mlsanityData to 7 Oct 2026

RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation

arXiv 2502.09183 ↗First posted 13 Feb 2025cs.CL cs.AIcited by 8

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

Code generation has attracted increasing attention with the rise of Large Language Models (LLMs). Many studies have developed powerful code LLMs by synthesizing code-related instruction data and applying supervised fine-tuning. However, these methods are limited by teacher model distillation and ignore the potential of iterative refinement by self-generated code. In this paper, we propose Adaptive Critique Refinement (ACR), which enables the model to refine itself by self-generated code and external critique, rather than directly imitating the code responses of the teacher model. Concretely, ACR includes a composite scoring system with LLM-as-a-Judge to evaluate the quality of code responses and a selective critique strategy with LLM-as-a-Critic to critique self-generated low-quality code responses. We develop the RefineCoder series by iteratively applying ACR, achieving continuous performance improvement on multiple code generation benchmarks. Compared to the baselines of the same size, our proposed RefineCoder series can achieve comparable or even superior performance using less data.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 40 of its 56 references that are in the map. First posted on arXiv 13 Feb 2025.

Builds on

40 of 56 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings2 Jan
  2. 2024Qwen2.5-Coder Technical Report18 Sep
  3. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code12 Mar
  4. 2024OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement22 Feb
  5. 2023Teaching Large Language Models to Self-Debug11 Apr

Other references · 35

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2021Program Synthesis with Large Language Modelscited by 3,509
  5. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  6. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  7. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  8. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,442
  9. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332
  10. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
  11. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
  12. 2023WizardCoder: Empowering Code Large Language Models with Evol-Instructcited by 728
23 more
  1. 2022Large Language Models Can Self-Improvecited by 656
  2. 2024ORPO: Monolithic Preference Optimization without Reference Modelcited by 556
  3. 2024BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructionscited by 527
  4. 2024From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judgecited by 480
  5. 2022CodeT: Code Generation with Generated Testscited by 369
  6. 2022The Stack: 3 TB of permissively licensed source codecited by 354
  7. 2024Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positivecited by 239
  8. 2022MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generationcited by 132
  9. 2024Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-stepcited by 123
  10. 2024Towards Analyzing and Understanding the Limitations of DPO: A Theoretical Perspectivecited by 69
  11. 2023Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Codecited by 62
  12. 2024SelfCodeAlign: Self-Alignment for Code Generationcited by 61
  13. 2025Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitatecited by 61
  14. 2023WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuningcited by 42
  15. 2024Self-Boosting Large Language Models with Synthetic Preference Datacited by 40
  16. 2024CodeDPO: Aligning Code Models with Self Generated and Verified Source Codecited by 32
  17. 2024Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignmentcited by 27
  18. 2025Revisit Self-Debugging with Self-Generated Tests for Code Generationcited by 21
  19. 2024S^3cMath: Spontaneous Step-level Self-correction Makes Large Language Models Better Mathematical Reasonerscited by 17
  20. 2024LogicPro: Improving Complex Logical Reasoning via Program-Guided Learningcited by 14
  21. 2024Teaching Language Models to Self-Improve by Learning from Language Feedbackcited by 9
  22. 2024InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instructcited by 7
  23. 2024CodeLutra: Boosting LLM Code Generation via Preference-Guided Refinementcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 3.

8 papers.

  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  2. 2025OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critiquecited by 24
  3. 2025Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewardscited by 14
  4. 2026RM -RF: Reward Model for Run-Free Unit Test Evaluationcited by 2
  5. 2025MemoCoder: Automated Function Synthesis using LLM-Supported Agentscited by 1
  6. 2025SCoder: Iterative Self-Distillation for Bootstrapping Small-Scale Data Synthesizers to Empower Code LLMscited by 0
  7. 2026Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoringcited by 0
  8. 2026Asymmetric Capacity Allocation in Self-Refinement Pipelinescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Rethinking Code Refinement: Learning to Judge Code Efficiency
  2. 2025CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models
  3. 2025CodeCriticBench: A Holistic Code Critique Benchmark for Large Language Models
  4. 2025Teaching Language Models to Critique via Reinforcement Learning
  5. 2025Beyond Sample-Level Feedback: Using Reference-Level Feedback to Guide Data Synthesis
  6. 2023PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback
  7. 2025CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks
  8. 2026Vision-Guided Iterative Refinement for Frontend Code Generation