. To estimate real-world rule compliance of coding agents, we curate 106 issues from 49 repositories containing AI contribution rules into RepoComplianceBench. We judge the trajectory of each run against the repository's rules, measuring whether the agent refuses to contribute, discloses its assistance truthfully, clears the required verification gates, or escalates critical steps to a human. We also test if extra prompts, rule disclosure, or feedback from the compliance verifier help with the situation. Our experiments on four frontier models show that today's agents almost never proactively retrieve the contribution rules. Agents pick up disclosure and verification with reminder prompts, rule quotes, and verifier feedback; however, they never refuse to contribute in AI-banned repositories under any condition we tested. The status reveals that verification and disclosure issues are solvable with existing mechanisms, yet enforcing bans and human escalations remains an open problem.

Wenhao Yang, Runzhi He, Minghui Zhou

Peking University, Beijing, China

AI Coding Agents AI Agent Benchmarks AI Agent Governance Human Oversight of AI

Jul 29, 2026cs.AI

UrbanDS: A Graph-Guided LLM Multi-Agent System for Data-Intensive Urban Tasks

Large language model (LLM) agents have been widely applied in automating data science tasks. However, existing methods typically rely on a limited set of provided datasets, and they face challenges in data-intensive scenarios that require discovering and leveraging relevant information from large-scale and heterogeneous data repositories. Urban tasks are representative examples of such scenarios, as urban data are not only large-scale and multi-sourced, but also exhibit complex spatial, temporal, and semantic relationships. To address these challenges, we propose UrbanDS, a graph-guided LLM multi-agent system for data-intensive urban tasks. We first construct a unified dataset graph to organize reusable dataset skills and the relationships among datasets. Specifically, we develop a Data Profiling Agent that constructs a skill for each dataset. Moreover, a Relation Agent identifies relationships among datasets and integrates these relationships into the dataset graph. At runtime, a Planner Agent retrieves task-relevant datasets from the graph and generates execution plans. Multiple Execution Agents then perform data processing and analysis, while their execution progress and intermediate results are shared through a common memory. Finally, a Report Agent synthesizes the experimental logs into a report, which can be further refined based on user feedback. To systematically evaluate the capability of agents in handling data-intensive urban scenarios, we further construct UrbanDS-Bench, an urban data science benchmark covering representative data analysis and modeling tasks. Experiments on both general and urban benchmarks demonstrate that UrbanDS consistently outperforms existing data science agents on data-intensive tasks. Furthermore, UrbanDS has been deployed on the urban operations platform of Dongxihu District, Wuhan, demonstrating its effectiveness in real-world urban applications.

Zhilun Zhou, Jianghao Yu, Yuming Lin +4

Multi-Agent LLM Systems AI Agent Benchmarks LLM Agents

Jul 29, 2026cs.AI

SciDataSailor: Deep Scientific Data Exploring

Scientific datasets are commonly organized as hierarchical repositories containing heterogeneous and interdependent files, making their inspection, integration, and analysis labor-intensive and reliant on domain expertise. Although large language model (LLM) agents have advanced substantially in planning, reasoning, and tool use, existing research has largely overlooked their ability to interact with real scientific data assets through executable environments. We introduce Deep Scientific Data Exploration, an agentic task paradigm in which agents navigate repositories, interpret heterogeneous files and schemas, execute analyses, integrate cross-file evidence, and produce conclusions grounded in executed observations. To operationalize this paradigm, we present SciDataSailor, a framework for synthesizing tool-interactive trajectories by balancing broad exploration with targeted exploitation. SciDataSailor instantiates trajectory synthesis as Monte Carlo Tree Search (MCTS) with four task-specific mechanisms: difficulty-stratified exploration seeds, dual-feedback first-play urgency, hierarchical strategy-to-tool action generation, and entropy-guided branching. Using this framework, we construct SciDataSailor-SFT-2K for supervised fine-tuning and SciDataSailor-Bench for evaluation, with the latter comprising 627 meta-information summarization tasks and 586 scientific question-answering tasks across 27 datasets spanning the life, earth, and physical sciences.

Jiyong Rao, Yicheng Qiu, Chi Zhang +2

Shanghai Artificial Intelligence Laboratory · Tongji University

Scientific QA AI Agent Benchmarks LLM Agent Trajectory Synthesis Synthetic Data Generation for Language Models Data Analysis Agents

Jul 29, 2026cs.AI

Exploring Structures in Physics Problems: Can AI Agents Discover Statistical Mechanical Mappings?

An important skill in theoretical physics is to recognize when a new problem can be transformed into a known model. We study this skill as an AI-agent task: can LLM-based agents discover statistical mechanical mappings from a raw partition function to a tractable representation? To probe this question, we introduce StatMechBench-v0, a benchmark of six Ising-type problems covering transfer-matrix methods, gauge-removable disorder, and planar/Pfaffian structure. We evaluate a simple propose-verify-revise agent across multiple LLMs and problem phrasings. The results show that numerical feedback often helps agents repair code and recover correct partition functions. However, agents can also pass the numerical checks while misidentifying the underlying tractable class or understating computational complexity. This both reveals limitations in current LLM reasoning and calls for a verification stack that goes beyond numerical agreement, incorporating, for example, symbolic checks and structural invariants. Our study provides an early evaluation and design directions for AI agents aimed at structural discovery in theoretical physics.

Wanyu Zhao, Wanbing Zhao

Department of Physics and Astronomy Rice University

AI Agents for Scientific Discovery LLM Agent Evaluation AI Agent Benchmarks

Jul 28, 2026cs.AI

ClinLens: Towards Long-Horizon Coding Agents for Longitudinal Multimodal Clinical Data Science

Clinical data-science agents must transform heterogeneous longitudinal records into auditable analyses, yet existing benchmarks largely isolate medical question answering, structured-table reasoning, or generic scientific repositories. We introduce CLINLENS, a benchmark of 200 executable tasks over five linked MIMIC resources spanning structured electronic health records, notes, electrocardiograms, chest radiographs, and echocardiograms. A 4 x 5 taxonomy crosses four patient-time scopes with five analysis capabilities. Program-first reverse synthesis pairs each bounded semi-raw package with an evaluator-private reference workflow and checks required artifacts, cohort and temporal semantics, and the final answer. On a fixed 126-task suite, the strongest of 24 standardized model-scaffold configurations achieves 56.3% scope-macro STRICTPASS despite 100% EXECSUCCESS. For reference, a separately configured coding agent solves 83 of 126 tasks, while five biomedical systems adapted to GPT-4o-mini reach at most 2.9% scope-macro STRICTPASS. These results expose a substantial gap between runnable submissions and correct clinical analyses.

Yuan Zhu, Ethan B. Liu, Frank Nie +1

Shandong University, China

Long-Horizon Agent Evaluation AI Agent Benchmarks LLM Agents

Jul 28, 2026cs.AI

Messier: A High-Resolution Corpus for Cross-Benchmark Agent Evaluation

Comprehensively evaluating AI agents across interactive environments is difficult due to fragmented tasks, scaffolds, verifiers, and scoring rules. Unfortunately, existing efforts to unify these evaluations are limited in scale and domain, making costly reruns necessary and leaving available data incomparable. We introduce MESSIER, a unified corpus of 957,611 records spanning 30 benchmarks, 745 agents, 11,891 tasks, and 74,263 verifiers. MESSIER combines public evaluation results with new runs on six underrepresented professional and scientific benchmarks, standardizing their heterogeneous components into a common schema. Using this corpus, we show that frontier progress is uneven across benchmark groups, with function-calling evaluations largely saturated, programming improving fastest, and enterprise workflows remaining most challenging. Counterfactual rescoring further shows that strict all-pass scoring in multi-verifier tasks can alter agent rankings. Finally, we derive capability scores from our corpus that correlate with Epoch's Evaluation Capability Index rankings at Spearman \r{ho} = 0.84. The scores can also be estimated for subsets defined by domain, occupation, action space, or verifier type. In essence, MESSIER is a reusable resource for studying agent performance at scale, and a basis for designing better evaluations.

Stefan Krsteski, Charlotte Meyer, Guillaume Allegre +2

Andromede AI

AI Agent Evaluation Agent Evaluation AI Agent Benchmarks Dataset Aggregation

Jul 28, 2026cs.SE

RSIBench-Data: Benchmarking Data-Centric Research for Recursive Self-Improvement

Recursive self-improvement requires turning evidence of model failures into better models. Data-centric post-training research entails diagnosing capability gaps, designing and validating training-data strategies, and learning from checkpoint feedback. Can LLM agents automate this loop? Existing benchmarks entangle research decisions with optimization, serving, evaluation, and systems implementation, obscuring agents' research capability. We introduce RSIBench-Data, a controlled benchmark of LLM agents as data-centric researchers with a fixed post-training stack. Agents iteratively revise training-data strategies for a fixed target model; training and serving use Tinker-backed services, official evaluation runs through Harbor and E2B sandboxes, and budgets are fixed across agents. We evaluate four frontier agents on six benchmarks across software engineering, terminal use, scientific question answering, and mathematics. Agents demonstrate core data-centric research capabilities: in 58.33% of settings, they improve upon the first valid attempt by refining strategies from feedback. However, improvement is inconsistent. Among searches continuing after the best observed score, 78.26% end with a lower-scoring final attempt, while the rest only recover the same peak. A strong candidate may therefore appear early or midway through a run even as later revisions fail. Trajectory analysis identifies four patterns in stronger runs: accurate hypotheses, validation-grounded supervision, behavior-aligned data, and preservation of strong checkpoints. These findings suggest that current agents can make useful data-centric discoveries but cannot yet translate feedback into consistent improvements. RSIBench-Data provides a measurable, auditable testbed for the research capabilities required for recursive self-improvement. We open-source our code at https://github.com/evolvent-ai/RSIBench-Data.

Fanqing Meng, Lingxiao Du, Qiguang Chen +4

1Evolvent AI · 2National University of Singapore

LLM Agent Evaluation LLM Agent Self-Improvement AI Agent Benchmarks LLM Post-Training Recursive Self-Improvement

Jul 28, 2026cs.CL

WorkSurface-Bench: Benchmarking Enterprise Agents on Multi-Surface Knowledge Routing

Enterprise agents often need to integrate heterogeneous knowledge sources: documents for narrative facts, tables for computation, and dependency graphs for file relationships. Existing benchmarks typically evaluate retrieval or tool use without distinguishing whether an agent first selects the appropriate knowledge sources. We introduce WorkSurface-Bench, a benchmark for evaluating this capability as surface routing. It contains 1,151 atomic tasks derived from persona-scoped Workspace-Bench-Lite workspaces, spanning document, table, graph, and cross-surface questions. Its reference answers are auditable: table answers are reproduced through executed DuckDB queries, document answers are grounded in verified text spans, and graph answers are traced to source dependency annotations. We evaluate four model backbones across six controlled agent settings, yielding 27,624 protocol-error-free trajectories. Under gold-constrained tool access, agents achieve 98.7-99.8 Route F1, while Answer remains only 56.1-75.3 percent, showing that correct surface selection is necessary but insufficient for task completion. Matched interventions further show that surface hints improve Answer for three of four models, whereas removing irrelevant tools primarily improves routing and efficiency. In an independent three-annotator audit, all 200 sampled tasks pass all six quality criteria by majority vote, with 192 receiving unanimous judgments on every criterion. We release the dataset, construction pipeline, scoring code, and agent harness at https://github.com/haolpku/WorkSurface-Bench.

Hao Liang, Meiyi Qiang, Sizhe Qiu +2

Peking University · Zhongguancun Academy · University of Chinese Academy of Sciences

Computer-Use Agent Benchmarks AI Agent Benchmarks Tool-Using Agents Knowledge-Intensive QA

Jul 28, 2026cs.AI

OrchBench: Evaluating Multi-Agent Orchestration Plans in Isolation via Deterministic Simulation

Complex tasks often decompose into parallelizable yet interdependent subtasks, making orchestration critical to the performance of multi-agent systems (MAS). Existing evaluations typically rely on end-to-end execution, which conflates orchestration-plan quality with worker capabilities, tool reliability, and environmental noise. Moreover, the time and token costs of real execution grow rapidly with workflow scale, making systematic evaluation expensive. We present OrchBench, a simulation-based benchmark for evaluating multi-agent orchestration plans in isolation. Starting from real-world tasks, OrchBench constructs directed acyclic graphs (DAGs) that encode task dependencies, with controlled sizes and degrees of parallelism. Given a DAG, a per-agent context limit, and an agent budget, the evaluated planner assigns subtasks to agents and specifies cross-agent information transfers and their retention ratios. A deterministic simulator evaluates the resulting plan without invoking worker agents and returns interpretable measures of result quality, makespan, and token cost. The simulated scores produced by OrchBench correlate strongly with quality scores from Claude Code executions, achieving a Pearson correlation of

r=0.816

, while requiring only

1.3\%

of the tokens and

10.3\%

of the wall-clock time. Across diverse planners and workflow scales, we find that preserving task-critical information is more important than simply increasing the number of agents, and the benefits of parallelism diminish as coordination failures accumulate. These results establish OrchBench as an efficient and interpretable benchmark for comparing and diagnosing multi-agent orchestration plans.

Zhenzhen Ren, Jiyan He, Xinpeng Zhang +5

1Fudan University · 2Zhongguancun Academy · 3Queen Mary University of London

Multi-Agent Coordination Multi-Agent Orchestration AI Agent Benchmarks

Jul 28, 2026cs.AI

PatientAgentBench: A Benchmark Framework for Evaluating Patient-Facing Health AI Agents

Health AI is evolving from answering questions to agentic systems that converse with patients, reason about health records, and act on their behalf. Primary care guards against diagnostic errors and unsafe care; agents assisting in this domain warrant evaluation against the same risks. Current benchmarks focus on medical knowledge, assessed through isolated question-answering or clinician-facing tasks. PatientAgentBench benchmarks patient-facing agentic healthcare; it evaluates a foundation model, wrapped in an agent with a sandbox of healthcare tools, conversing with a simulated patient. Each conversation is scored by an LLM-as-a-Jury across six dimensions via over a hundred conversation-agnostic, clinician-grounded criteria. To validate alignment, licensed clinicians annotated shared conversations, yielding 79-93% adjacent agreement between jury and expert raters, on par with or exceeding clinician inter-rater agreement. We benchmarked 10 models across four families on the same 1,200 scenarios and found clinical gaps. Triage quality is the most discriminating dimension: pass rates rise from 32% for the weakest models to 88% for the strongest, with agents often acting on administrative requests without clinical screening. Clinical safety and workflow accuracy follow the same pattern: the weakest models fail often, fabricating unexecuted actions, while frontier models fail on only 1-3% of cases, from unverified tool outputs and omitted crisis resources in an emergency. More capable models narrow these gaps but do not close them; the strongest scores only 4.25 of 5 overall. These failures surface only in sustained, tool-using conversations against realistic patient records, confirming that static benchmarks are insufficient as healthcare agentic systems gain autonomy. We release the framework as a reproducible, clinician-validated evaluation standard to help the field close this gap.

Korosh Vatanparvar, Ashutosh Joshi, Maria Xenochristou +11

Amazon Health AI

AI Agent Evaluation AI Agent Safety AI Agent Benchmarks LLM Agents

Jul 28, 2026cs.AI

HANDBOOK.md: A Benchmark for Long-Context Agentic Instruction Following

Language-model agents are increasingly deployed under standing instructions: a system prompt, a policy file, or a skills document is placed in context, and the agent is trusted to let that document govern every action that follows. Existing benchmarks rarely test this deployment pattern directly; they measure whether an agent can complete a task, not whether a long, binding policy document constrains its behavior over an extended tool-use horizon. We present HANDBOOK_md, a benchmark of 65 agentic tasks modeled on how employees follow company handbooks. Each task places an agent in a self-contained company environment (a file workspace with mock email, chat, calendar, issue-tracking, and commerce services exposed over the Model Context Protocol) and instructs it to carry out routine professional work governed by an expert-written standard operating procedure of 20-124 pages. Tasks span five domains (finance, medical billing, insurance, logistics, and HR) and 10 fictional companies. To resist memorization, every task modifies one of 10 base handbooks, altering the specific rules and thresholds on which grading depends, so no two tasks share the same set of policies. Grading is fully deterministic: each task carries a rubric of programmatic criteria (824 in total) that check both that required actions occurred and that prohibited actions did not. Under strict grading, where a trial passes only if every criterion is satisfied, the strongest evaluated model passes 36.2% of trials, and most frontier models remain below 25%. Failures follow consistent patterns: agents let a plausible but unauthorized in-environment request override the standing policy, perform a required check and then act against its result, lose rule details over long horizons, and report compliance they did not achieve. We release the tasks, environments, and evaluation harness.

Liudas Panavas, Sebastian Minus, Bradley Monton +4

Surge AI*

Computer-Use Agent Benchmarks AI Agent Reliability Tool-Augmented Language Model Agents Long-Horizon Agent Evaluation AI Agent Benchmarks Instruction Following+1

Jul 27, 2026quant-ph

Agentic AI for Scientific Reasoning in Autonomous Quantum Sensing Experiments

We implement an agentic AI workflow built around a large language model (LLM) agent for autonomous experiments with nitrogen-vacancy (NV) centers in diamond. NV centers are a widely used platform for quantum sensing, and the ability to control many measurements from a computer makes NV experiments a natural setting for autonomous workflows. We make two main contributions. First, we demonstrate an autonomous NV experiment workflow that combines persistent project records, quantitative calculation and data analysis tools, and deterministic experiment control. In one autonomous experiment, the agent selected a single NV center, calibrated its resonant frequency, measured

T_2^\ast

with Ramsey measurements, and added a Carr--Purcell--Meiboom--Gill (CPMG) measurement to check a weak feature that could be related to nearby

^{13}\mathrm{C}

. Second, we introduce two offline benchmarks that evaluate the agent's reasoning separately from laboratory execution. We evaluated both benchmarks with GPT-5.4, GPT-5.5, and GPT-5.6 Sol. In the Ramsey checkpoint benchmark, greater reasoning effort generally improved recognition of a residual resonance calibration offset. By contrast, in the pulsed optically detected magnetic resonance (pODMR) data evaluation benchmark, pulse sequence information alone produced more false positive resonance judgments at higher reasoning effort. Requiring an expected signal calculation kept false positive rates low across all three models and reasoning settings. The results suggest a clear division of labor for autonomous experiments. The agent forms scientific hypotheses and uses quantitative tools to evaluate data, while deterministic code controls the hardware and enforces safety constraints.

Takuya Isogawa, Ryotaro Okabe, Nutdech Phadetsuwannukun +2

Department of Nuclear Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA · Department of Chemistry, Massachusetts Institute of Technology, Cambridge, MA 02139, USA · Department of Physics, Massachusetts Institute of Technology, Cambridge, MA 02139, USA

AI Agent Benchmarks Laboratory Automation Agentic Reasoning Autonomous Experimentation Autonomous Research Agents

Jul 27, 2026cs.AI

SIREN: Towards End-to-End Extreme-Weather Early Warning with Experience-Grounded LLM Agents

Early warning of extreme weather is essential for mitigating the societal, economic, and environmental risks posed by hazardous weather events. However, expert-centered warning workflows are costly, labor-intensive, and difficult to scale throughout the warning-to-action process. Although recent advances in Large Language Model (LLM) agents have enabled the automation of weather-related tasks, existing studies remain centered on isolated scientific tasks and overlook the chain of interdependent processes required for operational extreme-weather early warning. To bridge this gap, this study investigates automated end-to-end extreme-weather early warning through LLM agents. We first develop SIREN-Bench, a comprehensive benchmark comprising 600 question-answer instances across 19 tasks, and covering four individual warning procedures and an end-to-end warning chain. Evaluation on SIREN-Bench reveals substantial capability gaps in existing weather agent frameworks. This motivates us to develop SIREN, an experience-grounded agent framework inspired by experts' use of historical cases, which combines an agentic execution environment integrating heterogeneous weather evidence and tools with a family of agent harnesses that exploit historical cases through retrieval, skill distillation, and predictive modeling. Extensive experiments demonstrate that SIREN outperforms weather-agent baselines on both individual warning procedures and end-to-end warning chains.

Hang Ni, Weijia Zhang, Fan Liu +2

AI Agent Benchmarks LLM Agents LLM Agent Harnesses Weather Forecasting Memory-Augmented Language Model Agents

Jul 27, 2026cs.LG

GAUGE: Grading Agent-Built Financial Models Without a Golden Answer

Financial models combine public disclosures with analyst assumptions to produce forecasts and valuations. While some components can be checked mechanically, forecasts, discount rates, and target prices often admit multiple reasonable answers. Existing benchmarks nevertheless tend to grade such outputs against a single expert reference. Using independently built analyst models for the same companies, we find that across 108 directed pairs covering 65 companies, the median single-reference score is 0.33, 92.6% score below 0.70, and no same-vintage pair agrees on implied price within 10%. Point-tolerance grading can therefore penalize disagreement already present among professionals. We introduce GAUGE, a benchmark for evaluating agent-built valuation models against observed analyst practice rather than a single point answer. GAUGE uses 1,001 vendor-classified analyst workbooks and a 196-task evaluation set, with a three-layer observed-practice envelope, 56 auditable facets, eight validity gates, and deterministic structural checks. We validate the benchmark with a 55-participant known-groups study, company-grouped cross-fitting, and judge-stability audits. On the failure-aware score

φ_0

, senior analysts average 88.3, juniors 66.0, and finance students 43.2. Across 24 agents and 1,011 scored generations, the best agent scores 53.4, above the student mean but below every senior and most juniors. It passes 93% of mechanical facets and 78% of judgment facets, with a fleet-median gap of 26 points. Current agents are substantially stronger at model construction than valuation judgment. We release the methodology, a gated de-identified data tier, a controlled training split, a versioned 48-task evaluation core, and a withheld refresh pool.

Jiacheng Lu, Sinuo Wang, Wentao Zhao +12

Shanghai Jiao Tong University Shanghai, China · StepFun Shanghai, China · University of Adelaide Adelaide, Australia +5

Quantitative Finance Financial Forecasting AI Agent Evaluation AI Agent Benchmarks Automated Evaluation Finance

Jul 27, 2026cs.IR

Agent Retrieval Bench: Evaluating Repository Context Retrieval for Coding Agents

Modern coding agents are usually evaluated by whether they eventually produce a correct patch, but patch generation depends on an earlier context-acquisition stage: finding the repository files needed for the task. We introduce Agent Retrieval Bench, a file-level benchmark for this upstream retrieval problem. Samples are built from real coding-workflow signals and evaluated against frozen base-commit repositories, with relevance defined by what an agent needs next rather than direct query-file semantic similarity. The benchmark covers four positive-retrieval tasks: code2test, comment2context, trace2code, and edit2ripple; a fifth subset evaluates selective retrieval using natural evidence-backed no-gold cases and counterfactual wrong-repository controls. Agent Retrieval Bench contains 427 samples across 25 repositories: 345 positive examples, 50 natural no-gold examples, and 32 counterfactual controls. The corpus includes 308 base-commit snapshots, 392,000 files, and 7.9 million chunks. We evaluate lexical retrieval, RepoMap, open-source embeddings, selective abstention, and logged agent context selection. No single retrieval family dominates: Qwen3-Embedding-4B has the best sample-weighted MRR on positive samples, Qwen3-Embedding-8B the best Recall@20, and RepoMap the best budgeted context yield at 8K tokens, with task-level winners differing substantially. Selective thresholds calibrated with counterfactual controls do not improve selective success on natural no-gold cases, revealing a calibration gap. Logged trajectories also miss every gold file on 27-35 percent of samples. A controlled seed-intervention pilot finds that retrieval-derived initial context yields higher file F1 with less post-seed exploration than random non-gold context, while oracle gold context shows substantial remaining headroom.

Bowen Qin, Yi Xie

1National University of Singapore (NUS) · 2Peking University

Software Engineering Agents AI Agent Benchmarks Agentic Retrieval

Jul 27, 2026cs.AI

The Cost of Knowing: A Resource-Aware Protocol for Benchmarking Hallucination Beyond Static Leaderboards

On standard factuality tasks, frontier models now cluster near the top of the scale. The question is therefore shifting from how factual a system is toward how much compute that factuality costs. Static leaderboards score factuality in isolation and treat compute as free, so they cannot tell a genuinely better system apart from one that simply spends more. Consider a ranking reversal. A brute-force Best-of-4 agent posts the higher raw factuality score (H-Score 0.9169 vs 0.9103) and would top a static leaderboard, but once cost is counted it is the worse system, losing on Q-Score (0.5169 vs 0.5217) at roughly four times the tokens and latency, under a reported cost weight whose sensitivity we sweep. So the system that tops a static leaderboard can be the worse one to deploy. To make this trade-off visible, we introduce MAS-HQ (Multi-Agent System Hallucination Quest), a resource-aware evaluation protocol. It wraps any factuality detector and normalizes for cost, and it pits systems against each other rather than scoring them in isolation. The Q-Score measures factuality minus normalized cost under a competitive match. Across summarization and open-domain QA, single-agent baselines drift into resource-heavy over-optimization, while competition elicits more resource-efficient policies. These gains are small but consistent, and stable across 100 trials. The axis stays discriminative for frontier systems (Gemini-2.5-Pro, and GPT-5) whose raw factuality scores are already bunched near the ceiling. MAS-HQ provides a reproducible way to measure how much a factual answer costs.

Keyu Li, Jin Gao, Dequan Wang

Shanghai Jiao Tong University Shanghai, China

Factual Consistency Evaluation AI Agent Benchmarks LLM Hallucination Detection Automated Evaluation

Jul 27, 2026cs.AI

Success Is Not Self-Explanatory: Auditing Success Provenance in Agent Evaluation

A correct answer can conceal why an agent succeeded. Once agents change their information state during evaluation, correctness no longer distinguishes intended reasoning from answer acquisition. Outcome evidence and exposure detection do not establish whether success depended on an acquired target; we call this missing evaluation object success provenance. AcquaBench audits it through matched CLEAN, GOLD, and SHAM value substitution on four standardized surfaces with joint qid-clustered analysis. CLEAN retains benchmark-authorized information. GOLD makes the correct target available. SHAM preserves source structure and exposure opportunity but substitutes a matched incorrect value. GOLD minus CLEAN measures the total score response to correct-target availability; GOLD minus SHAM tests whether that response tracks target correctness beyond matched source exposure. In D0, GOLD exceeds SHAM by 19.1 to 25.9 percentage points, showing that success follows the correct value. In D2, GOLD still exceeds SHAM under distributed sufficiency while coloc no longer transfers as a high-score marker, with AUROC 0.376 and 0.142. Behavioral dependence can thus persist beyond this probe's intended observation unit. In model comparison, a supported 5.0-point CLEAN score gap compresses to a raw GOLD difference of -0.6 points without establishing rank inversion. Agent benchmarks should report success together with whether the evaluated information state supported it.

Jingkun Luo, Da-Tian Peng

Northwestern Polytechnical University

Data Provenance Benchmark Auditing AI Agent Auditing Agent Evaluation AI Agent Benchmarks Benchmark Validity

Jul 26, 2026cs.AI

E-Bench: Benchmarking Multi-Step Tool-Use Agents in Real-World Product Scenarios

Large Language Models (LLMs) are increasingly deployed as agents that interact with stateful environments over multiple steps: gathering hidden information, composing tool calls, and committing state changes. We refer to this capability as multi-step tool use. Existing benchmarks have advanced tool-use agent evaluation, but often focus on isolated API calls, short trajectories, or settings that are difficult to scale or control. We introduce E-Bench, a fully synthetic benchmark with 323 state-changing tasks across three product domains: Honor of Kings, QQ Music, and Tencent Meeting. E-Bench decouples environment synthesis from task synthesis: graph-guided database filling builds reusable, orphan-free product environments, while generator-solver asymmetry creates tasks with both an information gap and a tool gap, requiring agents to discover hidden data and compose multiple tool calls before changing state. Outcomes are graded deterministically by database-state diffs. Since both environments and tasks are synthetic, E-Bench is controllable at the environment level and scalable at the task level. Benchmarking 11 cutting-edge LLMs shows that multi-step tool use remains challenging: Pass^3 stays below 60% for the strongest models, and even with code execution in the E-Bench-Code extension, reliability (Pass^3) remains below 70%.

Weihuang Zheng, Tianyuan Zou, Eileen Ye +5

Hunyuan Team, Tencent · Institute for AI Industry Research, Tsinghua University · School of Computer Science and Engineering, Southeast University

Computer-Use Agent Benchmarks Tool-Use Evaluation Tool-Augmented Language Model Agents AI Agent Benchmarks Synthetic Benchmark Generation Tool Use

Jul 26, 2026cs.CR

DualityCert: Verifier-Gated Language-Model Repair of Broken Duality Claims in Quantum Field Theory

We present DualityCert, a symbolic verifier for candidate Seiberg-duality claims in four-dimensional N=1 quiver gauge theories. The verifier evaluates 't Hooft anomaly matching, superpotential R-charge consistency, central-charge matching, and a bounded chiral-ring proxy. A claim that passes receives a consistency certificate, which states that no tested inconsistency was found, not that the duality is proven. We use the verifier as a repair environment for language-model agents, which receive a deliberately broken claim and must edit it until it certifies. On a preregistered benchmark of 145 broken claims, with the analysis fixed before the first confirmatory model call, verifier-gated retry improves final repair success over a single attempt by +8.3 percentage points (pp) on deepseek-chat and +7.1 pp on qwen-plus (Holm-adjusted p<0.002). Under an equal budget of eleven attempts, the stop-first strategy portfolio underperforms independent verifier-filtered resampling by 10.3 percentage points on deepseek-chat but outperforms it by 14.7 points on qwen-plus, reversing the ordering of the two tested verifier-exploitation policies across the two confirmatory models. On qwen-plus, category-level verifier feedback is worth +8.7 pp over content-free retry, and interpretable obligation identities alone are worth +6.4 pp over structurally identical masked feedback. Neither effect is detected on deepseek-chat. Separately, a preregistered MiniMax-M2.5 extension again finds an iteration gain and independent verifier-filtered resampling outperforming the strategy portfolio. Which policy is better thus differs between the two models, while every winning policy uses the same cheap certificate. The verifier, benchmark, protocol, and all per-attempt records are released.

Xingyang Yu

Department of Physics Virginia Tech Blacksburg, VA 24061, USA

LLM Self-Correction Claim Verification AI Agent Benchmarks LLM Agent Reliability

Jul 26, 2026cs.AI

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis

Deep search is becoming a core capability of modern agent systems, yet it is typically evaluated solely based on end-to-end answer accuracy. This coupled evaluation paradigm entangles retrieval quality, long-context comprehension, evidence verification, and tool-use decisions, making it difficult to determine whether a model truly knows when and how to delegate information seeking to search. To this end: (1) We formalize this meta-capability as Delegation Intelligence in deep search and decompose it into complementary dimensions-Search Decision-Making (recognizing information insufficiency and deciding whether, when, and how to search) and Information Synthesis and Verification (aggregating evidence from multiple sources, judging source reliability, and synthesizing information under noisy, potentially adversarial conditions). (2) To enable disentangled and reproducible measurement, we develop a controllable synthesis pipeline built on document-grounded reverse engineering. This yields a general recipe for constructing controlled deep-search evaluations rather than a single fixed dataset. (3) As a concrete instantiation, we construct DelegSearchBench, together with a disentangled evaluation protocol that isolates each capability dimension by varying document composition and tool access. (4) Across representative models, we demonstrate that deep-search competence cannot be adequately characterized by final-answer accuracy alone...

Xinhao Yao, Yuanzhuo Liu, Changhao Wang +6

Tencent · Renmin University of China · UCAS +1

Deep Research Agents LLM Agent Evaluation AI Agent Benchmarks

Jul 25, 2026cs.LG

AllocBench: Measuring Online Tool Allocation Capability in LLM Agents

Creating a reusable tool is an investment: an agent pays a fixed cost now in exchange for the potential of future reuse. Therefore, a user should prefer an agent that creates a small number of highly reusable tools, rather than many one-offs. We introduce a paired benchmark that tests whether LLM agents exhibit conscious allocation behavior under a fixed budget in two contexts: an abstract text-based formulation and a code-construction task. We find that every frontier model we test---Claude Haiku, Claude Opus, GPT-5.4-mini, and GPT-5.6 Sol---acts near-optimally in the abstract framing but fails to transfer this ability to script-writing. Through further experiments, we identify the particular failure modes for each model. Notably, the first three models fail even when the scripts are not evaluated, while GPT-5.6 Sol stays selective under that weaker manipulation and collapses only at full construction. Furthermore, an open-source Qwen model policy-trained for abstract allocation generalizes this ability across held-out lexical variations, but sees no improvement at script allocation. Together, these results establish online tool allocation as a significant capability boundary, even for modern frontier models.

Daniel Wang, Andrew Xu

Yale University

Tool-Augmented Language Model Agents AI Coding Agents LLM Agent Evaluation AI Agent Benchmarks Tool-Using Agents

Jul 25, 2026cs.AI

AgentOmnia: Scaling Agentic Models for Full-Scenario Applications

Large language model agents have advanced rapidly, yet progress remains fragmented across domains, capabilities, task difficulty, and interaction settings. We frame this as full-scenario agentic scaling and present AgentOmnia, a framework coordinating task-space definition, data synthesis, post-training, evaluation, and improvement across To-Consumer (ToC), To-Business (ToB), and To-Employee (ToE) applications. An extensible Domain x Capability x Atomic Difficulty taxonomy aligns these stages and enables fine-grained diagnosis with OmniaBench. AgentOmnia combines bidirectional environment-task synthesis with tool-dependency, program-structured, and solver-based pipelines, constructing 5,018 stateful environments with 255,375 tools and 52,361 tasks. Programs, solvers, and verifiers provide correctness signals, while supervised fine-tuning, online agentic reinforcement learning, and a rollback curriculum support post-training. Evaluation failures translate into Product Requirement Documents (PRDs) for targeted self-evolution. Starting from Qwen3-30B-A3B-Thinking-2507, AgentOmnia raises the pass rate on the OmniaBench challenging subset from 9.16% to 37.11% and the macro-average across OmniaBench,

τ^2

-Bench, DeepPlanning, and VitaBench from 22.86% to 41.69%. Under a unified protocol,it leads the evaluated agentic post-trained baselines on OmniaBench and retains the highest four-benchmark macro-average. It also surpasses Qwen3-235B-A22B-Thinking-2507 on all four benchmarks and exceeds Qwen3.5-35B-A3B on the macro-average. Gains span three application splits, ten capability dimensions, eight atomic-difficulty factors, and 76 of 90 level-1 domains, indicating broad rather than category-specific improvement. A one-round study provides initial evidence for PRD-guided self-evolution, motivating validation at larger scales and in industrial settings.

Hao Jiang, Gangtao Xin, Yingdi Huang +35

Huawei Cloud Post-Training Team

Tool-Augmented Language Model Agents Agentic RL LLM Agent Self-Improvement AI Agent Benchmarks LLM Agent Training