phenomenon · first seen 6 Oct 2026
self-improving agents
Agents that iteratively generate and verify solutions to improve their own performance on tasks.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Learning from Revision Consequences: Hindsight Meta-Experience Distillation for Self-Improving AgentsPapers · 6 Oct 2026 · Qianhan Feng, Zhongzhen Huang, Yakun Zhu, Xiaofan Zhang, Qi Dou
- Verification and Self-Improvement in Agentic AI: Foundations and LimitsPapers · 7 Oct 2026 · Chien-Ping Lu
- zjunlp/HarnessGradCode · 8 Oct 2026 · zjunlp · 26 stars
- VETR: Execution-Grounded Self-Improving Agent for Symbolic Graphics ReasoningPapers · 9 Oct 2026 · Yingbo Ma, Kuangshi Ai, Gordon Dai, Chenglong Yu, Chaoli Wang, Hua Shen
- ClawLoop: Self-Improving Agents via Harness-Native Training LoopPapers · 9 Oct 2026 · Hansi Yang, Linji Hao, Hongyan Hao, An Wang, Han Wu, Qi Gu, Xunliang Cai
- Does Failure Feedback Direct Agent Self-Modification?Papers · 10 Oct 2026 · Rong He
Latest sources
- Experience-Handoff Reinforcement Learning for Recursive Self-ImprovementPapers · 12 Nov 2026 · Doyoung Kim, Byeongguk Jeon, Kailin Zhang, Sherry Yang
- RSI-PDEbench: A Benchmark for Self-Improving Agents in PDE SolvingPapers · 11 Nov 2026 · Binghang Lu, Lang Cao, Changhong Mou, Yige Sun, Cindy Xiangrui Kong, Zheyuan Den…
- Exo: An Architecture for Self-Improving Systems at RuntimePapers · 30 Oct 2026 · Alexander Krentsel, Sylvia Ratnasamy, Ion Stoica, Martin Casado, Ankur Goyal
- Masked Erosion: How Acceptance Gates Lose Redundant Safeguards in Self-Improving AgentsPapers · 28 Oct 2026 · Hau-Sing So, Daixian Liu, Weicai Long
- Infinity Machine: a self-improving AI agent for researchPapers · 26 Oct 2026 · Harish Santhanalakshmi Ganesan
- ChartEvo: Self-Evolving Agent Harnesses for Long-Tail Chart ReasoningPapers · 20 Oct 2026 · Qi Wang, Peijie Wang, Jun Cao, Haoyang Tong, Xiao-Hui Li, Fei Yin, Cheng-Lin Liu
- Learning What to Remember: Resource-Efficient Self-Improvement for Lifelong AgentsPapers · 19 Oct 2026 · Guannan Lai, Zi-Yang Bai, Jun-Peng Jiang, Han-Jia Ye
- TimeRSI: Towards Self-Improved Agentic Deployment for Time-Series Foundation ModelsPapers · 14 Oct 2026 · Haoxin Liu, Deqing Fu, Lucheng Fu, Yiqiao Jin, Rushi Qiang, Harshavardhan Kamart…
- L3M: A Verifiable Harness and Runtime for Self-Extending and Self-Improving AgentsPapers · 14 Oct 2026 · Carson Eisenach, Robert Joseph George, Vincent Quenneville-Belair, Kate Gwimm, D…
- Lessons from Luck: Do LLM-Written Lessons Carry Chance into an Agent's Next Decision?Papers · 12 Oct 2026 · Kazuki Nakayashiki
- Does Failure Feedback Direct Agent Self-Modification?Papers · 10 Oct 2026 · Rong He
- ClawLoop: Self-Improving Agents via Harness-Native Training LoopPapers · 9 Oct 2026 · Hansi Yang, Linji Hao, Hongyan Hao, An Wang, Han Wu, Qi Gu, Xunliang Cai