LLM Self-Refinement

LLM: Large Language Model

Overview

Large language model self-refinement asks whether models can improve their answers, code, plans, or other outputs by evaluating and revising their own work. Common approaches use iterative critique-and-revision, structured rubrics or judges, and external signals such as execution results, formal verifiers, retrieved evidence, or environment feedback; some methods also train models to internalize reflection through reinforcement learning. These techniques are applied in settings from mathematical reasoning and code generation to clinical extraction, writing, and agentic tasks, with adaptive stopping and memory used to manage repeated attempts. A central tension is that revision can fix errors but also damage correct answers: gains depend on task, model, feedback quality, and compute, while externally grounded verification is often more reliable than self-assessment alone.

Latest papers

CardsList

118 papers8 papers in the last four weeks, down 56% on the four weeks before. 0.1% of all new papers.

  1. Does reflective LLM feedback survive a wet-lab-scale label budget?

    Nov 1, 2026Haoxuan Zeng, Xin LuoLLM Self-RefinementActive Learning

  2. Self-Refining Prompt Induction for Streaming Text-to-SQL

    Oct 31, 2026Gaetano Rossiello, Alfio Gliozzo, Nandana Mihindukulasooriya +3Text-to-SQLAutomatic Prompt Optimization

  3. Green Code or Costly Code? Evaluating the Energy Costs of Iterative LLM-Based Code Optimizations

    Oct 23, 2026Sadra Emami, Benjamin Weigell, Mohammad Reza Mousavi +3Large Language Model-Guided OptimizationCode Generation

  4. Adaptive Replay Refinement: Allocating Test-Time Compute Between Revision and Resampling

    Oct 20, 2026Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer +3Inference-Time Compute AllocationTest-Time Scaling

  5. GraphEvoResearcher: A Cost-Matched Mechanism Analysis of Explicit Reasoning Graphs in Training-Free Self-Reflection

    Oct 19, 2026Suxing Liu, Byungwon Min, Zhijian Zheng +1Multi-Hop QALLM Self-Refinement

  6. Self-Reflective Chain-of-Thought (SRCoT): Evidence-Based Text Generation via a Closed-Loop Retrieve--Reflect--Revise Pipeline on Edge LLMs

    Oct 16, 2026Fabian Broszio, Michael Hoffmann, Adrian PaschkeEvidence-Grounded GenerationSelf-Reflection in Language Model Agents

  7. Think More or Read More? A Token-Budget Theory of Reasoning with Shared Context

    Oct 16, 2026Manh Nguyen, Sunil Gupta, Hung LeEfficient Language Model ReasoningMulti-Agent Debate

  8. NL2SQL with Iterative Self-Refinement

    Oct 16, 2026Anjali Vemula, Akshat DasulaText-to-SQLExecution-Guided Text-to-SQL

  9. HERO: Harnessing Evidence for Test-time Refinement and Prompt Optimization in Program Generation

    Oct 13, 2026Mingyu Lu, Timothy Ossowski, Tristan Naumann +2Automatic Prompt OptimizationLLM Code Generation

  10. Verifier-Harness Co-Evolution for Training-Free Self-Improvement on Open-Ended Tasks

    Oct 13, 2026Tianyi Xu, Yaolun Zhang, Yiran Wu +6LLM Agent Self-ImprovementLLM Self-Refinement

  11. Learning to GUIDE the Group: Self-Learning LLM Facilitation Across Multi-Party Tasks

    Oct 12, 2026Ziyi Liu, Tzu-Sheng Kuo, Jiale Liu +3LLM AgentsLLM Agent Self-Improvement

  12. VETR: Execution-Grounded Self-Improving Agent for Symbolic Graphics Reasoning

    Oct 9, 2026Yingbo Ma, Kuangshi Ai, Gordon Dai +3LLM Self-RefinementAutomated Program Repair

  13. Learning the Loop, Not Just the Page: Execution-Grounded Loop Learning for Web Generation

    Oct 8, 2026Yuxin Meng, Ruixu Zhang, Junjie Wang +10LLM Self-RefinementRL for Language Models

  14. ReTeach: Building a Self-Teacher through Multi-Round Reflection and Retry

    Oct 8, 2026Yafeng Tang, Hao Li, Hongsheng Yu +1Language Model DistillationLLM Self-Refinement

  15. Auditing Pairwise Equivalence Judgments: Self-Critique Effects and Diversity Measurement in Multi-Agent Hypothesis Generation

    Oct 2, 2026Ji Young Byun, Anthony Hu, Jesse Rogers +3Language Model Generation EvaluationMulti-Agent LLMs

  16. Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite

    Oct 2, 2026Zongxia Li, Yucheng Shi, Zhongzhi Li +7LLM Agent Trajectory SynthesisSelf-Training for Language Models

  17. RefCon: Iterative Refinement and Contrastive Memory Extraction for Context-Evolving Agent

    Sep 30, 2026Ubaidillah Ariq Prathama, Bo Liu, Yeo Boon Hong +3Contrastive LearningLLM Self-Refinement

  18. AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks

    Sep 29, 2026Hongjin Qian, Chaofan Li, Kun Luo +11LLM Self-RefinementLLM Agent Training

  19. WeaveData: A Multimodal Data Analysis System with Self-Critiquing and Self-Evolving LLM Plans

    Sep 28, 2026Min Jia, Shihao Zhou, Jun-Peng Zhu +9LLM Self-RefinementLLM Planning

  20. VPEvolve: A Self-Evolving Virtual Process Engineer for Computational Lithography

    Sep 26, 2026Tianyi Li, Wenxuan Dong, Donger Luo +5Semiconductor ManufacturingLarge Language Model-Guided Optimization

  21. Vibe Patenting: Evaluating LLM Judges for Professional Patent-Drafting Agents

    Sep 11, 2026Toshiaki Koike-Akino, Vladislav Blaykhman, Ye Wang +2LLM Self-RefinementLLM-as-a-Judge

  22. What Drives Recovery in Agentic Text-to-Cypher? LAST-CQ: An LLM Agent Self-Refinement Framework

    Sep 11, 2026Ioannis Prokopiou, Athanasios Aidinis, Panagiotis-Christos Kyrmpatsos +1LLM Self-RefinementLLM Agent Evaluation