awesome-self-improving-llm

A curated collection of peer‑reviewed papers, projects, and resources on self‑improvement techniques for large language models (LLMs).

Well, I was gonna make this page using DeepResearch or Grok-3, but they are certainly failing at it. So, I'm doing it myself.

Papers

• Large Language Models Can Self-Improve [pdf]
  • Jiaxin Huang, Shixiang Gu, Le Hou, Yuexin Wu, Xuezhi Wang, Hongkun Yu, Jiawei Han. EMNLP'23
• LM vs LM: Detecting Factual Errors via Cross Examination [pdf]
  • Roi Cohen, May Hamri, Mor Geva, Amir Globerson. EMNLP'23
• Self‑Instruct: Aligning Language Models with Self‑Generated Instructions [pdf]
  • Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A. Smith, Daniel Khashabi, Hannaneh Hajishirzi. ACL'23
• Reflexion: Language Agents with Verbal Reinforcement Learning [pdf]
  • Noah Shinn, Federico Cassano, Edward Berman, Ashwin Gopinath, Karthik Narasimhan, Shunyu Yao. NeurIPS'23
• Self-Refine: Iterative Refinement with Self-Feedback [pdf]
  • Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, Shashank Gupta, Bodhisattwa Prasad Majumder, Katherine Hermann, Sean Welleck, Amir Yazdanbakhsh, Peter Clark. NeurIPS'23
• Self-Evaluation Guided Beam Search for Reasoning [pdf]
  • Yuxi Xie, Kenji Kawaguchi, Yiran Zhao, Xu Zhao, Min-Yen Kan, Junxian He, Qizhe Xie. NeurIPS'23
• Self‑Rewarding Language Models [pdf]
  • Weizhe Yuan, Richard Yuanzhe Pang, Kyunghyun Cho, Xian Li, Sainbayar Sukhbaatar, Jing Xu, Jason Weston. ICML'24
• Large Language Models Cannot Self-Correct Reasoning Yet [pdf]
  • Jie Huang, Xinyun Chen, Swaroop Mishra, Huaixiu Steven Zheng, Adams Wei Yu, Xinying Song, Denny Zhou. ICLR'24
• Teaching Large Language Models to Self‑Debug [pdf]
  • Xinyun Chen, Maxwell Lin, Nathanael Schärli, Denny Zhou. ICLR'24
• Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models [pdf]
  • Loka Li, Guangyi Chen, Yusheng Su, Zhenhao Chen, Yixuan Zhang, Eric Xing, Kun Zhang. arXiv'24
• Self-Improvement in Language Models: The Sharpening Mechanism [pdf]
  • Audrey Huang, Adam Block, Dylan J. Foster, Dhruv Rohatgi, Cyril Zhang, Max Simchowitz, Jordan T. Ash, Akshay Krishnamurthy. ICLR'25
• Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains [pdf]
  • Vighnesh Subramaniam, Yilun Du, Joshua B. Tenenbaum, Antonio Torralba, Shuang Li, Igor Mordatch. ICLR'25
• Iterative Deepening Sampling for Large Language Models [pdf]
  • Weizhe Chen, Sven Koenig, Bistra Dilkina. arXiv'25

Other awesome-selves

• Awesome-LLM-Self-Improvement [link]

  A curated list focusing on inference‑time self‑improvement techniques.

• Awesome LLM Self‑Reflection [link]

  A collection dedicated to self‑reflection and self‑correction methods in LLMs.

• Self‑Correction LLMs Papers [link]

  A repository collecting research papers on self‑correcting LLMs with automated feedback.

License

To the extent possible under law, Changho Shin has waived all copyright and related or neighboring rights to this work.