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

All topics

Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict
Oct 8, 2026Kaiser Sun, Bernal Jimenez Gutierrez, Hongjun Liu +4LLM Agent Evaluation Epistemic Uncertainty
Johns Hopkins University · New York University
DataSense-Bench: The First Step Toward an AI Scientist
Oct 8, 2026Yudi Zhang, Mingyu Cao, Lu Yin +2Training Data Selection AI Agent Benchmarks
Eindhoven University of Technology · Max Planck Institute for Intelligent Systems · University of Surrey +2
A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization
Oct 8, 2026Ming Chen, Rong-Xi Tan, Ke Xue +8Black-Box Optimization AI Agent Benchmarks
State Key Laboratory of Novel Software Technology, Nanjing University · School of Artificial Intelligence, Nanjing University
Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models
Oct 8, 2026Youwei Feng, Yitong Zhang, Yuetong Liu +1LLM Agent Safety LLM Guardrails
Tsinghua University, China · College of AI, Tsinghua University, China
Narrow and Deep: An Ontology Tower as the Knowledge of an LLM Agent for an Industrial Equipment System
Oct 8, 2026Younghwan Joo, Sung-il KimLLM Agents LLM Agent Evaluation
Energy Efficiency Research Division, Korea Institute of Energy Research, 152 Gajeong-ro, Yuseong-gu, Daejeon, 34129, Republic of Korea · Energy Engineering, University of Science & Technology, 217 Gajeong-ro, Yuseong-gu, Daejeon, 34113, Republic of Korea
TRACE: Diagnosing Verifier Brittleness in Agentic Evaluation
Oct 8, 2026Radhika GaonkarLLM Agent Evaluation AI Agent Evaluation
Prime Intellect
Evidence-Traceable Dynamic Interviewer Architecture for Expertise-Adaptive Qualitative Interviews Using Local LLMs
Oct 8, 2026Aisvarya Adeseye, Jouni Isoaho, Adeyemi Adeseye +2Conversational Agents LLM Agent Evaluation
Department of Computing, University of Turku, Turku, Finland
Evaluating Local Language Model Agents for Reproducible Data Engineering: An Empirical Software Engineering Study of Mobility Workflows
Oct 8, 2026Jorge García-Carrasco, Javier Sanchis, Alejandro Reina-Reina +2LLM Agent Evaluation LLM Agent Reliability
Lucentia Research, Department of Software and Computing Systems, University of Alicante, Ctra. de Sant Vicent del Raspeig s/n, 03690 Sant Vicent del Raspeig, Alicante, Spain
Closed-loop evaluation of LLM agents for embedded software development
Oct 8, 2026Jorge García-Carrasco, Sergio García-Carrasco, Alejandro Maté +1AI Coding Agents LLM Agent Evaluation
Lucentia Research, Department of Software and Computing Systems, University of Alicante, Ctra. de San Vicente del Raspeig s/n, 03690 Sant Vicent del Raspeig, Spain · Universitary Institute of Materials Technology (IUTM), Universitat Politècnica de València, Plaça Ferrándiz i Carbonell, 03801 Alcoi, Spain
Loud Failures, Quiet Failures: Fault Detection and Recovery in Tool-Using Language Model Agents
Oct 7, 2026Obada KraishanTool-Using Agents LLM Agent Reliability
College of Media and Communication Texas Tech University Lubbock, TX, USA
LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Evolving Markets
Oct 7, 2026Jun Zhao, Leiming Fu, Yanbo Wen +9LLM Agent Evaluation AI Agent Benchmarks
National University of Singapore · Fudan University · The University of Sydney
Coding-Agent Benchmarks Should Match Their Users' Task Flows
Oct 7, 2026Igor Slinko, Yaroslav Golubev, Sergey TitovLLM Agent Evaluation AI Agent Benchmarks
JetBrains Research
Correct Answers, Unsupported Findings: Evidence Binding in Forensic Reconstruction of LLM Agent Logs
Oct 7, 2026Taehyeon Yun, Dongho Kim, Geonwoo Kim +3Digital Forensics Data Provenance
aSungkyunkwan University, Republic of Korea
From Plausible Hierarchies to Useful Taxonomies: Evaluating Agentic Harnesses on Customer Feedback
Oct 7, 2026Prabhath Chellingi, Raviraja G, Viraj BagalAutomated Evaluation LLM Agent Evaluation
Enterpret
From Retrieval to Customer Context: Evaluating Frontier-Model Systems for Voice-of-Customer Analysis
Oct 7, 2026Raviraja G, Viraj Bagal, Prabhath ChellingiData Analysis Agents LLM Agent Evaluation
Enterpret
DUDA-Bench: Benchmarking LLM Agents on Multimodal Data-Driven Urban Diagnosis
Oct 7, 2026Yizhi Song, Hang Ni, Weijia Zhang +1Data Analysis Agents AI Agent Benchmarks
The Hong Kong University of Science and Technology (Guangzhou) Guangzhou, China
GeoNatureAgent (GNA): A Framework and Benchmark for Pre-Production Evaluation of Tool-Using Agents on Geospatial and Environmental Tasks
Oct 6, 2026Gabriel Diaz-Ireland, Diego Prieto-Herráez, Mario García Peces +3Tool-Use Evaluation LLM Agent Evaluation
Universidad Católica de Ávila (UCAV) Ávila, Spain · Independent Researcher Madrid, Spain · Department of Earth and Planetary Sciences, Johns Hopkins University Baltimore, MD, USA +1
Not Every Call Needs a Frontier Model: Per-Call-Site Evaluation of Small Language Models in a Deployed Agentic Home-Automation System
Oct 6, 2026Panagiotis Kasnesis, Christos Chatzigeorgiou, Lazaros Toumanidis +1Small Language Models LLM Agent Evaluation
University of West Attica, Athens, Greece · Waldiez PC · ThinGenious PC
Transect: Retaining Observability for Long-Horizon LLM Agent Evaluations
Oct 6, 2026Toby D. Pilditch, Konstantinos Voudouris, Alexandra Abbas +1LLM Agent Evaluation Long-Horizon Agent Evaluation
UK AI Security Institute
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?
Oct 6, 2026Yibo Li, Jinhang Qiu, Zhi Zheng +4LLM Agent Evaluation AI Agent Benchmarks
National University of Singapore
DecepEval: A Benchmark for Evaluating Deception in LLM Agents
Oct 6, 2026Yiming Xu, Hongyue Yu, Beihua Yang +8Deception in Language Models LLM Agent Evaluation
Xi’an Jiaotong University · University of Virginia · Griffith University +2
Confidence Reasoning Graphs: Structured Confidence Estimation for LLM Agents
Oct 6, 2026Brendan King, Farima Fatahi Bayat, Jean-Flavien Bussotti +2Probability Calibration Confidence Estimation in Language Models
University of California, Santa Cruz · Megagon Labs
An Empirical Study of Agent Skills' Downstream Utility
Oct 6, 2026Yu Cheng, Dehai Zhao, Zhongxin Liu +3LLM Agent Evaluation LLM Agent Skill Retrieval
Zhejiang University Hangzhou, China · Jiangxi Normal University Nanchang, China · CSIRO’s Data61 Australia
ServeLearnBench: How Well Can Agents Self-Improve from Serving Experience?
Oct 6, 2026Haizhong Zheng, Yizhuo Di, Ranajoy Sadhukhan +2Continual Learning for LLM Agents LLM Agent Evaluation
Carnegie Mellon University · Amazon
Quantization Effects on Tool-Failure Recovery Vary Across Prompts and Evaluation Designs
Oct 6, 2026Yuhe HuTool-Augmented Language Model Agents LLM Agent Evaluation
Duke University
From Evidence to Action: How Tool-Using Agents Fail
Oct 6, 2026Hongzhan Lin, Shidong Cao, Ziyang Luo +3Agent Failure Analysis Evidence-Grounded Reasoning
National University of Singapore · Hong Kong Baptist University · Amazon Web Services +1
AgentPrivArena: Evaluating and Auditing Real-world AI Agent Privacy
Oct 5, 2026Shouju Wang, Haopeng ZhangAI Agent Auditing LLM Agent Evaluation
University of North Carolina at Charlotte
Evaluating Inference Compute for Generative AI: A Framework for Enterprise Workloads
Oct 5, 2026Abbas Raza Ali, Muhammad Ajmal Siddiqui, Moona ZahidLLM Inference Efficiency Disaggregated LLM Serving
Citigroup Inc., London, United Kingdom · Ernst & Young LLP, London, United Kingdom · NVIDIA Corporation, London, United Kingdom
Judged Useless, Queried Anyway: Tool-Using Agents Rarely Turn Their Own Evidence Judgments into Stopping Decisions
Oct 5, 2026Chubin Zhang, Zhenglin Wan, Xingrui Yu +4LLM Agent Evaluation Tool-Using Agents
Nanyang Technological University, Singapore · National University of Singapore, Singapore · CFAR, Agency for Science, Technology and Research, Singapore +3
MedicalHarness: A Controlled Evaluation of LLMs and Agent Harnesses on Medical Tasks
Oct 5, 2026Ziqing Wang, Lili Zhao, Kaize DingLLM Agent Evaluation AI Agent Benchmarks
Northwestern University

Oct 8, 2026, cs.AIJ/K move · Enter open · S save

Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict

Kaiser Sun, Bernal Jimenez Gutierrez, Hongjun Liu, Jingyu Zhang+3

Johns Hopkins University · New York University

LLM Agent Evaluation Epistemic Uncertainty Knowledge Conflicts in Language Models

Open paper AskPDF arXiv

When retrieved evidence contradicts an agent's prior beliefs, does it revise its answer, acknowledge uncertainty, or persist with an incorrect conclusion? Existing evaluations of agentic systems focus primarily on task success, offering limited insight into how agents handle such conflicts. We propose to evaluate agents on epistemic humility (EH): the agent's willingness to recognize, act on, and communicate uncertainty during task execution. We operationalize EH through three trajectory-level behavioral dimensions: Identify, Solve, and Escalate (ISE). Through knowledge conflict, situations where the backbone language model's parametric knowledge contradicts the evidence it encounters, or where two contextual sources disagree, we evaluate two conflict settings: (1) controlled conflict and (2) naturally occurring conflict during multi-step agentic execution, each paired with matched no-conflict controls. Evaluating four agents, we find that higher task accuracy does not necessarily correspond to greater epistemic humility: some high-accuracy configurations recognize conflicts during execution but do not communicate unresolved uncertainty in their incorrect final answers. Trajectory-level analysis further reveals that agents frequently detect conflicts in early steps of execution but fail to maintain or resolve them in later steps. Finally, we show that model-level interventions can improve EH, but often at the cost of task accuracy, suggesting that epistemic humility emerges from the interaction among the backbone model, agent harness, and evaluation environment.

Momentum

Related topics

Latest papers 793