LLM Agent Evaluation

LLM: Large Language Model

The field studies whether language-model agents can use tools, manage state, follow instructions, and achieve users’ goals across multi-step interactions. Benchmarks place agents in executable settings such as coding repositories, websites, terminals, business workflows, and medical or scientific tasks, while methods use hidden tests, state checks, trajectory analysis, and simulated users to assess performance. Evaluation increasingly includes cost, latency, privacy, safety, consistency, and process quality—not just whether the final answer is correct. Results remain difficult to compare because harnesses and scoring choices can change rankings, and strong performance on short or isolated tasks often fails to transfer to long-horizon real-world work.

Latest papers

1,221 papers231 papers in the last four weeks, up 62% on the four weeks before. 1.3% of all new papers.

Voluntary Collusion with Secret Tools in Competing LLM Agents
May 26, 2026Xijie Zeng, Frank RudziczLLM Agent Evaluation LLM Agent Safety
Dalhousie University · Vector Institute for Artificial Intelligence
DynaSchedBench: Calibrated Dynamic Scheduling Benchmarks and Observability Paradox in LLM-based Scheduling Agents
May 26, 2026Shijie Cao, Yuan Yuan, Jing LiuLLM Agent Evaluation Combinatorial Optimization
School of Computer Science and Engineering, Beihang University, Beijing 100191, China · Shenzhen Loop Area Institute, Shenzhen, China · Qingdao Research Institute, Beihang University +3
Benchmarks are Not Enough: RAMP for Runtime Assessing of Agentic Models in Production Systems
May 26, 2026Yipeng Ouyang, Xin Huang, Bingjie Liu +3Software Engineering Agents LLM Agent Evaluation
School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents
May 26, 2026Ye Yuan, Rui Song, Weien Li +12Social Deduction Games LLM Agent Evaluation
McGill University · Mila - Quebec AI Institute · University of Cambridge +3
It's Not the Capability: Harness Sensitivity Is Non-Monotone Across LLM Agent Tiers
May 26, 2026Yong-eun ChoAI Agent Reliability LLM Agent Evaluation
KailosLab · Seoul, Republic of Korea
Towards Feedback-to-Plan Decisions for Self-Evolving LLM Agents in CUDA Kernel Generation
May 26, 2026Yee Hin Chong, Jiaming Wu, Youhui Zhang +1GPU Kernel Optimization LLM Agent Evaluation
Department of Computer Science and Technology, Tsinghua University, Beijing, China · Beijing National Research Center for Information Science and Technology, Beijing, China
LogDx-CI: Benchmarking Log Reduction Tools for LLM Root-Cause Diagnosis
May 26, 2026Bowen QinLLM Agent Evaluation AI Agent Benchmarks
National University of Singapore
Verus-SpecGym: An Agentic Environment for Evaluating Specification Autoformalization
May 26, 2026Anmol Agarwal, Natalie Neamtu, Pranjal Aggarwal +6LLM Agent Evaluation Formal Verification
CMU · Amazon · Work performed while at Amazon.
JobBench: Aligning Agent Work With Human Will
May 25, 2026Yuetai Li, Yichen Feng, Zhangchen Xu +21Computer-Use Agent Benchmarks LLM Agent Evaluation
University of Washington · 10Bake AI · University of California, Santa Barbara +10
CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists
May 25, 2026Junlin Yang, Dylan Zhang, Xiangchen Song +7Structural Causal Models LLM Agent Evaluation
Tsinghua University · University of Illinois Urbana-Champaign · Carnegie Mellon University +2
When Do LLM Agents Treat Surface Noise Differently from Semantic Noise? A 68-Cell Measurement Study with a Held-Out Trace-Level Validation
May 25, 2026Liyun Zhang, Jiayi GuoCoT Reasoning LLM Agent Evaluation
School of Information and Software Engineering, UESTC · Jacobs School of Engineering, UC San Diego
PolyGnosis 2.0: Enhancing LLM Reasoning via Agentic Harness Engineering for Polymarket and OSINT Insight Extraction
May 25, 2026Daren Wang, Hong Xu, Jiawen XianMulti-Agent LLM Systems LLM Agent Orchestration
The Chinese University of Hong Kong · Evolution AI Lab
GroupTravelBench: Benchmarking LLM Agents on Multi-Person Travel Planning
May 24, 2026Xiang Cheng, Yulan Hu, Lulu Zheng +4AI-Assisted Decision Making LLM Planning
Gaoling School of Artificial Intelligence, Renmin University of China · AMAP, Alibaba Group
ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions
May 22, 2026Xianzhong Ding, Yangyang Yu, Changwei Liu +3Tool-Augmented Language Model Agents AI Coding Agents
Center for Advanced AI, Accenture · Argonne National Laboratory · Independent Researcher
Beyond Final Answers: Auditing Trajectory-Level Hallucinations in Multi-Agent Industrial Workflows
May 22, 2026Harshada Badave, Santosh Borse, Andrea Gomez +6AI Agent Reliability AI Agent Auditing
1IBM · 2Columbia University
SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills
May 22, 2026Yingtie Lei, Zhongwei Wan, Jiankun Zhang +13LLM Agent Evaluation LLM Agent Skill Learning
1The Ohio State University · 2The University of Chicago · University College London +4
From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
May 22, 2026Zisu Huang, Jingwen Xu, Yifan Yang +13LLM Agent Evaluation LLM Agent Skill Learning
Fudan University · Microsoft Research · Shanghai Jiao Tong University
OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agents
May 22, 2026Jiahao Ying, Boxian Ai, Wei Tang +2LLM Agent Skill Evaluation LLM Agent Evaluation
Singapore Management University · Institute of Trustworthy Embodied AI, Fudan University · Joy Future Academy, JD
More Skills, Worse Agents? Skill Shadowing Degrades Performance When Expanding Skill Libraries
May 21, 2026Hongwen Song, Song WeiLLM Agent Evaluation LLM Agent Skill Learning
Databricks Inc.
MBABench: Evaluating LLM Agents on End-to-End Spreadsheet Tasks in Finance
May 21, 2026Thomson Yen, Julian Poeltl, Harshith Srinivas Gear +9LLM Agent Evaluation AI Agent Benchmarks
Decision, Risk, and Operations Division, Columbia Business School · ESB Business School, Reutlingen University · Decision, Risk,and Operations Division, Columbia Business School
Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents
May 21, 2026Asaf Yehudai, Lilach Eden, Michal Shmueli-ScheuerLLM Agent Evaluation AI Agent Benchmarks
IIBM Research
SynAE: A Framework for Measuring the Quality of Synthetic Data for Tool-Calling Agent Evaluations
May 21, 2026Shuaiqi Wang, Aadyaa Maddi, Zinan Lin +1Tool-Use Evaluation LLM Agent Evaluation
Carnegie Mellon University · Microsoft Research
TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks
May 21, 2026Zhaoyang Chu, Jiarui Hu, Xingyu Jiang +8Computer-Use Agent Benchmarks Terminal-Agent Benchmarks
University College London · Nanjing University · Tencent
Benchmarking Autonomous Agents against Temporal, Spatial, and Semantic Evasions
May 21, 2026Jianan Ma, Xiaohu Du, Ruixiao Lin +8LLM Agent Evaluation LLM Agent Security
Hangzhou Dianzi University · Ant Group · Zhejiang University +1
Evaluating Large Language Models as Live Strategic Agents: Provider Performance, Hybrid Decomposition, and Operational Gaps in Timed Risk Play
May 21, 2026H. C. EkneLLM Agent Evaluation AI Agent Benchmarks
SMDD-Bench: Can LLMs Solve Real-World Small Molecule Drug Design Tasks?
May 20, 2026Kevin Han, Renfei Zhang, Kathy Wei +3LLM Agent Evaluation AI Agent Benchmarks
Carnegie Mellon University · Stealth · Pennsylvania State University
What Twelve LLM Agent Benchmark Papers Disclose About Themselves: A Pilot Audit and an Open Scoring Schema
May 20, 2026Mahdi Naser Moghadasi, Faezeh GhaderiBenchmark Auditing LLM Auditing
BrightMind AI, Texas Tech University · Research Division, BrightMind AI, Seattle, WA · Texas Tech University, Lubbock, TX +2
Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents
May 20, 2026Akshay Manglik, Vijay S. Kalmath, Jason Qin +6Multi-Agent LLM Systems LLM Agent Evaluation
Scale AI
MemGym: a Long-Horizon Memory Environment for LLM Agents
May 20, 2026Wujiang Xu, Yu Wang, Kai Mei +8LLM Agent Memory LLM Agent Evaluation
1Rutgers University · 2Capital One · 3Princeton University +1
AgentAtlas: Beyond Outcome Leaderboards for LLM Agents
May 19, 2026Parsa Mazaheri, Kasra MazaheriLLM Agent Reliability Computer-Use Agent Benchmarks
University of California, Santa Cruz · Massachusetts Institute of Technology

May 26, 2026J/K move · Enter open · S save

Voluntary Collusion with Secret Tools in Competing LLM Agents

Xijie Zeng, Frank Rudzicz

Dalhousie University · Vector Institute for Artificial Intelligence

LLM Agent Evaluation LLM Agent Safety Multi-Agent System Security Multi-Agent LLMs

Open paper AskPDF arXiv

Even when a tool is explicitly described as unfair and harmful to others, ostensibly safety-aligned LLM agents still voluntarily engage in secret collusion whenever doing so confers a strategic advantage. To investigate this phenomenon, we introduce an empirical framework built on two strategic multi-agent environments: Liar's Bar, a competitive deception scenario, and Cleanup, a mixed-motive resource-management scenario, in which agents are offered secret collusion tools that provide significant advantages while clearly disadvantaging the other agents. Across 12 models (at the 7B, 70B, and proprietary scales) and 6 prompt variants, we find that most agents consistently accept these tools and develop collusive strategies, while explicitly acknowledging the unfairness of the tools before accepting. We further show that neither the unfairness labels nor baseline alignment alone reliably deters collusion: only explicit ethical framing reduces adoption and, even then, smaller models remain susceptible. More broadly, our work presents the first systematic investigation of voluntary collusion adoption in LLM-based multi-agent systems, and suggests that preventing such behaviour requires explicit safeguards rather than reliance on general alignment.