Recursive Self-Improvement

Ask about this topic

Momentum

31 papers in the last four weeks, up 94% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 101

All topics
CardsList

  1. Second-Order Problem Solving for Recursive Self-Improvement in Formal Verification

    Oct 5, 2026Yuxuan Jiang, Aditya Vempaty, Ashish JagmohanRecursive Self-ImprovementFormal Verification

    University of Maryland, Baltimore County · Emergence AI

  2. Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents

    Oct 1, 2026Yen-Jen Wang, Haozhe Jiang, Shuying Deng +7Robot AutonomyEmbodied Agents

    UC Berkeley · Amazon FAR · MIT +1

  3. ReSAIL: Mitigating Collapse in Iterative Agent Self-Distillation

    Sep 30, 2026Shengjie Jin, Hengbo Xu, Zelong Sun +2Self-Improving AgentsRecursive Self-Improvement

    Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China

  4. Rep2Skill: Representation-Guided Skill Self-Evolution for LLM Agents

    Sep 30, 2026Kaixing Zhang, Changming Li, Yingdong Shi +5Skill EvolutionSelf-Evolution

    ShanghaiTech University · Meituan

  5. RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement

    Sep 30, 2026Wenyi Wu, Minghao Fu, Jieyu You +10Self-Improving AgentsRecursive Self-Improvement

    University of California San Diego · ByteDance Inc. · Carnegie Mellon University

  6. EmbodiRSI: Recursive Self-Improvement for Data-Efficient Robot Adaptation

    Sep 30, 2026Haoran Lang, Haotao Lu, Shiyu Sang +6Scalable Robot LearningRobotic Manipulation Policies

    InstAdapt · ShanghaiTech University

  7. CollabFlow: Recursive Self-Improvement of Agent Collaboration

    Sep 29, 2026Xiao Huang, Mingda Zhang, Junming Zhang +5CollaborationRecursive Self-Improvement

    The Chinese University of Hong Kong, Shenzhen · Fudan University · University of Oxford

  8. Video-RSI: Recursive Self-Improvement of Video Understanding Agents via Harness Evolution

    Sep 29, 2026Bingjun Luo, Jialin Guo, Siqi LiVideo AgentVideo Understanding

    Tsinghua University · Harbin Engineering University

  9. Mixture of Self-Improving Branches For Agent Harness Optimization

    Sep 29, 2026Haoyu Dong, Yuhang Zhou, Zihao Lin +6Evolving HarnessRecursive Self-Improvement

    Meta · Duke University · Work done while at Meta. +1

  10. RLTL;DR: Self-improvement by Internalizing Self-generated Feedback

    Sep 29, 2026Michael Kirchhof, Eleonora Gualdoni, Andrew Szot +6Reinforcement Learning With Verifiable RewardRecursive Self-Improvement

    Apple

  11. In-Context Learning for Robots: Methods and Applications

    Sep 28, 2026Haojian Huang, Zexi Li, Junhao Guo +36In-Context LearningRobot Systems

    Knowin AI · HKUST(GZ) · The Chinese University of Hong Kong +5

  12. RSI-Master: Structuring Experiments to Guide Autonomous Model Improvement

    Sep 28, 2026Yaxin Du, Xiyuan Yang, Zhifan Zhou +10Recursive Self-ImprovementArtificial Intelligence Research

    Shanghai Jiao Tong University · Carnegie Mellon University · University of Waterloo

  13. Sol-H3: Recursive Self-Improvement for MiniMax-H3 Inference Acceleration on Sol-Engine across Cloud and Edge

    Sep 28, 2026Yitong Li, Jincheng Yu, Junsong Chen +6Edge DevicesCloud

    NVIDIA Research, Efficient AI Team & Singapore Lab.

  14. AutoDataBench: Can Agents Write the Data That Feeds the Self-Improvement Loop?

    Sep 28, 2026Haotian Luo, Haoyu Wang, Zeyu Qin +5Data Science AgentsAgentic Benchmarks

    HKUST · SLAI · NTU

  15. Audit the Scaffold, Not the Checkpoint: A Stationarity Dichotomy for Recursive Self-Improvement in Agentic Coding

    Sep 28, 2026Sebastian Bobadilla-Suarez, Bob Suh, Ryan FortinScaffoldsCoding Agents

    OnCorps

  16. R2^2 Flow: Recursive Self-Improvement via Recursive Skill Evolution

    Sep 27, 2026Mingda Zhang, Qiang Huang, Yanjin Li +4Skill EvolutionRecursive Self-Improvement

    The Chinese University of Hong Kong, Shenzhen · Fudan University · University of Illinois at Urbana-Champaign +2

  17. COEVO: Co-Evolving Context and Parameters for Recursive Self-Improvement

    Sep 27, 2026Siwei Chen, Xinping Bao, Xinyu Cai +3On-Policy Self-EvolutionRecursive Self-Improvement

    Peking University · Emotional Machine

  18. Which Self-Improvements Should We Trust? Reliable Self-Improvement When Agents Reuse Their Benchmarks

    Sep 27, 2026Xiaojing Sun, Yuhan Zeng, Zihua She +1Recursive Self-ImprovementAI Trustworthiness

    Purdue University

  19. Breaking the Environment Wall: A Unified Framework for Preparing and Evolving Agent-Native Environments

    Sep 24, 2026Yukai Wu, Yuanjing Yang, Le Zhou +8Self-Improving AgentsLarge Language Model Agents

    Shanghai Jiao Tong University · Theseus Labs · Tencent Hunyuan

  20. EvoAudio: Recursive Self-Improvement for Audio Understanding

    Sep 23, 2026Yuxiang Wang, Shengbo Cai, Yingda Shen +6Audio UnderstandingAudio Understanding

    The Chinese University of Hong Kong, Shenzhen · Tencent Hunyuan · Tsinghua University +1

  21. Recursive self-improvement of AI research agents

    Sep 22, 2026Dhruv Srikanth, Bingchen Zhao, Dixing Xu +2Self-Improving AgentsRecursive Self-Improvement

    Weco AI

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

    Sep 21, 2026Peng Xia, Rujun Han, Zifeng Wang +11Self-Improving AgentsRecursive Self-Improvement

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

  23. DENSE: Distilling Agent Trajectories into Evidence-Grounded Shortcut Trees for Self-Refinement

    Sep 18, 2026Siyuan Liu, Fan Yu, Dongyu Ru +5Self-Improving AgentsRetrying

    Fudan University · Meituan Longcat Team

  24. FINSKILLOPS: A Self-Evolving Multi-Agent System for SEC Filing QA

    Sep 17, 2026Yanzhang Ma, Zhenghan Tai, Hanwei Wu +25Financial Question AnsweringRecursive Self-Improvement

    University of Toronto · McMaster University · University of California, Los Angeles +11

  25. VideoResearcher: Self-Improving Tool Design for Long-Video Understanding

    Sep 17, 2026Dingqiang Ye, Dongdi Zhao, Kaishen Wang +11Video AgentVideo Understanding

    Johns Hopkins University

  26. Self Improvement via Fast Tree-search

    Sep 17, 2026Xinghong Fu, Aravinth Kulanthaivelu, Yutaro YamadaRecursive Self-ImprovementTree Search

    Massachusetts Institute of Technology · Sakana AI

  27. ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents

    Sep 15, 2026Shuhan Xue, Jianyuan Zhong, Ziyuan Nan +10Scientific AgentsRecursive Self-Improvement

  28. RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments

    Sep 14, 2026Sibo Zhu, Shicheng Fan, Xinyue Wang +3Self-Improving AgentsMixture-Of-Agents

    Aether AI · University of California San Diego · ‡Work done during internship in Aether AI +1

  29. Dream-RSI: Recursive Self-Improvement through Evolving Worlds

    Sep 14, 2026Tong Zheng, Xidong Wu, Zheng Zhang +14Stochastic ExplorationSelf-Improving Agents

    Google · University of Maryland, College Park · Google Deepmind +1

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

    Sep 14, 2026Siwei Wu, Jincheng Ren, Yizhi Li +11Evolving HarnessSelf-Improving Agents

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

  31. The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement

    Sep 10, 2026Yi Duan, Ying Liu, Zirui Tang +32Recursive Self-ImprovementArtificial Intelligence Systems

    Shanghai Jiao Tong University · Theseus Labs · Agent-Native Research Lab +6

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

    Sep 8, 2026NeoHorse Team, Guoliang Cao, Guohao Dai +34Self-Improving AgentsReinforcement Learning Post-Training

    TokenRhythm

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

    Sep 6, 2026Zihan Tan, Leixin Sun, Zitong Shi +28Recursive Self-ImprovementRecursive Models

    Hugging Face

  34. FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience

    Sep 3, 2026Zixun Huang, Kishan Panaganti, Haitao Mi +1Reinforcement Learning With Verifiable RewardReasoning Trajectory

    Tencent HY LLM Frontier · University of Pennsylvania

  35. Cheap Verifiers, Large Blind Spots: Measuring the Reliability Cost of Cost-Saving Cascades

    Sep 1, 2026Dushyant RajputVerification FrameworkEqual Error Rate

    AltSlate Labs LLP

  36. A Survey on Self-Improving Test-Time Intelligence: Feedback-Driven Adapting, Learning, and Scaling at Inference

    Sep 1, 2026Shuaicheng Niu, Guohao Chen, Yaofo Chen +14Test-Time AdaptationTest-Time Training

    South China University of Technology · Nanyang Technological University · Tulane University +3

  37. Recursive Criticality of AI Self-Improvement

    Aug 31, 2026Mikhail BurtsevRecursive Self-ImprovementArtificial Intelligence Research

    London Institute for Mathematical Sciences

  38. S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?

    Aug 31, 2026Jiajun Shi, Siyuan Tao, Yuhao Wu +18Self-Improving AgentsRecursive Self-Improvement

    ByteDance Seed

  39. Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement

    Aug 31, 2026Yi Ding, Ruqi ZhangOnline-Policy DistillationTeacher

    Department of Computer Science, Purdue University, USA

  40. WebWorld: The Browser as a World Model for Self-Improving Web Code

    Aug 31, 2026Jiajun Wu, Jian Yang, Yaxin Du +7WebBrowser Agent

    Beihang University · Shanghai Jiao Tong University · IQuest Research +1

  41. SIR: Self-improving Red-teaming for Compute Use Agents

    Aug 31, 2026Chen Xiong, Zhiyuan He, Pin-Yu Chen +2Indirect Prompt InjectionRed-Teaming

    The Chinese University of Hong Kong · IBM Research · University of Zagreb, FER & Radboud University +1

  42. DataFoundry: Evolving Data Preparators via Recursive Self-Improvement

    Aug 30, 2026Cehao Yang, Xiaojun Wu, Xueyuan Lin +4PreprocessingLarge Databases

    1IDEA Research, International Digital Economy Academy · 2Hong Kong University of Science and Technology (Guangzhou) · 3DataArc Tech Ltd.

  43. VideoHarness-RSI: Recursive Harness Self-Improvement for Long-Video Understanding with Frozen Vision-Language Models

    Aug 25, 2026Guoyang Xu, Hao ChenVideo UnderstandingFrozen Vision-Language Models

    Tencent

  44. What is Missing from AI Post-Training AI: An Empirical Analysis

    Aug 19, 2026Joy Jia Yin Lim, Xin Huang, Hao Peng +5Large Language Model AgentsPost-Training

    Tsinghua University · University of Electronic Science and Technology of China · Renmin University of China

  45. AQuA: Recursively Self-Improving Quantitative Trading Research Agents

    Aug 13, 2026Jiacheng Guo, Suozhi Huang, Yunlong Gao +5Algorithmic TradingRecursive Self-Improvement

    Princeton University · Ant Group · Stanford University

  46. DIVE: Unlocking Self-Improvement in Frozen Language Models Through Diversity-Driven Skill Evolution

    Aug 12, 2026Siheng Xiong, Ali Payani, Oguzhan Gungordu +1Self-Evolving Skill LibrariesFrozen Language Model

    Georgia Institute of Technology · Cisco Research

  47. SBCO: Self-Supervised, Verifier-Grounded Harness Optimization For Planning Agents

    Aug 10, 2026Vivek Kulkarni, Sudipta Paul, Aounon Kumar +2Self-Improving AgentsRecursive Self-Improvement

    Samsung Research America

  48. Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

    Aug 10, 2026Mind Lab, :, Vin Bo +74Replay-Based Continual LearningMixture-Of-Agents

  49. Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent Harnesses

    Aug 9, 2026Tailin ZhouEvolving HarnessLarge Language Model Agents

    HKUST

  50. EvolveNet: Collaborative Harness Evolution for Agent Self-Improvement

    Aug 5, 2026Jun Nie, Yonggang Zhang, Qianshu Cai +3Evolving HarnessRecursive Self-Improvement

    Hong Kong Baptist University · The Hong Kong University of Science and Technology · University of Science and Technology of China

  51. PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents

    Aug 4, 2026Shuhan Xue, Zixin Ding, Yichen Shen +6Self-Improving AgentsRecursive Self-Improvement

  52. Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering

    Jul 30, 2026Junlin Yang, Che Jiang, Yu Fu +21Mle-Bench LiteRecursive Self-Improvement

    Horizon Research, Frontis.AI

  53. Rehearse: Stepping Back from the Confidence Cliff in Self-Improving Autoresearch

    Jul 30, 2026Jiazhen Ji, Shouhong DingRecursive Self-ImprovementSelf-Evaluation

    Tencent

  54. RSIBench-Data: Benchmarking Data-Centric Research for Recursive Self-Improvement

    Jul 28, 2026Fanqing Meng, Lingxiao Du, Qiguang Chen +4Recursive Self-ImprovementAgentic Benchmarks

    1Evolvent AI · 2National University of Singapore

  55. From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement

    Jul 26, 2026Qinsi Wang, Jing Shi, Huazheng Wang +8Reinforcement Learning With Verifiable RewardVerifiable Rewards

    Duke University · Adobe Inc. · Oregon State University +3

  56. AREX: Towards a Recursively Self-Improving Agent for Deep Research

    Jul 23, 2026Shuqi Lu, Chaofan Li, Kun Luo +21Self-Improving AgentsDeep Research

    Beijing Academy of Artificial Intelligence (BAAI)

  57. Knowledge-Centric Self-Improvement

    Jul 21, 2026Xuefei Julie Wang, Lauren Hyoseo Yoon, Chengrui Qu +4Self-Improving AgentsRecursive Self-Improvement

    Caltech

  58. A Classifier That Teaches Itself: Self-Improving, Frozen-gate Training (SIFT) for Dynamic Document Classification

    Jul 20, 2026Bogdan Raduta, Horia Velicu, Alexandru Preda +1ClassifierRecursive Self-Improvement

  59. Recursive Harness Self-Improvement

    Jul 17, 2026Hyunin Lee, Jinglue Xu, Jeffrey Seely +3Evolving HarnessRecursive Self-Improvement

    1Sakana AI, 2UC Berkeley

  60. Self-Improving is Often Sudden: Enlightenment-style Finetuning for Large-Scale Models

    Jul 15, 2026Jing-Xiao Liao, Tianwei Zhang, Yu-Hao Jiang +3Parameter-Efficient Fine-Tuning MethodsModel Size

    Frontier of Artificial Network Lab, Department of Data Science, City University of Hong Kong, Hong Kong SAR, China · The Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen, China, The Chinese University of Hong Kong-Shenzhen, Shenzhen, China · School of Computer Science and Artificial Intelligence, Guangdong University of Education, Guangzhou 510303, China +1