mlsanityData to 7 Oct 2026

ProgCo: Program Helps Self-Correction of Large Language Models

arXiv 2501.01264 ↗First posted 2 Jan 2025cs.CL cs.AI cs.LGcited by 14

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

Self-Correction aims to enable large language models (LLMs) to self-verify and self-refine their initial responses without external feedback. However, LLMs often fail to effectively self-verify and generate correct feedback, further misleading refinement and leading to the failure of self-correction, especially in complex reasoning tasks. In this paper, we propose Program-driven Self-Correction (ProgCo). First, program-driven verification (ProgVe) achieves complex verification logic and extensive validation through self-generated, self-executing verification pseudo-programs. Then, program-driven refinement (ProgRe) receives feedback from ProgVe, conducts dual reflection and refinement on both responses and verification programs to mitigate misleading of incorrect feedback in complex reasoning tasks. Experiments on three instruction-following and mathematical benchmarks indicate that ProgCo achieves effective self-correction, and can be further enhance performance when combined with real program tools. We release our code at https://github.com/songxiaoshuai/progco.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 19 of its 31 references that are in the map. First posted on arXiv 2 Jan 2025.

Builds on

19 of 31 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives4 Jan
  2. 2023Large Language Models Cannot Self-Correct Reasoning Yet3 Oct
  3. 2023Self-Refine: Iterative Refinement with Self-Feedback30 Mar

Other references · 16

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  3. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  4. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  5. 2023Teaching Large Language Models to Self-Debugcited by 963
  6. 2023Language Models can Solve Computer Taskscited by 371
  7. 2024We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?cited by 281
  8. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 230
  9. 2024Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8Bcited by 156
  10. 2023Making Language Models Better Tool Learners with Execution Feedbackcited by 69
  11. 2024TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generationcited by 62
  12. 2024Large Language Models Can Self-Correct with Key Condition Verificationcited by 39
4 more
  1. 2024Progressive Multimodal Reasoning via Active Retrievalcited by 24
  2. 2024Small Language Model Can Self-correctcited by 23
  3. 2024HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflowscited by 13
  4. 2024Large Language Models as Code Executors: An Exploratory Studycited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 8; 2026: 6.

14 papers.

Sort:

By area:

  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  2. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 319
  3. 2025Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AIcited by 39
  4. 2025CodeCriticBench: A Holistic Code Critique Benchmark for Large Language Modelscited by 14
  5. 2025Process or Result? Manipulated Ending Tokens Can Mislead Reasoning LLMs to Ignore the Correct Reasoning Stepscited by 9
  6. 2025Diagnosing Visual Reasoning: Challenges, Insights, and a Path Forwardcited by 6
  7. 2025Introspection of Thought Helps AI Agentscited by 4
  8. 2025RETuning: Upgrading Inference-Time Scaling for Stock Movement Prediction with Large Language Modelscited by 1
  9. 2026From Atoms to Chains: Divergence-Guided Reasoning Curriculum for Unlabeled LLM Domain Adaptationcited by 0
  10. 2026Beyond Output Critique: Self-Correction via Task Distillationcited by 0
  11. 2026RefineRL: Advancing Competitive Programming with Self-Refinement Reinforcement Learningcited by 0
  12. 2026Counterexample Guided Learning in the Large using Reasoning Agentscited by 0
2 more
  1. 2026A Taxonomy of Cognitive Capability Gaps in Generative and Agentic AIcited by 0
  2. 2026Factorized Hypothesis Search for Evidence-to-Taxonomy Retrievalcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Learning to Check: Unleashing Potentials for Self-Correction in Large Language Models
  2. 2024Embedding Self-Correction as an Inherent Ability in Large Language Models for Enhanced Mathematical Reasoning
  3. 2025Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs
  4. 2024Small Language Models Need Strong Verifiers to Self-Correct Reasoning
  5. 2025PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier
  6. 2026A Training-Free Regeneration Paradigm: Contrastive Reflection Memory Guided Self-Verification and Self-Improvement
  7. 2024Large Language Models have Intrinsic Self-Correction Ability
  8. 2024Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models