LLM Agent Evaluation

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

115 papers in the last four weeks, up 140% on the four weeks before. 1.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 793

May 18, 2026cs.CL

Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?

Deep research agents increasingly automate complex information-seeking tasks, producing evidence-grounded reports via multi-step reasoning, tool use, and synthesis. Their growing role demands scalable, reliable evaluation, positioning LLM-as-judge as a supervision paradigm for assessing factual accuracy, evidence use, and reasoning quality. Yet the reliability of these judges for deep research agents remains poorly understood, posing a critical meta-evaluation problem: before deploying LLM judges to supervise research agents, we must first evaluate the judges themselves. Existing meta-evaluations fall short in two ways: (1) reliance on coarse, subjective human-preference agreement; (2) focus on instruction-following or verifiable tasks, leaving open-ended agent executions unexplored. To address these gaps, we introduce REFLECT (REliable Fine-grained LLM judge Evaluation via Controlled inTervention), a meta-evaluation benchmark targeting fine-grained failure detection in agentic environments. REFLECT defines a detailed taxonomy of process- and outcome-level failure modes, instantiated by performing controlled and localized interventions on quality-screened agent execution traces. This yields verifiable, comprehensive, and fine-grained instances for validating the judge models. Our experiments show that current LLM judges remain unreliable: even the best-performing models achieve overall accuracies below 55% across reasoning, tool-use, and report-quality failures, with especially poor performance on evidence verification. Together, our taxonomy and findings expose systematic judge limitations, reveal tradeoffs in cost and reliability, and offer actionable guidance for building more reliable evaluation pipelines for deep research agents.

Leyao Wang, Yanan He, Peng Chen +5

Yale University · IBM Research

AI Agent Reliability LLM-as-a-Judge LLM Agent Evaluation AI Agent Benchmarks Autonomous Research Agents

May 18, 2026cs.AI

How Far Are We From True Auto-Research?

Recent auto-research systems can produce complete papers, but feasibility is not the same as quality, and the field still lacks a systematic study of how good agent-generated papers actually are. We introduce ResearchArena, a minimal scaffold that lets off-the-shelf agents (Claude Code using Opus 4.6, Codex using GPT-5.4, and Kimi Code using K2.5) carry out the full research loop themselves (ideation, experimentation, paper writing, self-refinement) under only lightweight guidance. Across 13 computer science seeds and 3 trials per agent-domain pair, ResearchArena yields 117 agent-generated papers, each evaluated under three complementary lenses: a manuscript-only reviewer (SAR), an artifact-aware peer review (PR) in which agents inspect the workspace alongside the manuscript, and an human conducted meta-review. Under SAR alone the picture is optimistic: Claude Code obtains the highest score, outperforms Analemma's FARS, and matches the weighted-average human ICLR 2025 submission, suggesting that minimally scaffolded agents can produce papers that look competitive on manuscript-only review. Manual inspection, however, reveals this picture is overstated: SAR scores are poorly aligned with its actual acceptance decisions and reward plausible framing without verifying experimental substance. Under artifact-aware PR scores drop sharply, and manual auditing identifies experimental rigor as the major bottleneck, decomposing into three failure modes (fabricated results, underpowered experiments, and plan/execution mismatch) that are highly agent-dependent: Codex 5%/8% paper-vs-artifact mismatch / fabricated references versus Kimi Code 77%/72%, a

\sim

15

\times

spread that tracks distinct research personas the agents develop. None of the 117 agent-generated papers reaches the acceptance bar of a top-tier venue. This suggests that we are still gapped from the true auto-research.

Zhengxin Zhang, Ning Wang, Sainyam Galhotra +1

Cornell University

LLM Agent Evaluation AI Agent Benchmarks Autonomous Research Agents Generative AI Evaluation

May 18, 2026cs.CL

Agent Meltdowns: The Road to Hell Is Paved with Helpful Agents

Agents operating with computer and Web use inevitably encounter errors: inaccessible webpages, missing files, local and remote misconfigurations, etc. These errors do not thwart agents based on state-of-the-art models. They helpfully continue to look for ways to complete their tasks. We introduce, characterize, and measure a new type of agent failure we call \emph{accidental meltdown}: unsafe or harmful behavior in response to a benign environmental error, in the absence of any adversarial inputs. Because meltdowns are not captured by the existing reliability or safety benchmarks, we develop a taxonomy of meltdown behaviors. We then implement an agent-agnostic infrastructure for injecting simulated local and remote errors into the rollout environment and use it to systematically evaluate agent systems powered by GPT, Grok, and Gemini. Our evaluation demonstrates that meltdowns (e.g., conducting unauthorized reconnaissance or subverting access control) of varying severity and success occur in 64.7% of agent rollouts that encounter simulated errors, spanning all combinations of agent system, backing model, and error type. In over half of these meltdowns, unsafe behaviors are not reported to the user. Comparing behaviors of the same agents with and without errors, we find that exploration in response to errors is correlated with unsafe and harmful behavior.

Rishi Jha, Harold Triedman, Arkaprabha Bhattacharya +1

Department of Computer Science Cornell University

Agent Failure Analysis AI Agent Reliability LLM Agent Evaluation AI Agent Safety Tool-Using Agents

May 18, 2026cs.AI

POLAR-Bench: A Diagnostic Benchmark for Privacy-Utility Trade-offs in LLM Agents

LLM agents increasingly have access to private user data and act on the user's behalf when interacting with third-party systems. The user defines what may and must not be shared, and the agent must robustly follow that intent even when third-party systems behave adversarially. We introduce POLAR-Bench (Policy-aware adversarial Benchmark), in which a trusted model with a privacy policy and a task converses with a third-party model that adversarially probes for both task-relevant and protected attributes. Across 10 domains and 7,852 samples, we score privacy and utility by deterministic set-membership and vary privacy policy dimension and attack strategy along two orthogonal axes, producing a 5 times 5 diagnostic surface per model. Our results reveal a sharp split: current frontier models withhold over 99% of protected attributes, while smaller open-weight models in the 1--30B range, the class users most commonly run as their own trusted agent on-device or via private inference, score notably worse, with the weakest leaking over half. POLAR-Bench thus localizes where each model's intent-following breaks down, providing a foothold for privacy alignment where it matters most.

Qiaoyuan Zheng, Yiqu Yang, Qi Gao +1

ETH Zurich Zurich, Switzerland · ETH AI Center Zurich, Switzerland

LLM Agent Evaluation LLM Agent Security AI Agent Security Benchmarks LLM Agent Safety

May 18, 2026cs.AI

SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents

As LLM agents are increasingly built around reusable skills, a central challenge is no longer only whether agents can use provided skills, but whether they can generate correct, reusable, and executable skills from repositories and documents. Existing benchmarks primarily evaluate the efficacy of given skills or the ability of agents to solve downstream tasks from raw context, but they do not isolate skill generation itself as the object of study. We introduce SkillGenBench, a benchmark for evaluating skill generation pipelines under a unified and controlled protocol. In SkillGenBench, a generator receives raw corpora and produces standardized skill artifacts, which are then executed under fixed harnesses and assessed with unified evaluation procedures. The benchmark covers two generation regimes: task-conditioned generation, where a task-specific skill is synthesized after the task is revealed, and task-agnostic generation, where a reusable skill library must be distilled before downstream tasks are known. It also spans two complementary procedural sources: repository-grounded instances, where procedures are distributed across code, configuration, and scripts, and document-grounded instances, where procedures and constraints must be distilled from long-form text. We provide standardized task specifications, pinned environments, and evaluation protocols centered on deterministic execution-based checks, supplemented by auxiliary signals for diagnosis. Experiments across a range of skill-generation methods and backbones show substantial performance variation, highlight the difficulty of reusable skill distillation, and reveal distinct failure modes in skill generation from software repositories versus long-form documents. SkillGenBench establishes a reproducible testbed for studying skill generation as an independent research problem in agent systems.

Yifan Zhou, Zhentao Zhang, Ziming Cheng +8

1SJTU · 2XJTU · 3NUS +6

LLM Agent Evaluation LLM Agent Skill Learning AI Agent Benchmarks

May 18, 2026cs.CL

EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective

Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution. However, memory is also essential for agents, as it enables them to store, update, and retrieve information over time. This ability remains under-evaluated, largely because existing benchmarks do not provide a systematic way to assess memory mechanisms. In this paper, we study agent memory from a self-evolving perspective and introduce EvoMemBench, a unified benchmark organized along two axes: memory scope (in-episode vs. cross-episode) and memory content (knowledge-oriented vs. execution-oriented). We compare 15 representative memory methods with strong long-context baselines under a standardized protocol. Results show that current memory systems are still far from a general solution: long-context baselines remain highly competitive, memory helps most when the current context is insufficient or tasks are difficult, and no single memory form works consistently across all settings. Retrieval-based methods remain strong for knowledge-intensive settings, whereas procedural and long-term memory methods are more effective for execution-oriented tasks when their stored experience matches the task structure. We hope EvoMemBench facilitates future research on more effective memory systems for LLM-based agents. Our code is available at https://github.com/DSAIL-Memory/EvoMemBench.

Yuyao Wang, Zhongjian Zhang, Mo Chi +7

Hong Kong University of Science and Technology (Guangzhou) · Beijing University of Posts and Telecommunications · Beijing Institute of Technology +1

LLM Agent Memory LLM Agent Evaluation AI Agent Benchmarks Memory Agent Benchmarks Agent Benchmarks

May 18, 2026cs.SE

Same Signal, Different Semantics: A Cross-Framework Behavioral Analysis of Software Engineering Agents

Behavioral studies of LLM-based software engineering agents extract operational rules about which trajectory shapes correlate with higher resolution rates: that a test step follows a code modification, that error cascades are short, or that trajectories are compact. Each rule is typically derived from a single framework, and whether it transfers, in sign as well as magnitude, to structurally different agent designs has not been directly tested. We address this at ecosystem scale: 64,380 SWE-bench runs from 126 agent configurations spanning 43 frameworks, where each configuration pairs an LLM with a framework (e.g., SWE-Agent, OpenHands) that supplies its tools and workflow. We separate framework effects from LLM effects by holding each layer fixed in turn, then measure one behavior-outcome effect per configuration and examine how those effects agree or disagree. Swapping the framework while the LLM is held fixed produces large behavioral differences in every action feature. On most signals, configurations disagree not merely in magnitude but in direction. Error rate is the cleanest case: 47 configurations resolve more issues when their error rate is lower, while 48 resolve more when it is higher. Five other continuous features and three of seven binary patterns from prior SE literature show similar directional disagreement. Framework identity accounts for more of this variation than LLM family: for mean turns, framework explains 64% of the between-configuration variance against the LLM's 10%. The implication is that the same observable behavioral signal can carry opposite meaning for different agent configurations. Behavioral findings from any single framework therefore warrant cross-configuration validation before being claimed as general.

Wei Ma, Zhi Chen, Jingxu Gu +3

Blekinge Tekniska Högskola Karlskrona, Sweden · Singapore Management University Singapore, Singapore · Nanjing University Nanjing, China +1

Software Engineering Agents LLM Agent Evaluation

May 18, 2026cs.SE

ProcCtrlBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Agents

Existing benchmarks for LLM coding agents primarily evaluate final outcomes. While useful for measuring overall capability, these metrics provide limited visibility and often miss defects that arise during execution. We present ProcCtrlBench, a benchmark for execution-process evaluation in LLM coding agents. ProcCtrlBench organizes recurrent execution defects into a reusable ontology covering 11 defect types in 4 categories, and evaluates agent trajectories through standardized process evidence rather than final outcomes alone. To support comparison across heterogeneous agents, ProcCtrlBench standardizes raw logs into a unified trajectory representation and reports calibrated scorecards over process-level findings. In addition, ProcCtrlBench uses control preservation as a way to quantify execution-process quality, capturing whether execution remains interpretable, interruptible, correctable, reversible, and able to hand back authority when needed. We evaluate ProcCtrlBench on 200 cases sampled from three benchmarks: AndroidBench, TerminalBench, and SWE-bench-Verified. Results show that ProcCtrlBench can be instantiated with useful reliability, provides more stable semantics than direct thresholding, and reveals meaningful differences in execution quality that are often overlooked by conventional outcome-based evaluation.

Jiawei He, Jie Jia, Chenbo Liu +4

Amap, Alibaba Group

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

May 18, 2026cs.CL

PROTEA: Offline Evaluation and Iterative Refinement for Multi-Agent LLM Workflows

Multi-agent LLM workflows -- systems composed of multiple role-specific LLM calls -- often outperform single-prompt baselines, but they remain difficult to debug and refine. Failures can originate from subtle errors in intermediate outputs that propagate to downstream nodes, requiring developers to inspect long traces and infer which agent to modify. We present PROTEA, a unified interface for offline, test-driven improvement of multi-agent workflows. PROTEA executes a workflow, scores intermediate node outputs with configurable rubrics, and overlays per-node states and rationales on the workflow graph to localize likely bottlenecks. To support complex systems where final-answer references are the primary supervision, PROTEA performs backward node evaluation: it generates candidate node-level expectations from final-answer references and graph context, then compares them with observed node outputs. For selected nodes, PROTEA presents targeted prompt revisions as editable before/after comparisons, then automatically reruns and re-evaluates the workflow to show output changes and score trajectories within the same interface. In two production-adjacent workflows, PROTEA improved document-inspection accuracy from 64.3% to 83.9% and recommendation Hit@5 from 0.30 to 0.38. In a formative study with six experienced LLM developers, participants valued graph-level localization, per-node rationales, and editable before/after prompt revisions.

Kazuki Kawamura, Satoshi Waki, Kei Tateno

Sony Group Corporation

Multi-Agent LLM Systems LLM Agent Evaluation LLM Agent Workflow Optimization Prompt Optimization

May 18, 2026cs.AI

Evaluating Cognitive Age Alignment in Interactive AI Agents

While agentic AI and its core multimodal large language models (MLLMs) have demonstrated remarkable promise in language and visual reasoning across domains ranging from daily life to advanced scientific research, a profound gap remains between artificial and human intelligence. Despite the integration of powerful tools and advanced MLLMs, state-of-the-art AI agents frequently fail at foundational, seemingly simple tasks that a child can resolve with ease. Inspired by the Wechsler Intelligence Scale for Children (WISC), we introduce ChildAgentEval, the first psychometrically grounded interactive benchmark for evaluating cognitive age alignment in MLLM-based agents. ChildAgentEval systematically compares the reasoning performance of various MLLM-based interactive agents against age-specific human developmental stages, exposing where current agentic AI systems can and cannot simulate age-specific cognitive behavior.

Yifan Shen, Jiawen Zhang, Jian Xu +4

1PediaMed AI · University of Illinois Urbana-Champaign · 4Peking University +2

LLM Agent Evaluation AI Agent Benchmarks Multimodal Agents

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 18, 2026cs.CL

SocialMemBench: Are AI Memory Systems Ready for Social Group Settings?

Memory systems for AI assistants were built for single-user dialogue and fail characteristically when applied to multi-party social group settings. This gap matters for the social assistants being built today: group-acting agents embedded in chat platforms, and proactive personal-assistant agents whose holistic model of a user must include their social context. Existing memory benchmarks evaluate dyadic or workplace dialogue; none targets multi-party social groups, where memory must anchor facts in shared history rather than professional roles, separate group norms from individual exceptions, and correctly attribute even after member departure. We introduce SocialMemBench, a benchmark of human-verified synthetic social group networks across five archetypes (close friends, family, recreational, interest community, acquaintance network) and three group-size tiers (4-30 members), with 430 personas and 7,355 conversation turns, yielding 1,031 QA pairs across nine question categories. Each category isolates an architectural capability, and the five failure modes (single-stream conflation, temporal-state overwrite, entity merging at scale, missing cross-persona knowledge, norm-individual conflation) are testable hypotheses; our two research probes Subject-Mem and SMG provide evidence on two, three remain open. A full-context Gemini 2.5 Flash reference reaches only 0.721 against a blind-critic reasoning-model mean of 0.98 on small networks, indicating the benchmark is genuinely difficult even with complete access to the conversation. Across all 43 networks, the four open-source memory frameworks evaluated (Mem0, LangMem, Graphiti, Cognee) cluster in the 0.12-0.18 question-weighted range with overlapping 95% CIs, well below an uncompressed retrieval reference of 0.345 and a matched-answerer full-context reference of 0.369 (GPT-4o-mini). Current memory systems show a measurable gap.

Olukunle Owolabi

Independent Researcher

Agent Memory Conversational Memory LLM Agent Evaluation AI Agent Benchmarks Memory Agent Benchmarks

May 17, 2026cs.AI

Evaluating Deep Research Agents on Expert Consulting Work: A Benchmark with Verifiers, Rubrics, and Cognitive Traps

Frontier deep research agents (DRAs) are being deployed in enterprise workflows faster than they are being evaluated. Existing benchmarks measure factual recall, single-hop QA, or generic agentic skill, and miss the multi-document, decision-grade deliverables DRAs are asked to produce. We introduce a benchmark of 70 SME-authored management consulting prompts, each embedding cognitive traps that penalize surface-pattern reasoning. Three frontier agents, namely Claude Opus~~4.6, OpenAI o3-deep-research and Gemini~~3.1Pro deep-research, are scored on two complementary layers: deterministic binary verifiers (mean 14.9 per task) and a five-criterion 0--3 SME rubric (Data Integrity, Analytical Rigor, Relevance & Focus, Execution Precision, Format & Deliverability), combined into a Verifier-Rubric Score (VRS, 0--100). Acceptance under a joint threshold (rubric mean $\geq 2.5$ and verifier pass rate $\geq 80\%$ ) is uniformly low: o3 15.7%, Claude 12.9%, Gemini 12.9%. Pairwise differences are statistically indistinguishable. On the continuous VRS, o3 leads (61.4[CI: 55.2,,67.5]), followed by Gemini (52.6) and Claude (38.5); the o3--Claude gap (

Δ{=}22.9

,

p{<}0.001

) survives Bonferroni correction. No agent averages above the rubric's ``adequate'' threshold of 2.0; no agent's mean verifier pass rate reaches the 80% acceptance floor. Each agent fails distinctively: Claude leads on data fabrication and file-access failures; o3 propagates cascading computation errors; Gemini oscillates between the highest perfect-verifier rate and the most catastrophic collapses. The benchmark, evaluation code, and full prompt corpus are publicly released.

Tanmay Asthana, Aman Saksena, Divyansh Sahu

Deccan AI Research

AI Agent Reliability Deep Research Agents LLM Agent Evaluation LLM Agent Verification AI Agent Benchmarks Agentic Reasoning+1

May 17, 2026cs.CR

Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback

Tool-using LLM agents increasingly rely on external tools to make consequential decisions, yet most existing agent-security benchmarks and defenses implicitly assume that tool feedback is trustworthy once a tool has been selected. We study a different failure mode, cognitive poisoning, in which a malicious tool behaves plausibly during exploration, accumulates trust through benign-looking feedback, and becomes harmful only when hidden state conditions align with the final executable action. To study this setting, we construct TRUST-Bench, a task-conditioned benchmark of 1,970 hidden-trigger tool-compromise episodes with matched safe controls, introduce an asymmetric penalty metric, GuardedJoint, to better reflect real deployment risk, and present VISTA-Guard, a backbone-agnostic framework for final-action risk scoring. The core idea is to abstract multi-step tool interaction into structured environment variables that encode trust-formation dynamics and then score the risk of the final executable action from this trajectory-conditioned representation. Experiments show that prompt-centric heuristics, scalarized features, and zero-shot judges fail in this regime, whereas trajectory-aware final-action scoring yields strong in-domain discrimination and remains effective under balanced out-of-distribution transfer. Under GuardedJoint, VISTA-Guard reaches

84.2

in-domain and

56.9

on balanced out-of-distribution evaluation, while methods that optimize only one side of the safety--utility tradeoff collapse to zero. These findings support a broader view of agent security in black-box tool ecosystems: the decisive defense target is not local prompt text or tool descriptors alone, but the way trust is formed across the interaction trajectory and committed through the final action.

Lecheng Yan, Ruizhe Li, Xicheng Han +5

Southern University of Science and Technology · University of Science and Technology of China · Zhejiang University +2

AI Agent Reliability LLM Agent Evaluation LLM Agent Security AI Agent Security Benchmarks AI Agent Safety Benchmarks

May 17, 2026cs.SE

DiagEval: Trajectory-Conditioned Diagnosis for Reliable Software Evaluation with GUI Agents

Evaluating LLM-generated interactive software requires execution in addition to static analysis. The key difficulty is that correctness is a graph-level reachable property over latent UI state-transition graphs, whereas a GUI evaluator observes only a single execution trajectory. A failed rollout therefore rules out only one realized path, leaving failure attribution ambiguous between evaluator-side execution error and genuine software defect. We present DiagEval, a trajectory-conditioned diagnostic evaluation protocol for post-failure GUI-agent evaluation of interactive software. Rather than blindly retrying from scratch, DiagEval reuses the failed trajectory to choose targeted diagnostic probes and aggregates their outcomes into an internal attribution signal. The latent-graph view motivates the diagnostic problem; DiagEval does not reconstruct the graph or estimate calibrated posterior probabilities. We evaluate DiagEval on WebDevJudge-Unit and RealDevBench across multiple GUI-agent evaluators and LLM backbones. On false-negative cases, DiagEval recovers 45.6-62.1% of failures that were initially misattributed to software defects, outperforming retry-based baselines with 34.4-160.6% relative gains. On the full evaluation sets, this recovery improves accuracy from 69.9% to 78.3% on WebDevJudge-Unit and from 65.0% to 81.6% on RealDevBench. These results suggest that reliable GUI-agent evaluation requires not only stronger execution, but also active failure diagnosis to disambiguate evaluator-side errors from genuine software defects. Our code is available at https://github.com/scutGit/DiagEval.

Sirui Hong, Zhijie Liu, Tengfei Li +3

1DeepWisdom · 2Independent Researcher · 3The Hong Kong University of Science and Technology (Guangzhou)

Agent Failure Analysis GUI Agents LLM Agent Evaluation

May 17, 2026cs.AI

MetaCogAgent: A Metacognitive Multi-Agent LLM Framework with Self-Aware Task Delegation

Multi-agent large language model (LLM) systems have shown promise for solving complex tasks through agent collaboration. However, existing frameworks assign tasks based on predefined roles without considering whether an agent can accurately assess its own competence boundaries, leading to overconfident execution on tasks beyond its expertise. Inspired by metacognition theory from cognitive science, we propose MetaCogAgent, a multi-agent LLM framework where each agent is equipped with a Metacognitive Self-Assessment Unit that evaluates task-capability alignment before execution. The framework introduces three contributions: (1) a self-assessment mechanism that estimates per-task confidence by combining verbalized uncertainty with historical capability profiles; (2) an adaptive delegation protocol that routes low-confidence tasks to better-suited agents through cross-agent evaluation; and (3) a capability boundary learning module that iteratively refines each agent's competence model via cybernetic feedback. Experiments on our constructed MetaCog-Eval benchmark (700 tasks across 5 cognitive dimensions) demonstrate that MetaCogAgent achieves 82.4% task accuracy -- 8.7% above the best routing baseline -- while using 5% fewer API calls than AutoGen and 34% fewer than ensemble voting. Ablation studies confirm that each metacognitive component contributes to overall system performance.

Chenyu Wang, Yang Shu

School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China · Zhejiang University, Hangzhou, China

LLM Agent Orchestration LLM Agent Evaluation LLM Agents Multi-Agent LLMs

May 17, 2026cs.SE

ContractBench: Can LLM Agents Preserve Observation Contracts?

Tool-augmented LLM agents call APIs whose intermediate outputs, such as presigned URLs, session tokens, and OAuth state parameters, are observation contracts: artifacts whose later use is constrained by the external system that produced them. We show that observation contract compliance (preserving the temporal validity and byte-level integrity) is an emergent, regression-prone capability: it is neither guaranteed by general tool-use ability nor consistently improved by larger or newer models. To measure this, we introduce ContractBench, a benchmark of 33 dual-axis tasks that probe two orthogonal failure modes no existing benchmark evaluates: validity failures (using an artifact after expiry) and integrity failures (corrupting an artifact's bytes through the observation-to-action pipeline). Our evaluation is deterministic and programmatic, with a virtual clock controlling time and SHA-256 hashes verifying byte integrity. We assign each outcome a failure label drawn from real-world API specifications. We evaluate 38 models and report four findings: (i) no evaluated model clears 80%, with Claude-Opus-4.6 leading at 77.8%, revealing that current frontier models still fail to comply with observation contracts; (ii) a sharp within-family capability cliff in Qwen 3.5 between 4B (0%) and 9B (56.6%), smoothing to 70.7% at 397B-A17B: what emerges across the cliff is mid-trajectory restraint, not tool-call competence; (iii) non-monotonic scaling across the GPT-5 family: agentic post-training can erode compliance through sycophancy-driven regression; (iv) our failure taxonomy works as an actionable in-context reward signal, yielding +7.1 pp on 42 paired GPT-5.1 failures.

Jicheng Wang, Yifeng He, Zili Wang +3

University of California, Davis · University of Southern California · University of Hong Kong

AI Agent Reliability LLM Agent Evaluation AI Agent Benchmarks LLM Agent Reliability

May 16, 2026cs.LG

Representation Signatures and Risk-Feedback Alignment in LLM Trading Agents

We study behavioral alignment and representation dynamics of large language model (LLM) agents in financial decision environments. TradeArena, an auditable trading-agent testbed with risk reports, execution simulation, memory, and replayable trajectories, lets us analyze how rationales, positions, and interventions evolve under market stress. Code and data artifacts are available through the TradeArena repository. We find pre-failure signatures: planning embeddings drift from normal centroids, fused plan-risk representations separate normal from pre-drawdown states, and local manifolds exhibit effective-rank contraction. Across 80 rolling failure anchors and eight LLM trajectories, this pattern persists across hash, LSA, Transformer, and white-box hidden-state probes. Stress tests with CoT-free target weights, lexical controls, OHLCV noise, and false audits show that rationale-level contraction can vanish without rationales, while intent-space and fused signatures remain informative. Structured risk feedback can act as an external alignment signal without fine-tuning, but not as a universal performance enhancer: true audit feedback improves calibration for some models, returns for others, and exposes cases where placebo or hidden feedback has higher short-horizon return but weaker alignment diagnostics. A 51-stock intraday experiment reveals a correlation blind spot: LLM rationales justify exposure to coupled assets that the risk layer clips. Finally, a financial-audit task suite shifts comparison from ``which model trades best'' to whether models can audit trajectories, respect execution boundaries, reproduce artifacts, and avoid claim overreach. These results support a research claim, not a profitability claim: auditable risk feedback and representation trajectories reveal when LLM financial reasoning is aligning, drifting, or failing.

Weicheng Xue

Virginia Tech

LLM Alignment LLM Auditing LLM Interpretability LLM Agent Evaluation AI Agent Benchmarks LLM Agents+1

May 16, 2026cs.AI

PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Models

Large language models (LLMs) increasingly serve as interactive social agents, yet their ability to maintain coherent and authentic persona-level role-playing remains limited, particularly in realistic social scenarios. Existing research predominantly focuses on character-level settings and relies on static evaluation formats, failing to capture the complexity of everyday social interactions. In this work, we present PersonaArena, a dynamic simulation framework for evaluating and improving persona-level role-playing in LLMs. PersonaArena leverages a large, filtered corpus of user-generated social content to construct a nuanced persona bank, and elicits multi-turn, context-rich interactions within simulated social environments. Our framework features a multi-agent debating judge for holistic and unbiased assessment. Through extensive experiments, we demonstrate that PersonaArena enables rigorous evaluation and enhancement of LLMs' role-playing capabilities, advancing the development of more authentic and socially adept AI agents.

Wenlong Shi, Jianxun Lian, Mingqi Wu +5

College of Computer Science and Software Engineering, Shenzhen University, China · Microsoft Research Asia · Microsoft Gaming +2

Large Language Model-Based Role-Play Simulation Personality Modeling in Language Models Human Behavior Simulation LLM Agent Evaluation AI Agent Benchmarks Large Language Model-Based Social Simulation

May 16, 2026cs.CE

The Alpha Illusion: Reported Alpha from LLM Trading Agents Should Not Be Treated as Deployment Evidence

End-to-end LLM trading agents have moved quickly from research curiosity to a small ecosystem of named systems, including FinCon, FinMem, TradingAgents, FinAgent, QuantAgent, and FLAG-Trader. Several of these report headline Sharpe ratios that would be material if read at face value on a deployment desk, and associated benchmarks such as FinBen report trading-task Sharpe statistics in the same range. The gap between architecture research and deployment claim has been crossed too freely on both sides of the academia--industry divide. We take a position on that gap: reported alpha from end-to-end LLM trading agents should not be treated as deployment evidence. Before such returns can support claims of deployable trading capability, they must survive structural validity tests for temporal integrity, real-world frictions, counterfactual robustness, predictive calibration, numerical execution, and multi-agent disaggregation. Current public evidence cannot yet distinguish robust predictive ability from temporal contamination, unmodeled frictions, short-window Sharpe uncertainty, narrative fitting, and parametric priors. The problem is not only evaluative but structural. Language confidence is not tradable probability, narrative reasoning is not numerical execution, and model priors may become undisclosed implicit factor exposures. We contribute a minimum reporting protocol suite, P1--P6, with tiered applicability by claim strength, and a conservative modular alternative that uses LLMs as auditable information interfaces upstream of independent calibration, risk, and execution modules. Code and reproduction harness: https://github.com/hj1650782738/Trading.

Yuxuan Ye, Jun Han, Ao Hu +7

Fudan University · Shanghai University of Finance and Economics · Southwest University of Finance and Economics +3

LLM Agent Evaluation AI Agent Benchmarks LLM Agents Finance Algorithmic Trading

May 16, 2026cs.AI

Multi-Paradigm Agent Interaction in Practice:A Systematic Analysis of Generator-Evaluator, ReAct Loop,and Adversarial Evaluation in the buddyMe Framework

The rapid evolution of Large Language Model (LLM) agents has produced diverse interaction paradigms, yet few production systems integrate multiple paradigms within a unified architecture. This paper presents a systematic analysis of three principal agent interaction paradigms, including Multi-Agent Orchestration (Generator-Evaluator), ReAct Tool-Use Loops, and Memory-Augmented Interaction, as implemented in buddyMe, an open-source multi-model agent programming framework. We formalize a five-stage processing pipeline: Requirement Pre-Review -> Task Decomposition -> ReAct Execution -> Real-Execution Verification -> Adversarial Evaluation Discussion, and establish a six-dimensional evaluation schema with weighted scoring. Through four empirical case studies drawn from real-world deployment logs covering museum guide generation, scheduled weather tasks, and comprehensive tour planning, we draw three key conclusions. First, Generator-Evaluator pre-review detects requirement omissions in 20 percent of complex tasks, with 80 percent tasks passing initial inspection. Second, the ReAct loop ensures stable subtask execution but leads to around 30 percent redundant tool invocations. Third, adversarial Evaluator-Defender discussions reach consensus within 2-3 rounds for nearly 70 percent of scenarios, functioning mainly for content refinement rather than logical reversal. We additionally provide three Mermaid-based architectural diagrams and conduct cross-paradigm comparisons with CrewAI, AutoGen, LangGraph, MemGPT and A-Mem across six system dimensions. The research outcomes offer practical design guidelines for constructing stable and reliable multi-paradigm agent systems.

Xiaohua Wang, Chao Han, Kai Yu +2

BuddyMe Research Team, Nanjing 210000, China · CHARMMIRAEL Biotech Co., Ltd, Nanjing 210000, China

LLM Agent Orchestration LLM Agent Evaluation

May 15, 2026cs.CL

PQR: A Framework to Generate Diverse and Realistic User Queries that Elicit QA Agent Failures

Evaluating LLM-based agents remains challenging because identifying meaningful failure cases often requires substantial human effort to design realistic test scenarios. Prior works primarily focus on automatically discovering agent failures induced by adversarial users, while overlooking queries with real user intents that also trigger agent failures. We introduce PQR, a framework that not only surfaces agent failures with respect to specific objectives (e.g., helpfulness, safety, etc.) but also resembles real users' intents. PQR operates through an iterative interaction between two complementary modules. The query refinement module performs rewrites to explore diverse query variations, while the prompt refinement module uses prior feedback to derive new objective-violating strategies and realism policies for refining prompts, which in turn generate failure-triggering yet realistic queries. We evaluate PQR on detecting an e-commerce QA agent's unhelpful responses. Our method uncovers 23% - 78% more unhelpful responses, and our generated queries are more diverse and realistic compared to previous methods.

Yunan Lu, Luigi Liu, Omar Yahia +2

Columbia University · University of California San Diego · Walmart

AI Agent Reliability Adversarial Prompt Generation LLM Agent Evaluation Conversational Agents LLM Agent Reliability

May 15, 2026cs.AI

Confirming Correct, Missing the Rest: LLM Tutoring Agents Struggle Where Feedback Matters Most

Effective tutoring requires distinguishing optimal, valid but suboptimal, and incorrect student solutions, a distinction central to intelligent tutoring systems (ITS) but untested for LLM-based tutors. As LLMs are increasingly explored as conversational complements to ITS, evaluating their diagnostic precision is essential. We present a benchmark of seven LLM feedback agents in propositional logic using knowledge-graph-derived ground truth across 10,836 solution--feedback pairs and three feedback conditions. Models achieved near-ceiling performance on optimal steps but systematically over-rejected valid but suboptimal reasoning and over-validated incorrect solutions, precisely where adaptive tutoring matters most. These failures persisted across models regardless of solution context, suggesting architectural rather than informational limits. Moreover, accurate diagnosis did not reliably produce pedagogically actionable feedback, revealing a gap between diagnostic judgment and instructional effectiveness. Our findings suggest that LLMs are better suited for hybrid architectures where KG-grounded models handle diagnosis while LLMs support open-ended scaffolding and dialogue.

Tahreem Yasir, Wenbo Li, Sam Gilson +3

North Carolina State University

Intelligent Tutoring Systems Educational Assessment LLM Agent Evaluation Generative AI in Education

May 15, 2026cs.AI

Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDP

Deploying compound LLM agents in adversarial, partially observable sequential environments requires navigating several design dimensions: (1) what the agent sees, (2) how it reasons, and (3) how tasks are decomposed across components. Yet practitioners lack guidance on which design choices improve performance versus merely increase inference costs. We present a controlled study of compound LLM agent design in CybORG CAGE-2, a cyber defense environment modeled as a Partially Observable Markov Decision Process (POMDP). Reward is non-positive, so all configurations operate in a failure-mitigation mode. Our evaluation spans five model families, six models, and twelve configurations (3,475 episodes) with token-level cost accounting. We vary context representation (raw observations vs. a deterministic state-tracking layer with compressed history), deliberation (self-questioning, self-critique, and self-improvement tools, with optional chain-of-thought prompting), and hierarchical decomposition (monolithic ReAct vs. delegation to specialized sub-agents). We find that: (1) Programmatic state abstraction delivers the largest returns per token spent (RPTS), improving mean return by up to 76% over raw observations. (2) Distributing deliberation tools across a hierarchy degrades performance relative to hierarchy alone for all five model families, reaching up to 3.4

\times

worse mean return while using 1.8-2.7

\times

more tokens. We call this destructive pattern a deliberation cascade. (3) Hierarchical decomposition without deliberation achieves the best absolute performance for most models, and context engineering is generally more cost-effective than deliberation. These findings suggest a design principle for structured adversarial POMDPs: invest in programmatic infrastructure and clean task decomposition rather than deeper per-agent reasoning, as these strategies can interfere when combined.

Igor Bogdanov, Chung-Horng Lung, Thomas Kunz +3

Carleton University Ottawa, Ontario, Canada · Defence R&D Canada Ottawa, Ontario, Canada · Cistel Technology Ottawa, Ontario, Canada

Multi-Agent LLM Systems LLM Agent Orchestration LLM Agent Evaluation LLMs for Cybersecurity LLM Agents

May 15, 2026cs.AI

SaaS-Bench: Can Computer-Use Agents Leverage Real-World SaaS to Solve Professional Workflows?

Computer-Using Agents (CUAs) are rapidly extending large language models (LLMs) beyond text-based reasoning toward action execution in more complex environments, such as web browsers and graphical user interfaces (GUIs). However, existing web and GUI agent benchmarks often rely on simplified settings, isolated tasks, or short-horizon interactions, making it difficult to assess capabilities of agents in realistic professional workflows. Software-as-a-Service (SaaS) environments are a natural choice for CUA evaluation, as they host a large share of modern digital work and naturally involve dynamic system states, cross-application coordination, domain-specific knowledge, and long-horizon dependencies. To this end, we introduce SaaS-Bench, a benchmark built on 23 deployable SaaS systems across six professional domains, containing 106 tasks grounded in realistic work scenarios. These tasks require long-horizon execution, cover both text-only and multimodal settings, and are evaluated with weighted verification checkpoints that measure strict task completion and partial progress. Experiments show that representative LLM-based agents struggle on SaaS-Bench, with even the strongest model completing fewer than 4% of tasks end-to-end, exposing limitations in planning, state tracking, cross-application context maintenance, and error recovery. Code are available at https://github.com/UniPat-AI/SaaS-Bench for reproduction.

Kean Shi, Zihang Li, Tianyi Ma +13

1UniPat AI · 2PKU · 3HKU +2

Computer-Use Agent Benchmarks Computer-Use Agents LLM Agent Evaluation AI Agent Benchmarks Long-Horizon LLM Agents

May 15, 2026cs.LG

Rule2DRC: Benchmarking LLM Agents for DRC Script Synthesis with Execution-Guided Test Generation

Manufacturable chip layouts must satisfy thousands of geometry-based design rules, and design rule checking (DRC) enforces them by running executable DRC scripts on layouts. Translating natural language rules into correct DRC scripts is labor-intensive and requires specialized expertise, motivating LLM agents for DRC script synthesis and debugging. However, existing benchmarks have small evaluation sets and often evaluate scripts by code similarity rather than execution correctness, and prior machine learning-based methods either ignore execution feedback or require labeled test layouts as agent's input. To this end, we introduce Rule2DRC, a large-scale benchmark for DRC script coding agents with 1,000 rule-to-script tasks and 13,921 evaluation chip layouts for execution-based scoring. Rule2DRC provides an evaluation pipeline that measures functional correctness via DRC execution outcomes without requiring evaluation layouts as input to the agent. We also propose SplitTester, a tester agent for program selection that uses execution feedback to generate discriminative test cases and separate previously indistinguishable candidate scripts, substantially improving Best-of-N selection performance in this domain. We release the code at https://github.com/snu-mllab/Rule2DRC.

Jinuk Kim, Junsoo Byun, Donghwi Hwang +2

Department of Computer Science and Engineering, Seoul National University · Neural Processing Research Center · Samsung Electronics Co., Ltd.

Electronic Design Automation LLM Agent Evaluation Automated Test Generation Code Generation Benchmarks

May 15, 2026cs.AI

PRISM: Prompt Reliability via Iterative Simulation and Monitoring for Enterprise Conversational AI

Deploying large language model (LLM)-driven conversational agents in enterprise settings requires prompts that are simultaneously correct at launch and resilient to the non-deterministic behavioral drift that characterizes production LLM deployments. Existing prompt optimization frameworks address prompt quality as a one-time compile-time problem, leaving open the equally critical question of how to detect and repair prompt regressions caused by silent LLM behavior changes over time. We present PRISM (Prompt Reliability via Iterative Simulation and Monitoring), a closed-loop framework that treats prompt engineering as a continuous reliability engineering problem rather than a one-time authorship task. PRISM takes as input plain-language agent requirements, a set of configured tools and memory variables, and an initial draft prompt. It automatically generates test cases from requirements, simulates full multi-turn conversations against a platform-faithful LLM environment, evaluates pass/fail using an LLM-as-judge, diagnoses root causes of failures, and surgically repairs the prompt -- iterating until all tests pass. Critically, PRISM is designed to run on a scheduled basis (daily), treating LLM behavioral drift as a first-class reliability concern. We evaluate PRISM across 35 enterprise conversational agents over a three-week deployment period on the Yellow.ai V3 platform. PRISM reduces median prompt authoring time from 2 days to under 30 minutes, achieves 99% production reliability across all evaluated agents, and successfully identifies and repairs production regressions caused by LLM behavioral drift within a 24-hour detection window. Our results suggest that continuous, simulation-driven prompt optimization is both tractable and necessary for reliable enterprise conversational AI at scale.

Keshava Chaitanya, Jahnavi Gundakaram

LLM Prompting LLM Agent Evaluation Prompt Optimization Language Model Robustness LLM Agent Reliability

May 14, 2026cs.CL

Is Grep All You Need? How Agent Harnesses Reshape Agentic Search

Recent advances in Large Language Model (LLM) agents have enabled complex agentic workflows where models autonomously retrieve information, call tools, and reason over large corpora to complete tasks on behalf of users. Despite the growing adoption of retrieval-augmented generation (RAG) in agentic search systems, existing literature lacks a systematic comparison of how retrieval strategy choice interacts with agent architecture and tool-calling paradigm. Important practical dimensions, including how tool outputs are presented to the model and how performance changes when searches must cope with more irrelevant surrounding text, remain under-explored in agent loops. This paper reports an empirical study organized into two experiments. Experiment 1 compares grep and vector retrieval on a 116-question sample from LongMemEval, using a custom agent harness (Chronos) and provider-native CLI harnesses (Claude Code, Codex, and Gemini CLI), for both inline tool results and file-based tool results that the model reads separately. Experiment 2 compares grep-only and vector-only retrieval while progressively mixing in additional unrelated conversation history, so that each query is embedded in more distracting material alongside the passages that matter. Across Chronos and the provider CLIs, grep generally yields higher accuracy than vector retrieval in our comparisons in experiment 1; at the same time, overall scores still depend strongly on which harness and tool-calling style is used, even when the underlying conversation data are the same.

Sahil Sen, Akhil Kasturi, Elias Lumer +2

PricewaterhouseCoopers, U.S.

Agentic Search LLM Agent Evaluation Lexical Retrieval Information Retrieval LLM Agent Harnesses Dense Retrieval

May 14, 2026cs.CL

From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents

Voice agents increasingly require reliable tool use from speech, whereas prominent tool-calling benchmarks remain text-based. We study whether verified text benchmarks can be converted into controlled audio-based tool calling evaluations without re-annotating the tool schema and gold labels. Our dataset-agnostic framework uses text-to-speech, speaker variation, and environmental noise to create paired text-audio instances while preserving the original dataset annotations. Based on extensive evaluation of 7 omni-modal models on audio-converted versions of Confetti and When2Call, our framework demonstrates that the performance is strongly model- and task-dependent: Gemini-3.1-Flash-Live obtains the highest Confetti score (70.4), whereas GPT-Realtime-1.5 performs best on When2Call (71.9). On Confetti, the text-to-voice gap ranges from 1.8 points for Qwen3-Omni to 4.8 points for GPT-Realtime-1.5. A targeted analysis of failure cases demonstrates that degradations most often reflect misunderstandings of argument values in the speech. Considering real-world deployment scenarios, we further report text-only results, an ambiguity-based reformulation stress test, and a reference-free LLM-as-judge protocol validated against human preferences. Notably, we find that open-source Qwen3 judges with at least 8B parameters exceed 80% agreement with proprietary judges, supporting privacy-preserving evaluation. Overall, our framework provides a verifiable and reproducible first-stage diagnostic that complements purpose-built audio corpora.

Md Tahmid Rahman Laskar, Xue-Yong Fu, Seyyed Saeed Sarfjoo +3

Dialpad Inc.

Audio-Language Model Evaluation Voice Agent Evaluation Tool-Augmented Language Model Agents LLM Agent Evaluation AI Agent Benchmarks

May 14, 2026cs.LG

TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing

LLM routing matters most in long-horizon applications such as coding agents, deep research systems, and computer-use agents, where a single user request triggers many model calls. Routing each call to the cheapest sufficient model can cut costs without sacrificing quality, yet existing router benchmarks evaluate routers only on one-shot prompts. They never expose the router-visible prefix at an intermediate agent step, never test whether a cheaper replacement preserves downstream task success, and often rely on online LLM judges at evaluation time. We introduce TwinRouterBench, a step-level routing benchmark with two tracks. The static track provides 970 router-visible prefixes from 520 instances across SWE-bench, BFCL, mtRAG, QMSum, and PinchBench, each paired with an execution-verified target tier estimated under a released downgrade-and-cascade protocol; scoring is deterministic arithmetic over tier labels, trajectory membership, and token costs, with no online evaluator-side LLM judge. The dynamic track supplies a harness that runs routers on the full 500-case SWE-bench Verified suite; in this paper we report a 100-case held-out evaluation disjoint from the static SWE supervision split. At each LLM call the router selects a concrete model from a locked pool, and success is measured by official task resolution and realized API spend. The two tracks support fast offline iteration followed by end-to-end validation under live agent execution. Code and data are available at https://github.com/CommonstackAI/TwinRouterBench.

Pei Yang, Wanyi Chen, Tongyun Yang +15

Gradient · Soochow University · Independent Researcher +7

Benchmark Design LLM Agent Evaluation Long-Horizon Agent Evaluation AI Agent Benchmarks LLM Agent Routing