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. Evolutionary System Prompt Learning for Reinforcement Learning in LLMs

    Feb 16, 2026Lunjun Zhang, Ryan Chen, Bradly C. StadieLanguage Model Self-ImprovementRL for Language Models

  2. TTSR: Test-Time Self-Evolving via Reflection

    Feb 6, 2026Haoyang He, Zihua Rong, Yunjia Zhao +3LLM Self-RefinementTest-Time Optimization

  3. Position: Agentic Evolution is the Path to Evolving LLMs

    Jan 30, 2026Minhua Lin, Hanqing Lu, Zhan Shi +12Online Language Model AdaptationLanguage Model Self-Improvement

  4. TTCS: Test-Time Curriculum Synthesis for Self-Evolving

    Jan 30, 2026Chengyi Yang, Zhishang Xiang, Yunbo Tang +5Test-Time TrainingLanguage Model Self-Improvement

  5. Self-Improving Training & Thinking

    Jan 29, 2026Ellen Xiaoqing Tan, Jack Lanchantin, Zichun Yu +11Mid-Training for Language ModelsLLM Training

  6. Self-Improvement as Coherence Optimization: A Theoretical Account

    Jan 20, 2026Tianyi Qiu, Ahmed Hani Ismail, Zhonghao He +1Language Model Self-Improvement

  7. OpenSIR: Open-Ended Self-Improving Reasoner

    Nov 1, 2025Wai-Chung Kwan, Joshua Ong Jun Leang, Pavlos Vougiouklis +3Self-Play RLRL for Language Model Reasoning

  8. A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning

    Oct 21, 2025Mengqi Li, Lei Zhao, Anthony Man-Cho So +2Self-Training for Language ModelsMathematical Reasoning

  9. Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation

    Sep 18, 2025Yujun Zhou, Zhenwen Liang, Haolin Liu +7Language Model Self-ImprovementRL for Language Models

  10. Discovering New Theorems via LLMs with In-Context Proof Learning in Lean

    Sep 16, 2025Kazumi Kasaura, Naoto Onda, Yuta Oriike +3Automated Theorem ProvingIn-Context Learning

  11. ReST-RL: Reinforcing LLM Reasoning through Unified Self-Training and Value-Guided Search

    Aug 27, 2025Sining Zhoubian, Dan Zhang, Jie TangRL for Code GenerationRL for Language Model Reasoning

  12. SyncLoop: A Multimodal Dual-Loop Framework for Self-Improving Mathematical Reasoning

    Jul 22, 2025Xiuwei Chen, Wentao Hu, Hanhui Li +9Synthetic Data GenerationMultimodal Large Language Models

  13. RL-STaR: Theoretical Analysis of Reinforcement Learning Frameworks for Self-Taught Reasoner

    Oct 31, 2024Fu-Chieh Chang, Yu-Ting Lee, Hui-Ying Shih +2Reinforcement LearningRL for Language Model Reasoning