mlsanityData to 14 Oct 2026

A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models

arXiv 2508.12903 ↗First posted 18 Aug 2025cs.CL cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Recent advances in self-refinement have demonstrated significant potential for improving the outputs of large language models (LLMs) through iterative refinement. However, most existing self-refinement methods rely on a reactive process with a fixed number of iterations, making it difficult to determine the optimal timing and content of refinement based on the evolving generation context. Inspired by the way humans dynamically refine their thoughts during execution, we propose ProActive Self-Refinement (PASR), a novel method that enables LLMs to refine their outputs during the generation process. Unlike methods that regenerate entire responses, PASR proactively decides whether, when, and how to refine based on the model's internal state and evolving context. We conduct extensive experiments on a diverse set of 10 tasks to evaluate the effectiveness of PASR. Experimental results show that PASR significantly enhances problem-solving performance. In particular, on Qwen3-8B, PASR reduces average token consumption by 41.6% compared to standard generation, while also achieving an 8.2% improvement in accuracy. Our code and baselines used in the paper are available on GitHub.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 34 of its 53 references that are in the map. First posted on arXiv 18 Aug 2025.

Builds on

34 of 53 references.

References · 34

  1. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  4. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  5. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  6. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,822
  7. 2024A Survey on LLM-as-a-Judgecited by 1,423
  8. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  9. 2023Teaching Large Language Models to Self-Debugcited by 988
  10. 2023Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotationscited by 928
  11. 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 903
  12. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
22 more
  1. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMscited by 570
  2. 2024From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judgecited by 494
  3. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 462
  4. 2024Training Language Models to Self-Correct via Reinforcement Learningcited by 426
  5. 2023Language Models can Solve Computer Taskscited by 372
  6. 2022Large Language Models are Better Reasoners with Self-Verificationcited by 307
  7. 2022Generating Sequences by Learning to Self-Correctcited by 277
  8. 2023Is Self-Repair a Silver Bullet for Code Generation?cited by 197
  9. 2024Recursive Introspection: Teaching Language Model Agents How to Self-Improvecited by 165
  10. 2025Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMscited by 163
  11. 2024The pitfalls of next-token predictioncited by 160
  12. 2025DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Modelscited by 158
  13. 2024GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinementscited by 103
  14. 2023Learning From Mistakes Makes LLM Better Reasonercited by 101
  15. 2024Unfamiliar Finetuning Examples Control How Language Models Hallucinatecited by 87
  16. 2024Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoningcited by 69
  17. 2025Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitatecited by 63
  18. 2025Improve LLM-as-a-Judge Ability as a General Abilitycited by 37
  19. 2025Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoningcited by 36
  20. 2025AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPOcited by 33
  21. 2024Small Language Model Can Self-correctcited by 23
  22. 2024Think Thrice Before You Act: Progressive Thought Refinement in Large Language Modelscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Memory in the Age of AI Agentscited by 303
  2. 2025Enhancing Large Language Model Reasoning with Reward Models: An Analytical Surveycited by 8
  3. 2026Brain-Inspired Graph Multi-Agent Systems for LLM Reasoningcited by 6
  4. 2026ARBITER: Reasoning Trajectory Basins and Majority Vote Failures in Test-Time Samplingcited by 1