Recursive Self-Improvement

Ask about this topic

Overview

Recursive self-improvement asks how AI systems can use their own experience to make future versions more capable, efficient, or safe. Approaches include revising agent prompts, tools, memory, and code; evolving training data or models; and using search, world models, or learned evaluators to guide changes. Most demonstrated progress comes from bounded tasks with external or held-out checks, such as coding, reasoning, robotics, and scientific research benchmarks. A central challenge is ensuring that gains persist beyond the feedback used to produce them, without benchmark overfitting, unsafe regressions, or goal drift.

Latest papers

CardsList

84 papers40 papers in the last four weeks, up 167% on the four weeks before. 0.2% of all new papers.

  1. Skill∞^{\infty}: Recursive Self-Improvement for Agent Skill Optimization

    Oct 26, 2026Wangcheng Tao, Zhanglu Yan, Han Wu +1LLM Agent Self-ImprovementLLM Agent Skill Learning

    National University of Singapore · City University of Hong Kong

  2. Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges

    Oct 26, 2026Jiayue Pu, Ang Gao, Jinyi Bai +9Recursive Self-ImprovementLanguage Model Self-Improvement

    Gaoling School of Artificial Intelligence, Renmin University of China · University of Chinese Academy of Sciences

  3. RSI Arena: Towards Recursive Self-Improvement with Human Feedback

    Oct 24, 2026Yue Huang, Yanbo Wang, Lichi Li +15LLM Agent Self-ImprovementLLM Agent Training

    Bake AI · University of Notre Dame · University of California, Los Angeles +8

  4. HarnessMM: Recursive Self-Improvement for Harness Token Efficiency

    Oct 23, 2026Yuhua Jiang, Chang Xu, Feifei Gao +1Agent Harness OptimizationLLM Agent Efficiency

    Tsinghua University · Microsoft Research Asia (MSRA)

  5. Evolving with Open Worlds: Towards Recursive Self-Improvement for Future Forecasting

    Oct 21, 2026Zhipeng Chen, Yunsen Liang, Yanxi Chen +12Recursive Self-ImprovementSelf-Evolving Agents

    Gaoling School of Artificial Intelligence, Renmin University of China · IQuest Research · Nanyang Technological University

  6. Toward Recursive Self-Improvement in Physical AI

    Oct 21, 2026Meng Luo, Zechen Bai, Shanqing Xu +9Recursive Self-ImprovementRobot Learning

    National University of Singapore · Huazhong University of Science and Technology · Shanghai Jiao Tong University +2

  7. RSI Control: Can AI Models Perform Covert Sabotage in the Self-Improvement Process?

    Oct 20, 2026Kaiwen Zhou, Udari Madhushani SehwagRecursive Self-ImprovementAI Control

    Preparedness and Policy, Scale AI

  8. Auditing the Product, Not the Recursion: The Evaluation Evidence Behind Recursive Self-Improvement Claims

    Oct 20, 2026Zihan Chen, Di Zhu, Lei Nico ZhengRecursive Self-ImprovementAI Agent Auditing

    Stevens Institute of Technology Hoboken, NJ, USA · University of Massachusetts Boston Boston, MA, USA

  9. Compile Once, Run Cheap: Frozen, Portable Skills for Embodied Agents, and What Recursive Self-Improvement Adds

    Oct 18, 2026Jingwen Bai, Guochao Bai, Canbo Zhang +4Robot Skill LearningLLM Agent Self-Improvement

    Beijing Ou Rui Ling Shi Technology Co., Ltd. · ChangingTek Robotics Technology (Suzhou) Co., Ltd. · Shanghai Yunfan Intelligent Control Robot Technology Co., Ltd.

  10. Learning to Compose: Recursive Self-Improvement of Shared Executable Stacks for Zero-Shot Long-Horizon Robot Manipulation

    Oct 17, 2026Yangzhi Chen, Feiran Liu, Zishuo Wang +4Robotic ManipulationRecursive Self-Improvement

    Beijing Jiaotong University · New York University · University of Southern California +2

  11. DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses

    Oct 16, 2026Jianyuan Zhong, Chenwei Wu, Zhaochen Yu +20Scientific Hypothesis GenerationAutonomous Research Agents

    PhAI Labs · The Chinese University of Hong Kong · University of Michigan +13

  12. InstAgent: A Recursively Self-Improving Agent Operating System for Heterogeneous Robot Collaboration

    Oct 16, 2026Haoyang Luo, Junhao Qin, Jingyan Cao +7Agentic AI for RoboticsMulti-Robot Systems

    ShanghaiTech University, Shanghai, China. · InstAdapt, Shanghai, China.

  13. Terminal-RSI: Recursive Self-Improving Terminal Agents via Recursive Self-Rewrite and Policy-Refine

    Oct 15, 2026Junyao Yang, Zongxia Li, Yucheng Shi +6Terminal AgentsRecursive Self-Improvement

  14. The Self-Improvement Problem

    Oct 15, 2026Brian B. Moser, Stanislav Frolov, Tobias C. Nauen +2Self-Improving AgentsRecursive Self-Improvement

    German Research Center for Artificial Intelligence (DFKI) · RPTU Kaiserslautern-Landau

  15. Recursive Reward Improvement via Adversarial Meta-Prompt Evolution

    Oct 15, 2026Wei Dai, Qianchu Liu, Guanghui Qin +4Recursive Self-ImprovementRubric-Based RL

    Massachusetts Institute of Technology · Microsoft Research · Johns Hopkins University

  16. SwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm

    Oct 14, 2026Qianru Meng, Xi Zhang, Konstantinos Papakostas +9AI Agents for Scientific DiscoveryRecursive Self-Improvement

    Huawei Technologies Co., Ltd. · Leiden University · University of Groningen

  17. MMLA-RSI: Recursive Self-Improvement through RTT and RTMA

    Oct 14, 2026Junyi Zou, Avrova DonzSelf-Improving AgentsRecursive Self-Improvement

    MMLA-org · Communication University of China (CUC), No. 1 Dingfuzhuang East Street, Chaoyang District, Beijing 100024, China

  18. VideoHarness-SRSI: Structured Recursive Self-Improvement for Video Understanding Harness

    Oct 14, 2026Zihao Lin, Haoyu Dong, Haobo Xu +10LLM Agent HarnessesRecursive Self-Improvement

    University of California, Davis · Meta MRS Research · Duke University +3

  19. The Last Remote Sensing Model Built by Humans? Casting Any Earth Observation Task as Recursive Self-Improvement

    Oct 13, 2026Sijie Zhao, Zeqi Zhou, Heli Qi +6Remote SensingRecursive Self-Improvement

    The University of Tokyo · RIKEN · Stanford University

  20. Who Improves the Robot? Toward Physical Recursive Self-Improvement

    Oct 13, 2026Hai Zhou, Fan Yang, Zeyi Chen +27Recursive Self-ImprovementContinual Robot Learning

    Shanghai Jiao Tong University · Google · Microsoft +13

  21. AReaL-RSI: Adaptive Scaling and Coordination of Recursive Self-Improvement

    Oct 13, 2026Wenhao Zhou, Jiajun Song, Haitao Wang +11Self-Improving AgentsRecursive Self-Improvement

    Ant Group · Zhejiang University · HKUST

  22. Drafting Agents, Not Just Tokens: Speculative Recursive Self-Improvement for Agentic Systems

    Oct 12, 2026Xin Xu, Ke Cheng, Hao Wang +11LLM Agent Self-ImprovementRecursive Self-Improvement

    Tencent AMS, Beijing, China · State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China · CCSE lab, Beihang University. +3

  23. SpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specifications

    Oct 11, 2026Yutong Cheng, Haifeng Chen, Peng Gao +1Software Engineering AgentsAgentic Code Generation

    Virginia Tech · NEC Laboratories America

  24. Pre-Registered Genesis Accounting for Recursive Self-Improvement: First Audited Operator-Genesis Events in a Physics-Discovery Runtime

    Oct 10, 2026Wenbin Mao, Pei ZouRecursive Self-ImprovementAutonomous Scientific Discovery

    HoomanBio AI Lab, Huaman Biotechnology (Beijing) Co., Ltd.

  25. EvoCowork: A Benchmark for Real-World Office Tasks

    Oct 10, 2026Zhou Liu, Xingyan Chen, ZhaoYang Han +6Computer-Use Agent BenchmarksAI Agent Benchmarks

    Peking University · Sun Yat-sen University · Shanghai Jiao Tong University +3

  26. From Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvement

    Oct 10, 2026Leijun Zhou, Yanke Yu, Zhihao Liu +10Recursive Self-ImprovementLLM Agent Self-Improvement

    PrismShadow · Peking University · Zhejiang University +1

  27. RSI-Anything: Unlocking Recursive Self-Improvement with World Models

    Oct 9, 2026Taoyong Cui, Pinxian Zeng, Wanghan Xu +8Recursive Self-ImprovementSelf-Improving Agents

  28. ReSI: Recursive Safety Improvement toward Resistant and Resilient AI

    Oct 8, 2026Jingnan Zheng, Dongcheng Zhang, Yi Zhang +10LLM Safety AlignmentRecursive Self-Improvement

    Shanghai AI Laboratory · National University of Singapore · Shanghai Jiao Tong University +2

  29. Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks

    Oct 8, 2026Haoyu Zhao, Zhengxu Yu, Zhiyuan He +5Continual Learning for LLM AgentsRecursive Self-Improvement

    University College London · Huawei Noah’s Ark Lab, UK · University of Liverpool

  30. RSIGym: A Flexible Environment for Recursive Self-Improvement

    Oct 7, 2026Fanqing Meng, Lingxiao Du, Haocheng Lu +6LLM Agent Self-ImprovementRecursive Self-Improvement

    Evolvent AI · National University of Singapore