# REFINE: Enhancing Program Repair Agents through Context-Aware Patch Refinement arXiv: https://arxiv.org/abs/2510.03588 ยท HTML: https://mlsanity.com/paper/2510.03588/ ## Key facts - Cited by 6 papers in the map (data through 14 Oct 2026). - Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. - Builds on 28 of its 64 references that are in the map. - First posted on arXiv 4 Oct 2025. ## Placed in - LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/) ## Builds on (most cited first, 28 of 28) - [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020) - [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021) - [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024) - [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024) - [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024) - [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024) - [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024) - [Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving](https://mlsanity.com/paper/2504.02605/) (2025) - [Few-shot training LLMs for project-specific code-summarization](https://mlsanity.com/paper/2207.04237/) (2022) - [Large Language Models are Few-shot Testers: Exploring LLM-based General Bug Reproduction](https://mlsanity.com/paper/2209.11515/) (2022) - [Automating Code Review Activities by Large-Scale Pre-training](https://mlsanity.com/paper/2203.09095/) (2022) - [ChatUniTest: A Framework for LLM-Based Test Generation](https://mlsanity.com/paper/2305.04764/) (2023) - [SpecRover: Code Intent Extraction via LLMs](https://mlsanity.com/paper/2408.02232/) (2024) - [CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation](https://mlsanity.com/paper/2310.04951/) (2023) - [HITS: High-coverage LLM-based Unit Test Generation via Method Slicing](https://mlsanity.com/paper/2408.11324/) (2024) - [Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination](https://mlsanity.com/paper/2503.04149/) (2025) - [CoTran: An LLM-based Code Translator using Reinforcement Learning with Feedback from Compiler and Symbolic Execution](https://mlsanity.com/paper/2306.06755/) (2023) - [Hybrid Automated Program Repair by Combining Large Language Models and Program Analysis](https://mlsanity.com/paper/2406.00992/) (2024) - [DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal](https://mlsanity.com/paper/2503.14269/) (2025) - [On the Effectiveness of LLM-as-a-judge for Code Generation and Summarization](https://mlsanity.com/paper/2507.16587/) (2025) - [ITER: Iterative Neural Repair for Multi-Location Patches](https://mlsanity.com/paper/2304.12015/) (2023) - [Large Language Model (LLM) for Software Security: Code Analysis, Malware Analysis, Reverse Engineering](https://mlsanity.com/paper/2504.07137/) (2025) - [Exploring LLMs for Malware Detection: Review, Framework Design, and Countermeasure Approaches](https://mlsanity.com/paper/2409.07587/) (2024) - [KGym: A Platform and Dataset to Benchmark Large Language Models on Linux Kernel Crash Resolution](https://mlsanity.com/paper/2407.02680/) (2024) - [iFixR: Bug Report driven Program Repair](https://mlsanity.com/paper/1907.05620/) (2019) - [PPM: Automated Generation of Diverse Programming Problems for Benchmarking Code Generation Models](https://mlsanity.com/paper/2401.15545/) (2024) - [Alleviating Patch Overfitting with Automatic Test Generation: A Study of Feasibility and Effectiveness for the Nopol Repair System](https://mlsanity.com/paper/1810.10614/) (2018) - [LLM-based Unit Test Generation via Property Retrieval](https://mlsanity.com/paper/2410.13542/) (2024) ## Built on by (most cited first, 6 of 6) - [Handoff Debt: The Rediscovery Cost When Coding Agents Take Over Interrupted Tasks](https://mlsanity.com/paper/2606.02875/) (2026) - [Preventing Premature Commitment in Coding Agents with an Evidence-Conditioned Execution Layer](https://mlsanity.com/paper/2607.28815/) (2026) - ["Refactoring Runaway": Understanding and Mitigating Tangled Refactorings in Coding Agents for Issue Resolution](https://mlsanity.com/paper/2605.22526/) (2026) - [EvoOtter: Evolutionary Reproduction Test Generator](https://mlsanity.com/paper/2607.02854/) (2026) - [SWE-Spot: Building Small Repo-Experts with Repository-Centric Learning](https://mlsanity.com/paper/2601.21649/) (2026) - [AdaRepair-Mem: Adaptive Experience Orchestration for Repository-Level Program Repair](https://mlsanity.com/paper/2609.20130/) (2026) ## Abstract (arXiv) Large Language Models (LLMs) have recently shown strong potential in automatic program repair (APR), especially in repository-level settings where the goal is to generate patches based on natural language issue descriptions, large codebases, and regression tests. However, despite their promise, current LLM-based APR techniques often struggle to produce correct fixes due to limited understanding of code context and over-reliance on incomplete test suites. As a result, they frequently generate Draft Patches-partially correct patches that either incompletely address the bug or overfit to the test cases. In this work, we propose a novel patch refinement framework, Refine, that systematically transforms Draft Patches into correct ones. Refine addresses three key challenges: disambiguating vague issue and code context, diversifying patch candidates through test-time scaling, and aggregating partial fixes via an LLM-powered code review process. We implement Refine as a general refinement module that can be integrated into both open-agent-based and workflow-based APR systems. Our evaluation on the SWE-Bench Lite benchmark shows that Refine achieves state-of-the-art results among workflow-based approaches and approaches the best-known performance across all APR categories. Specifically, Refine boosts AutoCodeRover's performance by 14.67%, achieving a score of 51.67% and surpassing all prior baselines. On SWE-Bench Verified, Refine improves the resolution rate by 12.2%, and when integrated across multiple APR systems, it yields an average improvement of 14%-demonstrating its broad effectiveness and generalizability. These results highlight the effectiveness of refinement as a missing component in current APR pipelines and the potential of agentic collaboration in closing the gap between near-correct and correct patches. We also open source our code.