ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation

• URL: http://arxiv.org/abs/2405.17057v2
• Date: Thu, 29 May 2025 12:34:04 GMT
• Title: ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation
• Authors: Houxing Ren, Mingjie Zhan, Zhongyuan Wu, Aojun Zhou, Junting Pan, Hongsheng Li,
• Abstract summary: We present ReflectionCoder, a novel approach to improve one-off code generation performance.<n>We propose reflection self-distillation and dynamically masked distillation to effectively utilize reflection sequences.<n>Our experiments demonstrate that models fine-tuned with our method achieve state-of-the-art performance.
• Score: 39.778073569406175
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Code generation plays a crucial role in various tasks, such as code auto-completion and mathematical reasoning. Previous work has proposed numerous methods to enhance code generation performance, including integrating feedback from the compiler. Inspired by this, we present ReflectionCoder, a novel approach that effectively leverages reflection sequences constructed by integrating compiler feedback to improve one-off code generation performance. Furthermore, we propose reflection self-distillation and dynamically masked distillation to effectively utilize these reflection sequences. Extensive experiments on three benchmarks, i.e., HumanEval (+), MBPP (+), and MultiPL-E, demonstrate that models fine-tuned with our method achieve state-of-the-art performance. Beyond the code domain, we believe this approach can benefit other domains that focus on final results and require long reasoning paths. Code and data are available at https://github.com/SenseLLM/ReflectionCoder.

Related papers

• Turning the Tide: Repository-based Code Reflection [52.13709676656648]
  We introduce LiveRepoReflection, a benchmark for evaluating code understanding and generation in multi-file repository contexts.<n>1,888 rigorously filtered test cases across $6$ programming languages to ensure diversity, correctness, and high difficulty.<n>We also create RepoReflection-Instruct, a large-scale, quality-filtered instruction-tuning dataset derived from diverse sources.
  arXiv  Detail & Related papers  (2025-07-14T02:36:27Z)
• Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instruction [11.838351314880736]
  Instruct-of-Reflection (IoRT) is a novel and general reflection framework that leverages dynamic-meta instruction to enhance the iterative reflection capability of Large Language Models (LLMs) Our experiments demonstrate that IoRT achieves an average improvement of 10.1% over established baselines in mathematical and commonsense reasoning tasks.
  arXiv  Detail & Related papers  (2025-03-02T14:02:03Z)
• Multi-Turn Code Generation Through Single-Step Rewards [68.05767417891057]
  Existing methods either generate code without feedback or use complex, hierarchical reinforcement learning to optimize multi-turn rewards. We propose a simple yet scalable approach, $mu$Code, that solves multi-turn code generation using only single-step rewards.
  arXiv  Detail & Related papers  (2025-02-27T18:55:05Z)
• RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation [13.75248879205993]
  We propose Adaptive Critique Refinement (ACR), which enables the model to refine itself by self-generated code and external critique.<n>ACR includes a composite scoring system with LLM-as-a-Judge to evaluate the quality of code responses.<n>We develop the RefineCoder series by iteratively applying ACR, achieving continuous performance improvement on multiple code generation benchmarks.
  arXiv  Detail & Related papers  (2025-02-13T11:17:53Z)
• PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback [78.89596149768458]
  Large Language Models (LLMs) are widely adopted for assisting in software development tasks. We propose PerfCodeGen, a training-free framework that enhances the performance of LLM-generated code.
  arXiv  Detail & Related papers  (2024-11-18T06:22:38Z)
• CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models [106.11371409170818]
  Large language models (LLMs) can act as agents with capabilities to self-refine and improve generated code autonomously. We propose CodeTree, a framework for LLM agents to efficiently explore the search space in different stages of the code generation process. Specifically, we adopted a unified tree structure to explicitly explore different coding strategies, generate corresponding coding solutions, and subsequently refine the solutions.
  arXiv  Detail & Related papers  (2024-11-07T00:09:54Z)
• SelfCodeAlign: Self-Alignment for Code Generation [15.23960029671979]
  SelfCodeAlign is the first fully transparent and permissive pipeline for self-aligning code language models (LLMs) It first extracts diverse coding concepts from high-quality seed snippets to generate new tasks. It then samples multiple responses per task, pairs each with test cases, and validates them in a sandbox environment. Finetuning on this dataset leads to a model that achieves a 67.1 pass@1 on HumanEval+, surpassing CodeLlama-70B-Instruct despite being ten times smaller.
  arXiv  Detail & Related papers  (2024-10-31T17:55:13Z)
• Process Supervision-Guided Policy Optimization for Code Generation [15.943210767010045]
  Reinforcement learning (RL) with unit test feedback has enhanced large language models' (LLMs) code generation, but relies on sparse rewards provided only after complete code evaluation.<n>We propose a Process Reward Model (PRM) that delivers dense, line-level feedback on code correctness during generation, mimicking human code refinement.
  arXiv  Detail & Related papers  (2024-10-23T07:22:33Z)
• Enhancing Sequential Recommendations through Multi-Perspective Reflections and Iteration [16.10791252542592]
  Sequence recommendation (SeqRec) aims to predict the next item a user will interact with by understanding user intentions and leveraging collaborative filtering information. Large language models (LLMs) have shown great promise in recommendation tasks through prompt-based, fixed reflection libraries, and fine-tuning techniques. MoRE introduces three reflectors for generating LLM-based reflections on explicit preferences, implicit preferences, and collaborative signals.
  arXiv  Detail & Related papers  (2024-09-10T09:58:55Z)
• DOCE: Finding the Sweet Spot for Execution-Based Code Generation [69.5305729627198]
  We propose a comprehensive framework that includes candidate generation, $n$-best reranking, minimum Bayes risk (MBR) decoding, and self-ging as the core components. Our findings highlight the importance of execution-based methods and the difference gap between execution-based and execution-free methods.
  arXiv  Detail & Related papers  (2024-08-25T07:10:36Z)
• Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation [25.344800819245858]
  FunCoder is a code generation framework incorporating the divide-and-conquer strategy with functional consensus. FunCoder outperforms state-of-the-art methods by +9.8% on average in HumanEval, MBPP, xCodeEval and MATH with GPT-3.5 and GPT-4.
  arXiv  Detail & Related papers  (2024-05-30T14:31:33Z)
• DolphCoder: Echo-Locating Code Large Language Models with Diverse and Multi-Objective Instruction Tuning [36.78560777629329]
  We introduce a diverse instruction model (DolphCoder) with self-evaluating for code generation. It learns diverse instruction targets and combines a code evaluation objective to enhance its code generation ability. Our model achieves superior performance on the HumanEval and MBPP benchmarks.
  arXiv  Detail & Related papers  (2024-02-14T12:34:58Z)
• StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback [58.20547418182074]
  We introduce StepCoder, a novel framework for code generation, consisting of two main components. CCCS addresses the exploration challenge by breaking the long sequences code generation task into a Curriculum of Code Completion Subtasks. FGO only optimize the model by masking the unexecuted code segments to provide Fine-Grained Optimization. Our method improves the ability to explore the output space and outperforms state-of-the-art approaches in corresponding benchmarks.
  arXiv  Detail & Related papers  (2024-02-02T13:14:31Z)
• PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback [5.459517921633247]
  We propose a novel RRTF (Rank Responses to align Test&Teacher Feedback) framework, which can effectively and efficiently boost pre-trained large language models for code generation. Under this framework, we present PanGu-Coder2, which achieves 62.20% pass@1 on the OpenAI HumanEval benchmark.
  arXiv  Detail & Related papers  (2023-07-27T15:28:29Z)
• CONCORD: Clone-aware Contrastive Learning for Source Code [64.51161487524436]
  Self-supervised pre-training has gained traction for learning generic code representations valuable for many downstream SE tasks. We argue that it is also essential to factor in how developers code day-to-day for general-purpose representation learning. In particular, we propose CONCORD, a self-supervised, contrastive learning strategy to place benign clones closer in the representation space while moving deviants further apart.
  arXiv  Detail & Related papers  (2023-06-05T20:39:08Z)
• Coder Reviewer Reranking for Code Generation [56.80381384717]
  We propose Coder-Reviewer reranking as a method for sampling diverse programs from a code language model and reranking with model likelihood. Experimental results show that Coder-Reviewer reranking leads to consistent and significant improvement over reranking with the Coder model only. Coder-Reviewer reranking is easy to implement by prompting, can generalize to different programming languages, and works well with off-the-shelf hyper parameters.
  arXiv  Detail & Related papers  (2022-11-29T18:56:33Z)
• ReACC: A Retrieval-Augmented Code Completion Framework [53.49707123661763]
  We propose a retrieval-augmented code completion framework, leveraging both lexical copying and referring to code with similar semantics by retrieval. We evaluate our approach in the code completion task in Python and Java programming languages, achieving a state-of-the-art performance on CodeXGLUE benchmark.
  arXiv  Detail & Related papers  (2022-03-15T08:25:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.