Agent Harness Optimization

Ask about this topic

Momentum

46 papers in the last four weeks, up 130% on the four weeks before. 0.5% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 118

All topics
CardsList

  1. Raven: The Harness of Harnesses for Composable Agentic Intelligence

    Sep 27, 2026EverMind AILLM Agent OrchestrationAgent Harness Optimization

    EverMind AI

  2. Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents

    Sep 24, 2026Tingyu Qu, Weigao Sun, Yuecheng Liu +23Agentic RLAgent Harness Optimization

    MAI Team, Alibaba Token Hub, Alibaba Group

  3. Policy as Code: A Coroutine-Bridge Harness for Fast-Reasoning Reliability on CAR-bench

    Sep 24, 2026Ivan MatveevAgent Harness OptimizationAI Agent Benchmarks

    Proxima Ultra

  4. AdaHVLA: Adaptive Harnesses for Long-Horizon Vision-Language-Action Execution

    Sep 24, 2026Junyi Tang, Jie Peng, Zezhen Ding +2Long-Horizon Robotic ManipulationAgent Harness Optimization

    UNC · USTC · HKUST +1

  5. HarnessPAI: An Evolving Harness for Physical AI

    Sep 24, 2026Xin Wang, Wenhao Wu, Menghao Zhang +20Program SynthesisAgent Harness Optimization

  6. Control the Harness, Control the Cost: Routing and Governing AI Coding Agents in the Enterprise

    Sep 24, 2026Arian Abbasi, Alan Aqrawi, Ted KwartlerTool-Augmented Language Model AgentsCoding Agents

    Accenture Responsible AI · Accenture Americas Advanced AI Practice · Harvard Extension School, Harvard University

  7. Automatic Harness Evolution for Hardware Design Verification: Can LLMs Consolidate Gains Across Discovered Harnesses?

    Sep 24, 2026Kidus Seyoum, Ajay MitturFormal Hardware VerificationAgent Harness Optimization

    NVIDIA

  8. CAVEAT: Towards Robust Computer-Use Agents in Incentive-Misaligned Environments

    Sep 23, 2026Yuxuan Li, Will Epperson, Wesley Deng +1Computer-Use AgentsAgent Harness Optimization

    Carnegie Mellon University · Microsoft Research

  9. Grow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents

    Sep 22, 2026Laizhen Li, Jiarui Li, Juanjuan Zhao +4Agent Harness OptimizationLLM Agent Workflow Optimization

    Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Shenzhen University of Advanced Technology +1

  10. RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

    Sep 21, 2026Peng Xia, Rujun Han, Zifeng Wang +11OOD GeneralizationAgent Harness Optimization

    Google Cloud AI Research · UNC-Chapel Hill · Stanford University +1

  11. An Empirical Study of Harness Design for Coding Agents

    Sep 17, 2026Run-Ze Fan, Zihao Zhang, Simin Ma +6Coding AgentsAgent Harness Optimization

    UMass Amherst · Emory University · UNC Charlotte

  12. SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

    Sep 17, 2026Haozhe Liu, Tian Ye, Sensen Gao +11Agent Harness OptimizationLLM Agent Workflow Optimization

    NVIDIA · NTU · MIT

  13. How Do Agent Harnesses Create Value? Planning Information and Release Control in Stateful LLM Agents

    Sep 17, 2026Yukun Zhang, Kemu Xu, Yishen ChenAgent Harness OptimizationLLM Agent Verification

    The Chinese University of Hong Kong, Shenzhen, China · University of Edinburgh, Edinburgh, United Kingdom · The Chinese University of Hong Kong, Hong Kong, China

  14. Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts

    Sep 16, 2026Guojun Zhu, Xunheng Huang, Peng Yin +3Counterfactual EvaluationBenchmark Construction

    School of Mathematical Sciences, University of Chinese Academy of Sciences, China · Department of Statistics & Data Science, National University of Singapore, Singapore · Institute of Automation, Chinese Academy of Sciences, China

  15. ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement

    Sep 14, 2026Siwei Wu, Jincheng Ren, Yizhi Li +11Coding AgentsAgent Harness Optimization

    University of Manchester · 3IQuest Research · 4M-A-P +3

  16. Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents

    Sep 12, 2026Ruiqing Yue, Yu Cui, Zhuoyu Sun +11Agent Harness OptimizationLLM Agent Harnesses

    Chengdu Institute of Computer Applications, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Beijing Institute of Technology +3

  17. RobustSGPO: Search-Space Control for Agent Harness Evolution

    Sep 10, 2026Zibo Zhao, Jijun Shi, Mo Zhou +9Agentic WorkflowsAgent Harness Optimization

    Wuhan University, Wuhan, China · Kuaishou Technology, Beijing, China

  18. Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails

    Sep 8, 2026Zhou Yu, Bin Bi, Shiva Kumar Pentyala +8Agent Harness OptimizationImitation Learning

    Salesforce AI

  19. NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

    Sep 8, 2026NeoHorse Team, Guoliang Cao, Guohao Dai +34Agent Harness OptimizationLLM Agent Self-Improvement

    TokenRhythm

  20. A Theory of Reliable Self-Evolution for Agent Harnesses

    Sep 8, 2026Qianshu Cai, Yonggang Zhang, Jun Nie +6Agent Harness OptimizationSelf-Improving Agents

    University of Science and Technology of China · Hong Kong Generative AI Research & Development Center; The Hong Kong University of Science and Technology · Hong Kong Baptist University

  21. MetaRSI / RSI2: A Meta-Recursive Self-Improving System for Recursive Self-Improving Systems Themselves

    Sep 6, 2026Zihan Tan, Leixin Sun, Zitong Shi +28Meta-LearningAgent Harness Optimization

    Hugging Face

  22. Beyond Prompts: Measuring and Optimizing LLM Tool-Agent Harnesses

    Sep 4, 2026Cen Mia Zhao, Haibo Ruan, Wenjie Chen +3Agent Harness OptimizationLLM Agent Workflow Optimization

    Airbnb, Inc., USA

  23. Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement

    Sep 1, 2026Haoyang Yan, Min-le Su, Hangfan Zhang +6Agent Harness OptimizationSelf-Improving Agents

    Shanghai Artificial Intelligence Laboratory

  24. HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?

    Sep 1, 2026Yuhao Wu, Jingyuan Zhang, Jiajun Shi +16LLM Agent EvaluationAgent Harness Optimization

  25. AgentFactory: Towards Automated Agentic System Design and Optimization

    Sep 1, 2026Enci Zhang, Haofeng Wang, Yuesheng Zhu +2Large Language Model-Guided OptimizationAgentic Workflows

    Peking University Shenzhen Graduate School, Shenzhen, China

  26. HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution

    Sep 1, 2026Wen Jiang, Mingmin Chu, Yimeng Tian +6Agent Harness OptimizationLLM Agent Reliability

    ICT AI Competence Center, Huawei Technologies, Shanghai, China

  27. WHALE: A Simple Recipe for Joint Harness-Weight Optimization

    Aug 31, 2026Haechan Kim, Yoonho Lee, Gisang Lee +2Agent Harness OptimizationLLM Agent Training

    KRAFTON · KAIST · Stanford University

  28. 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 SystemsAgent 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

  29. JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution

    Aug 26, 2026Guibin Zhang, Leo Lu, Fangzhou Xie +15Tool-Augmented Language Model AgentsAgent Harness Optimization

    JIT-Agent Team

  30. Harness Continual Learning: Continual Adaptation Beyond Model Parameters

    Aug 19, 2026Borui Kang, Jinrui Gu, Junhan Lv +3Continual Learning for LLM AgentsContinual Learning

    State Key Laboratory for Novel Software Technology, Nanjing University, China · University of Wollongong, Australia