When the Critic Falls Behind: Co-Evolving Rubrics and Harnesses for Continual Agent Self-Improvement
Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology(哈尔滨工业大学社会计算与交互机器人研究中心);Department of Computer Science and Technology, Institute for AI, Tsinghua University(清华大学计算机科学与技术系、人工智能研究院)
Hao Chen, Yukun Yan, Ziyu Han, Ye He, Chuanzhe Guo, Shangzhan Li, Qi Shi, Qingfu Zhu, Maosong Sun, Wanxiang Che
Autonomous agents increasingly depend on harnesses that govern interaction, memory, tools, and execution around large language models (LLMs). While recent work has begun to evolve these harnesses from execution experience, the supervision used to guide evolution often remains relatively static, making it difficult to track changing behavioral weaknesses across rounds and potentially limiting generalization to unseen tasks. To address this issue, we propose RuHarness, a rubric--harness co-evolution framework for continual agent self-improvement. RuHarness continually discovers and reassesses behavioral criteria from execution trajectories, prioritizes the most relevant unresolved weaknesses, and uses them to guide targeted harness updates while keeping the task objective fixed. Extensive experiments across diverse agent tasks and backbone models show that RuHarness outperforms strong harness-evolution baselines, particularly on unseen held-out tasks. Further analyses show that adaptive rubric prioritization tracks shifting weaknesses and supports more sustained improvement and stable generalization across evolution rounds.
Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents
Zhejiang University(浙江大学);University of Electronic Science and Technology of China(电子科技大学);Beijing University of Posts and Telecommunications(北京邮电大学);Zhejiang University of Technology(浙江工业大学)
CriticGen: Generation-Aware Evaluation as Actionable Feedback
AI Lab, Qifu Technology(奇富科技AI实验室);Beijing University of Posts and Telecommunications(北京邮电大学);University of Science and Technology Beijing(北京科技大学);Tongji University(同济大学)
InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training
Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China(香港理工大学计算机系);Department of Control Science and Engineering, Zhejiang University(浙江大学控制科学与工程学院)
Patient-specific rubric-based evaluation of large language models across longitudinal cancer care
Sun Yat-sen University Cancer Center(中山大学肿瘤防治中心);The Hong Kong Polytechnic University(香港理工大学);Nanfang Hospital, Southern Medical University(南方医科大学南方医院)
AI to Learn 2.0: A Deliverable-Oriented Governance Framework and Maturity Rubric for Opaque AI in Learning-Intensive Domains
Department of Biomedical Sciences, College of Life and Health Sciences, Chubu University(生物医学科学系,生命与健康科学学院,楚博大学);Center for Mathematical Science and Artificial Intelligence, Chubu University(数学科学与人工智能中心,楚博大学);Institute for Advanced Research, Nagoya University(先进研究所,名古屋大学)
Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values
State Key Laboratory of General Artificial Intelligence(通用人工智能国家重点实验室);School of Intelligence Science and Technology, Peking University(北京大学智能科学与技术学院);Peking University School of Software and Microelectronics(北京大学软件与微电子学院);Peking University School of Psychological and Cognitive Sciences(北京大学心理与认知科学学院);Key Laboratory of Machine Perception (Ministry of Education), Peking University(北京大学机器感知重点实验室)
Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite
Tencent HY LLM Frontier(腾讯HY大语言模型前沿);University of Maryland, College Park(马里兰大学帕克分校);University of Georgia(佐治亚大学);National University of Singapore(新加坡国立大学);Indiana University(印第安纳大学);Washington University in St. Louis(圣路易斯华盛顿大学);Nanyang Technological University(南洋理工大学)