Language Model Self-Improvement

Overview

The field studies how language models can improve their reasoning, instruction following, coding, and other skills by learning from their own attempts and interactions. Common approaches include self-training and self-distillation on generated responses, reinforcement learning and challenger–solver self-play, and test-time adaptation through memory, skills, or evolving prompts. Feedback ranges from exact checks such as code execution and formal proof to model-generated critiques, preferences, and confidence signals, with evaluation spanning math and coding benchmarks as well as agent and multimodal tasks. The central tension is whether these internal signals are reliable enough to produce transferable gains: noisy feedback, narrow curricula, and repeated selection can cause regressions or collapse, while oracle-supervised performance often remains difficult to match.

Latest papers

CardsList

195 papers22 papers in the last four weeks, down 21% on the four weeks before. 0.2% of all new papers.

  1. AutoMaster: Autonomous Post-Training by Making the Same Model a Better Teacher

    Nov 19, 2026Guoxin Chen, Shuang Sun, Fanzhe Meng +3LLM Post-TrainingLanguage Model Self-Improvement

  2. Learning through Discernment: when a small language model learns from user feedback on the job, and when it decays

    Nov 18, 2026Sirisilp KongsilpLanguage Model Self-ImprovementOnline Language Model Adaptation

  3. RSI-Prime: Training Models to Train Models

    Nov 17, 2026Dewu Zheng, Yang Ye, Hongyu Zhang +2Language Model Self-ImprovementLLM Post-Training

  4. Language Models Can Rewrite Their Own Weights

    Nov 16, 2026Jiajun Fan, Neil He, Changyi Yang +8Language Model Self-ImprovementLanguage Model Editing

  5. TrainExplorer: Autonomous LLM Post-Training via Plan-and-Decouple Exploration

    Nov 16, 2026Xuannan Liu, Tian Lan, Zekun Li +9LLM Post-TrainingLanguage Model Post-Training

  6. Third Eye: Beyond Immediate Gains in Recursive Self-Improvement

    Nov 8, 2026Sujato Dutta, Padala Indira Sneha, Kypu Mahitha +2Language Model Self-ImprovementRecursive Self-Improvement

  7. Toward LLM Self-Play Under Data Scarcity: Effectiveness, Generalizability, and Trustworthiness

    Nov 6, 2026Zhiyin Yu, Yuchen Mou, Bingzhe Wu +3Self-Play for Language ModelsLanguage Model Self-Improvement

  8. WeightLoop: Weight-Space Programming with Experimental Feedback

    Nov 5, 2026Mengran Li, Bo Li, Weijing Zhao +6Weight-Space ProgrammingLanguage Model Self-Improvement

  9. PRIME: Predictive Routing of Interventions by Modeling Effects for Scientific Ideation

    Nov 2, 2026Fengxian Ji, Xie Yu, Zhexuan Cui +8Large Language Model-Guided Scientific DiscoveryLanguage Model Self-Improvement

  10. Compositional Self-Improvement: Promises and Pitfalls

    Oct 30, 2026Changho Shin, Daiwei Chen, Brenden Lake +2Language Model Self-ImprovementSelf-Training for Language Models

  11. Safin-1.5: Safety-Native Architecture and Verifiable Reasoning for Recursive Safety Improvement

    Oct 29, 2026Jingnan Zheng, Cheng Jin, Ming Zhang +28LLM SafetyLanguage Model Self-Improvement

  12. Incentivizing Self-Learning in Large Language Models via Reinforcement Learning

    Oct 29, 2026Lingkai Kong, Yuzhe Gu, Haiteng Zhao +6Language Model Self-ImprovementRL for Language Model Reasoning

  13. 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

  14. Self-Evolution Reasoner: Continuous Optimization via Policy-Intrinsic Exploration and Exploitation

    Oct 25, 2026Wenhang Shi, Yiren Chen, Zhe Zhao +3Language Model Self-ImprovementRL for Language Model Reasoning

  15. Recursive Code Evolution for Task-Oriented Semantic Communications

    Oct 21, 2026Yan Gong, Zheng Chu, Wei Koong Chai +5Semantic CommunicationLarge Language Model-Guided Optimization

  16. MaD-RSI: Model-as-Data for Recursive Self-Improvement of Agent Harnesses

    Oct 20, 2026Yu Cui, Hong He, Ruiqing Yue +8Agent Harness OptimizationLLM Agent Harnesses

  17. Language Models Learn to Improve Language Models

    Oct 16, 2026Minhua Lin, Zijun Wang, Zewen Liu +7Language Model Self-ImprovementLarge Language Model-Guided Optimization

  18. Selection Is Not Learning: Choosing Model Futures

    Oct 15, 2026Haoyi Yang, Kshitij Mishra, Nils Lukas +1Language Model Self-ImprovementSelf-Training for Language Models