Language model agents increasingly operate over long interaction streams, requiring online adaptation to distribution shifts through continual learning. However, existing agent harnesses typically either evolve their states only through forward information flow or rely on additional replay or validation data for harness optimization. To address this, we propose ReHarness, a recurrent harness framework for agentic continual learning that complements forward read and write with backward revision under a strictly online streaming protocol. We ask what information could have been captured differently in the harness state to better inform the current instance in the stream. Specifically, after each instance, we leverage the resulting trajectory as feedback to revise the reflections retrieved for that instance, thereby propagating feedback backward through the textual harness state. Across three continual learning benchmarks and three language model backbones, ReHarness consistently outperforms strong raw-context baselines, memory- and reflection-based methods, and prompt optimization approaches. Further analysis shows that ReHarness produces source-grounded and meaningful revisions, corrects overgeneralized or outdated experience under distribution shifts, and improves both stability and plasticity during continual learning.
EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究院，中国科学院）；Tongyi Lab , Alibaba Group（通义实验室，阿里巴巴集团）；Alibaba Group（阿里巴巴集团）；SUAT（深圳大学）
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；DeepWisdom；Singapore University of Technology and Design（新加坡科技设计大学）；Nanyang Technological University（南洋理工大学）；Shanghai Jiao Tong University（上海交通大学）；Tsinghua University（清华大学）；Université de Montréal & Mila（蒙特利尔大学及Mila）
AgentBug-Smith: Automatically Reproducing Real-World Harness Bugs in Agentic Systems
The University of Chicago（芝加哥大学）；Fudan University（复旦大学）；TensorBlock, Inc.（TensorBlock公司）；Tsinghua University（清华大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
HERA: Harness-Environment Co-Evolution for Reliable Agentic Abstention
University of Washington（华盛顿大学）；University of Leeds（利兹大学）；Carnegie Mellon University（卡内基梅隆大学）；Stanford University（斯坦福大学）；Allen Institute for AI（艾伦人工智能研究所）
Distilling Agentic Systems: A Roadmap across Models, Artifacts, and Harnesses
Central South University（中南大学）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；Hong Kong Polytechnic University（香港理工大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
Meituan（美团）；MBZUAI（Mohamed bin Zayed University of Artificial Intelligence）；Huazhong University of Science and Technology（华中科技大学）；Peking University（北京大学）；Tsinghua University（清华大学）；The Chinese University of Hong Kong（香港中文大学）；Shanghai Jiao Tong University（上海交通大学）
AIProver: Agentic Auto-Formalization of Mathematical Research via Certificate-Driven Evolving Harness
Georgia Institute of Technology（佐治亚理工学院）；University of Pennsylvania（宾夕法尼亚大学）；Foothill College（山麓学院）；Rutgers University（罗格斯大学）；Simon Fraser University（西蒙弗雷泽大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）
AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models
Institute of Artificial Intelligence, Beihang University（北京航空航天大学人工智能研究院）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；University of Science and Technology Beijing（北京科技大学）
Agentic Router: An Execution-Grounded Continual Learning Approach With Memory
Zhejiang University（浙江大学）；Zhejiang Lab（之江实验室）；State Grid Hebei Electric Power Co., Ltd.（国网河北省电力有限公司）；Macau University of Science and Technology（澳门科技大学）
HARBOR: A Harness Framework for Agentic Robot Reinforcement Learning
TU Darmstadt（达姆施塔特工业大学）；Honda Research Institute Europe（本田欧洲研究所）；Columbia University（哥伦比亚大学）；Tongji University（同济大学）；Shanghai Research Institute for Intelligent Autonomous Systems（上海智能自主系统研究院）；University of Würzburg（维尔茨堡大学）；Hessian.AI（黑森人工智能中心）
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
Department of Computer Science, The University of Texas at Dallas（德克萨斯大学达拉斯分校计算机科学系）；Department of Electrical and Computer Engineering, University of Florida（佛罗里达大学电气与计算机工程系）；University of California, Davis（加州大学戴维斯分校）
