LLM Agent Harnesses

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

49 papers in the last four weeks, up 88% on the four weeks before. 0.5% of all new papers.

Jul 13Week of Sep 28

Latest papers 198

All topics

Interface-Induced Trajectory Censoring
Sep 3, 2026Wenbo WangTool-Use Evaluation AI Agent Evaluation
City University of Hong Kong
A Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious Behaviors
Sep 3, 2026Pengxun Li, Litian Zhang, Jianwei Hou +4AI Agent Security LLM Agent Harnesses
Beijing University of Posts and Telecommunications · Data and Technology Support Center of the Cyberspace Administration of China · Beihang University +1
Bioinfoysis Technical Report
Sep 3, 2026Qingyang Shao, Xin Zhang, Zhouyang Yuan +24Multi-Agent LLM Systems LLM Agent Harnesses
DeepAutonomy Team
What Do CAE Simulation Agents Really Need Beyond a Generic Harness?
Sep 3, 2026Jiasheng Shi, Tianhan ZhangMulti-Agent LLM Systems LLM Agent Evaluation
DP Technology · Beijing, China · School of Astronautics, Beihang University +1
SafeEvolve: Harness-Policy Co-Evolution from Agent Experience for Safety Alignment
Sep 2, 2026Qinghua Mao, Wanying Qu, Dadi Guo +8LLM Safety Alignment LLM Agent Safety
Shanghai AI Laboratory · SJTU · Fudan University +2
Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool Primitives
Sep 1, 2026Haibo Jin, Suijin Wang, Xucheng Yu +2Tool-Augmented Language Model Agents LLM Agent Orchestration
School of Information Sciences University of Illinois at Urbana-Champaign Champaign, IL 61820 · Independent Researcher Starc Institute
CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses?
Sep 1, 2026Damien Sileo, Dimitri KachlerTemporal Reasoning in Language Models AI Agent Benchmarks
Univ. Lille, Inria, CNRS, Centrale Lille, UMR 9189 - CRIStAL, F-59000 Lille, France
Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement
Sep 1, 2026Haoyang Yan, Min-le Su, Hangfan Zhang +6Agent Harness Optimization Self-Improving Agents
Shanghai Artificial Intelligence Laboratory
Agentic programs: an emerging form of scientific software in computational materials science
Sep 1, 2026Yunsung Lim, Haekwan Jeon, Jaesun Kim +2LLM Agent Harnesses Computational Materials Science
Research Institute of Advanced Materials, Seoul National University, Seoul, 08826, Republic of Korea. · Department of Materials Science and Engineering, Seoul National University, Seoul, 08826, Republic of Korea. · Center for AI and Natural Sciences, Korea Institute for Advanced Study, Seoul, 02455, Republic of Korea.
Runtime-Independent Persistent Agents: Preserving Identity, Memory, and Code Across Models, Harnesses, and Servers
Sep 1, 2026Zhenyu Zhao, Roy ZhaoLLM Agent Harnesses Agent Memory Management
Independent Researcher · Paul G. Allen School of Computer Science & Engineering, University of Washington
Dr. Claw: An AI Scientist Workspace for Vibe Research
Aug 31, 2026Dingjie Song, Hanrong Zhang, Dawei Liu +10AI Agents for Scientific Discovery Coding Agents
Lehigh University · University of Illinois Chicago · University of Pennsylvania +3
A Human-in-the-Loop Autonomous Agent for Industry Time Series Forecasting
Aug 31, 2026Xiaoyu Tao, Mingyue Cheng, Ze Guo +4Electricity Price Forecasting Time Series Forecasting
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China
Reachability-Based Capability Confinement for LLM Agents under Indirect Prompt Injection
Aug 30, 2026Wujie Xiong, Rabimba Karanjai, Yang Lu +2LLM Agent Security Information Flow Control
Kent State Univeristy · PayPal AI Labs · University of Houston
Harness-RL: Black-Box Reinforcement Learning with Action-Args Decoupling for Central-Agent Multi-Agent Harnesses
Aug 30, 2026Xinke Jiang, Zhixin Zhang, Zhibang Yang +6Multi-Agent LLM Systems Agent Harness Optimization
National Engineering Research Center of Software Engineering, Peking University, Beijing, China · School of Computer Science, Peking University, Beijing, China · Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China +3
Logos: An Agent Harness on a Cross-Process Bus
Aug 28, 2026Hanzhang Jia, Liheng Zeng, Hao Cheng +2Multi-Agent Systems LLM Agent Harnesses
University of Sussex Brighton, United Kingdom · Zhejiang Gongshang University Hangzhou, China · Shanghai Shuyuan Information Technology Co., Ltd. Shanghai, China
EvoUndo: Recoverability-Constrained Self-Evolution for LLM Agent Harnesses
Aug 28, 2026Tanmay Sah, Dolly Sah, Harshul Jain +1LLM Agent Self-Improvement LLM Agent Harnesses
Independent Researcher
SKILL.state: Scalable Long-Horizon Agent Skills
Aug 26, 2026Sanket Badhe, Priyanka Tiwari, Jonghyun ChungLong-Horizon Agent Tasks Long-Horizon LLM Agents
Google LLC · Purdue University
Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report
Aug 16, 2026TaoLive AIGC LLM Team, Yuhan Sun, Wenhao Lin +7LLM Agent Training LLM Agent Harnesses
TaoLive AIGC LLM Team
Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents
Aug 15, 2026Tianxin Wei, Zhan Shi, Minhua Lin +14Continual Learning for LLM Agents LLM Agent Skill Learning
University of Illinois Urbana-Champaign · Amazon · The Pennsylvania State University +3
Capability Sheaves for Compositional Agent-Harness Repair: Controlled Quotients and a Real-Repository Stress Test
Aug 13, 2026Saveliy BatruinAutomated Program Repair Sheaf Theory
Independent researcher
Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents
Aug 13, 2026Jiajun Ruan, Peiyang Li, Yukun Chen +2LLM Agent Security LLM Agent Safety
University of Minnesota · Ant Group · Tsinghua University +1
@skills: Attention is all you have
Aug 12, 2026Li Yin, Zhi Li, Zhan Shi +4LLM Agent Skill Retrieval LLM Agent Harnesses
Atlas · SylphAI · The University of Texas at Austin
SHE: Trajectory-driven Safety Harness Evolution for LLM Agents
Aug 10, 2026Wanying Qu, Qinghua Mao, Yu Li +12Agent Harness Optimization LLM Agent Safety
Shanghai Artificial Intelligence Laboratory · Shanghai Jiao Tong University · Fudan University +1
STAIR: Effective Incident Response Using an End-to-End Agentic Planning Framework
Aug 10, 2026Hanlin Jiang, Jionghao Huang, Shaofei Li +6Autonomous Cyber Defense LLM Agent Orchestration
Key Laboratory of High Confidence Software Technologies, Peking University, Ministry of Education · Southeast University · Huawei Technologies Co., Ltd.
From Prompt to Harness: Coderlet from Scratch
Aug 10, 2026Mengfan LiCoding Agents Agent Harness Optimization
Evidence-Calibrated Runtime Reconstruction for Agent Skills Across Heterogeneous Coding Agents
Aug 9, 2026Xueping GaoAI Coding Agents AI Agent Monitoring
Alibaba Cloud, Hangzhou, China
The Scaffolding Matters More Than the Interface: A Controlled Comparison of MCP and CLI Tool Use Across Seven Agent Scaffoldings, Five Language Models, and One Software Task
Aug 9, 2026Marc Alier Forment, María José Casañ Guerrero, Francisco José García-Peñalvo +1AI Coding Agents LLM Agent Evaluation
Universitat Politècnica de Catalunya (UPC), Barcelona, Spain · Universidad de Salamanca (USAL), Salamanca, Spain · Universidad del País Vasco / Euskal Herriko Unibertsitatea (UPV/EHU), Donostia-San Sebastián, Spain
$A^2E$ : An End-to-End Agent Auditing Engine
Aug 7, 2026Haoning Wang, Mingxun Zhang, Chenyue Yu +4Tool-Use Evaluation AI Agent Auditing
Shanghai Artificial Intelligence Laboratory
HarnessSafe: Evaluating Safety Across Persistent Carriers in Agent Harnesses
Aug 7, 2026Xiao Zhang, Yusheng Wang, Yuhao Fei +5AI Agent Security AI Agent Safety Benchmarks
Beijing University of Posts and Telecommunications · China Telecom Group Co., Ltd. · Beijing Academy of Artificial Intelligence
SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries
Aug 6, 2026Xingyu Tan, Xiaoyang Wang, Qing Liu +4LLM Agent Skill Retrieval LLM Agent Harnesses
UNSW & CSIRO Sydney, Australia · UNSW Sydney, Australia · CSIRO Hobart, Australia +2

Sep 3, 2026, cs.AIJ/K move · Enter open · S save

Interface-Induced Trajectory Censoring

Wenbo Wang

City University of Hong Kong

Tool-Use Evaluation AI Agent Evaluation AI Agent Benchmarks LLM Agent Harnesses

Open paper AskPDF arXiv

Agent evaluations report a tool-call rate read off the serving stack. That number can be zero while the model is emitting well-formed calls: the interface censors the trajectory before anything downstream sees it. On BFCL v4's own data, executor and scorer, holding weights, cases, decoding and seeds fixed and changing only the serving adapter, the same model scores 0.00 or 0.96 / 0.19. A 2x2 over chat template and parser locates the effect exactly: both main effects are exactly zero and all of it sits in the interaction -- no component is defective, and repairing one side of the contract buys precisely nothing. On tau-bench's 115 interactive retail tasks the same swap moves server-parsed calls from 0 to 636 and tasks reaching any tool execution from 0 to 103. Our probe reproduces the funnel across a 21x scale range of Qwen2.5-Coder: the server parses 0/100 at every size while well-formed emitted calls rise to 80/100 at 32B (~72 after calibration against an adjudicated gold standard). Under a matched envelope, across a comparable scale span, the silent fraction stays at 0-2, a prediction committed to the repository before the run. Llama-3.1-8B's 23% rate of calling the task function itself as a tool falls to 0 under one strict:true flag. The mismatch reaches inside the training loop, and its consequence is scale-dependent: in verl's AgentLoop at 7B, 45 of 115 generations carry a complete call; 0 are accepted, 0 execute, 0 return an observation. At 1.5B the same zero is over-determined, so we report the two scales separately. At evaluation time, repairing the adapter restores the mechanism but not a significant outcome gain: parsing 0->84, rescues 0->9, pass rate 53->62 (n.s.). We release a 98-line preflight check that catches every silent failure here. The observed tool-call rate is not a property of the model alone; it is a property of the model-interface stack that measures it.

Momentum

Related topics

Latest papers 198