| 1 | RSI-Anything: Unlocking Recursive Self-Improvement with World Models | Taoyong Cui, Pinxian Zeng, Wanghan Xu +8 | cs.CL | 2026-10-09 |
| 2 | X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems | Yeonsung Jung, Zhiyuan Wang, Zifan Wang +5 | cs.AI | 2026-10-09 |
| 3 | MC-EvoBench: Auditing Experience-Driven Self-Improvement in Minecraft Agents | Jingwei Song, Zhisheng Chen, Bingfan Zeng +5 | cs.RO | 2026-10-09 |
| #4 | VETR: Execution-Grounded Self-Improving Agent for Symbolic Graphics Reasoning | Yingbo Ma, Kuangshi Ai, Gordon Dai +3 | cs.AI | 2026-10-09 |
| #5 | Mitigating Capability Degradation in LLM Self-Improvement via Representation Geometry Regularization | Jiaqi Tian, Ting Long | cs.AI | 2026-10-09 |
| #6 | RoboRSI: Stable, efficient, and reusable robot self-evolution in complex real-world environments | Zimo Wen, Yijin Chen, Yuxuan Cao +8 | cs.RO | 2026-10-08 |
| #7 | Embodied Turing Machines: Stateful Code for Robot Recursive Self-Improvement | Kairui Hu, Siyuan Hu, Fangzhou Hong +2 | cs.RO | 2026-10-08 |
| #8 | Language Models as AI Research World Models | Zijun Wang, Zewen Liu, Minhua Lin +10 | cs.CL | 2026-10-08 |
| #9 | ReSI: Recursive Safety Improvement toward Resistant and Resilient AI | Jingnan Zheng, Dongcheng Zhang, Yi Zhang +10 | cs.CR | 2026-10-08 |
| #10 | DataSense-Bench: The First Step Toward an AI Scientist | Yudi Zhang, Mingyu Cao, Lu Yin +2 | cs.LG | 2026-10-08 |
| #11 | Recursive Self-Improvement through Multi-Agent Self-Supervision | Hyunin Lee, Jinglue Xu, Jeffrey Seely +4 | cs.AI | 2026-10-08 |
| #12 | Learning to Plan by Looking Back: Hindsight Hierarchies for Training Reasoning Models | Lars Simon, Holger Eble, Manuel Radons | cs.AI | 2026-10-08 |
| #13 | Agentic-TTT: Training test-time policy for test-time training | Jiahao Lu, Mohan Kankanhalli | cs.LG | 2026-10-08 |
| #14 | MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement | Xiaomi LLM-Core Team, :, Zongming Qiao +147 | cs.CL | 2026-10-08 |
| #15 | Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks | Haoyu Zhao, Zhengxu Yu, Zhiyuan He +5 | cs.AI | 2026-10-08 |
| #16 | SynCo: Data Synthesis Co-Training for Self-Evolving LLMs via Multi-Agent Reinforcement Learning | Wei Yang, Shawn Li, Yuehan Qin +8 | cs.AI | 2026-10-08 |
| #17 | RSIGym: A Flexible Environment for Recursive Self-Improvement | Fanqing Meng, Lingxiao Du, Haocheng Lu +6 | cs.LG | 2026-10-07 |
| #18 | Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language Models | Yi Wang, Rui Qian, Yu Li +2 | cs.LG | 2026-10-07 |
| #19 | Verification and Self-Improvement in Agentic AI: Foundations and Limits | Chien-Ping Lu | cs.AI | 2026-10-07 |
| #20 | RSI-Forge: From Research Papers to Environments for Recursive Self-Improvement | Renxiong Wang, Darvin Yi, Abril Herrlein +16 | cs.AI | 2026-10-07 |
| #21 | The Winner's Curse in LLM Self-Improvement Loops: Selection Noise, Lock-in, and Acceptance Rules | Litao Hu, Yutong Tang | cs.AI | 2026-10-07 |
| #22 | PhysEvo: Astra Can Act, Let It | Wenqing Tian, Zeyu Zhang, Zhaocheng Liu +3 | cs.RO | 2026-10-06 |
| #23 | Agent Plasticity: Measuring Self-Improvement Through Experience | Harman Singh, Anton Bakhtin, Rulin Shao +8 | cs.AI | 2026-10-06 |
| #24 | VeriFine: Scaling Verification for Self-Improvement in Embodied Reasoning | Zewei Zhou, Rachel Luo, Yulong Cao +10 | cs.AI | 2026-10-06 |
| #25 | Towards In-Parameter Memory Augmentation for Large Language Models | Haoyu Huang, Zhongwei Xie, Jiaxin Bai +6 | cs.CL | 2026-10-06 |
| #26 | EmbodiedSmith: Scaling Embodied Data through Recursive Self-Improvement Flywheel in Simulation | Yikai Qin, Yifei Deng, Mingjian Liang +13 | cs.CV | 2026-10-06 |
| #27 | SIGMA: Self-Improving Alignment Generalization from a Model Spec | Jingyu Zhang, Shruti Palaskar, Daniel Khashabi +3 | cs.AI | 2026-10-06 |
| #28 | Selective Critique for Cost-Aware LLM Agents in Long-Horizon Decision Making | Heewon Park, Somin Im, Minhae Kwon | cs.LG | 2026-10-05 |
| #29 | SPECTRUM: Proximal Spectral Modulation for Looped Self-Distillation | Yunbo Long, WenJie Chen, Jiaquan Zhang +4 | cs.AI | 2026-10-05 |
| #30 | Beyond Successor Accuracy: State Retention for Recursive Self-Improvement in Recommendation | Jinfeng Xu, Zheyu Chen, Ziyue Peng +5 | cs.IR | 2026-10-05 |
| #31 | ImproveAnyTask: An Autonomous Post-Training Harness for Iterative Model Self-Improvement | Xingbo Yao, Xiaoman Wang, Zhengwu Lei +11 | cs.AI | 2026-10-05 |
| #32 | Off-Policy Merging Beats On-Policy Self-Distillation for Continual Learning | Chen Henry Wu, Thomas Zhang, Aditi Raghunathan | cs.LG | 2026-10-05 |
| #33 | Second-Order Problem Solving for Recursive Self-Improvement in Formal Verification | Yuxuan Jiang, Aditya Vempaty, Ashish Jagmohan | cs.AI | 2026-10-05 |
| #34 | FLEX-WAM: Flexible Block-Causal World-Action Models for Long-Horizon Imagination and Planning | R. Khorrambakht, Joseph Amigo, Félix Lebel +4 | cs.RO | 2026-10-04 |
| #35 | Assembling Insights for Agentic Machine Learning Engineering Systems | Bihui Jin, Yinxi Li, Kaiyuan Wang +1 | cs.SE | 2026-10-04 |
| #36 | Trinity: Self-Evolving Vision-Language Models with a Self-Verifier | Youngwan Lee, Yong-Ju Lee, Sung Ju Hwang | cs.AI | 2026-10-03 |
| #37 | What to Preserve in Recursive Computation: A Local Predictive Sufficiency Principle | Peilin Wang, Feng Shiyang, Hongfu Gao +4 | cs.LG | 2026-10-03 |
| #38 | EvalResearchBench: Can AI Agents Design Their Own Evaluations? | Yaolun Zhang, Tianyi Xu, Yujie Zhao +3 | cs.AI | 2026-10-03 |
| #39 | Recursive Harness Self-Improvement for Frontier Reasoning Data Synthesis | Wenlong Zhang, Zhengbo Jiao, Chenxu Zhang +5 | cs.AI | 2026-10-02 |
| #40 | MobiAgent: Dual-Loop Recursive Policy Self-Improvement for Long-Horizon Mobile Manipulation | Chenzhi Liu, Yue Zhang, Jiehong Lin +4 | cs.RO | 2026-10-02 |
| #41 | Recursive Self-Improvement in Unified Multimodal Models | Huijuan Wang, Chufan Shi, Cheng Yang +3 | cs.CL | 2026-10-02 |
| #42 | Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents | Yen-Jen Wang, Haozhe Jiang, Shuying Deng +7 | cs.RO | 2026-10-01 |
| #43 | Mimir: Physics-Grounded LLM Agents for Long-Horizon Irrigation Control | Yimeng Liu, Mi Zhang, Younsuk Dong +1 | cs.AI | 2026-10-01 |
| #44 | ReSAIL: Mitigating Collapse in Iterative Agent Self-Distillation | Shengjie Jin, Hengbo Xu, Zelong Sun +2 | cs.LG | 2026-09-30 |
| #45 | Rep2Skill: Representation-Guided Skill Self-Evolution for LLM Agents | Kaixing Zhang, Changming Li, Yingdong Shi +5 | cs.AI | 2026-09-30 |
| #46 | RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement | Wenyi Wu, Minghao Fu, Jieyu You +10 | cs.CL | 2026-09-30 |
| #47 | UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement | Fang Wu, Da Xing, Yanjie Huang +16 | cs.AI | 2026-09-30 |
| #48 | CollabFlow: Recursive Self-Improvement of Agent Collaboration | Xiao Huang, Mingda Zhang, Junming Zhang +5 | cs.MA | 2026-09-29 |
| #49 | From Solo to Social Learning: Characterizing Recursive Social Improvement in LLMs | Kunal Jha, Max Kleiman-Weiner, Natasha Jaques | cs.MA | 2026-09-29 |
| #50 | Self-Evolving Harness on Multiple Tasks with the Agent as Its Own Optimizer | Qiankai Xu | cs.AI | 2026-09-29 |