MultiFixer: A Coordinator-Proposer Based Multi-Agent Framework For Fixing Multi-Hunk Bugs

• URL: http://arxiv.org/abs/2607.26591v1
• Date: Wed, 29 Jul 2026 08:13:12 GMT
• Title: MultiFixer: A Coordinator-Proposer Based Multi-Agent Framework For Fixing Multi-Hunk Bugs
• Abstract summary: MultiFixer is a novel Coordinator-Proposer based multi-agent framework for multi-hunk repair.<n>We evaluate MultiFixer on 835 bugs from Defects4J and three vulnerability benchmarks.
• Score: 18.01768265568016
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Automated Program Repair (APR) has benefited greatly from Large Language Models (LLMs), but existing LLM-based APR methods still struggle with multi-hunk bugs that require coordinated changes across multiple locations. These bugs demand repository-level context understanding, repair-order scheduling, and effective hunk-level patch generation and selection. To address these challenges, we propose MultiFixer, a novel Coordinator-Proposer based multi-agent framework for multi-hunk repair. MultiFixer performs tool-augmented bug analysis, constructs fine-grained repair context, iteratively generates patches through a Coordinator-Proposer architecture, and applies two-stage patch refinement for syntactic and semantic correctness. We evaluate MultiFixer on 835 bugs from Defects4J and three vulnerability benchmarks. On Defects4J, MultiFixer fixes 326 bugs, including 62 multi-method and 27 multi-file bugs, and outperforms prior APR baselines in the reported comparisons with the same base model. Moreover, MultiFixer also fixes 46 multi-hunk bugs among 95 unique fixes. When combined with Claude-3.5-Sonnet, MultiFixer repairs 420 bugs, establishing a new state of the art on Defects4J. On VUL4J, MultiFixer repairs 24 real-world vulnerabilities, including 5 multi-hunk cases. On the multi-hunk subsets of SEC-bench and PatchEval, MultiFixer fixes 11 and 19 vulnerabilities, respectively, outperforming all compared baselines under GPT-3.5. These results demonstrate the effectiveness of MultiFixer for multi-hunk repair.

Related papers

• Beyond Fail-to-Pass: Iterative Hardening of Co-Generated Bug Reproduction Tests and Fixes [55.114939648705395]
  Large language models (LLMs) have made automated program repair increasingly practical for real-world bugs.<n>Bug reproduction tests (BRTs) help close this gap by turning a bug report into an executable, bug-specific signal.<n>We propose CoHarden, a co-generation framework that uses the Lax signal as an in-loop convergence criterion.
  arXiv  Detail & Related papers  (2026-07-22T07:30:07Z)
• AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents [83.37969790806069]
  LLM agent failures are difficult to debug because the step where an error surfaces is often not the one that caused it.<n>We present Agent DebuggerX, an open-source framework that organizes debug as a closed loop of Detect, Attribute, Recover, and Rerun.<n>At its core, Deep Debugger performs multi-turn root-cause diagnosis through global trajectory understanding.
  arXiv  Detail & Related papers  (2026-07-21T06:21:13Z)
• One Rewrite to Fix Them All? Type-Aware Repair Allocation for Text-to-Image Prompt Optimization [59.164665622252016]
  Text-to-image (T2I) generators often fail to follow their prompts faithfully, producing wrong counts, swapped attributes, ambiguous relations, and illegible text.<n> Prompt optimization repairs such failures by rewriting the user prompt, requiring no generator retraining, and has yielded promising results.<n>We formulate semantic prompt optimization as atomic repair allocation: each failed proposition is routed to a type-conditioned repair operator before the resulting local constraints are compiled into one executable prompt.
  arXiv  Detail & Related papers  (2026-07-21T05:31:43Z)
• Multi-Perspective Agentic Program Repair via Code Property Graphs and Temporal Execution Graphs [16.200330031305473]
  We present CT-Repair, an agentic APR framework representing static and dynamic evidence as queryable Code Property Graph (CPG) and Temporal Execution Graph (TEG)<n>Three finite-state-machine-guided agents analyze each bug from static, dynamic, and hybrid perspectives and independently produce repair strategies.<n>A strategy-guided generation procedure instantiates these strategies as candidate patches and uses validation feedback to refine the most promising strategy.
  arXiv  Detail & Related papers  (2026-07-14T10:33:29Z)
• Anchored Self-Play for Code Repair [68.0728003844994]
  Code repair is an important capability for language models (LMs)<n>We propose __generator--fixer self-play__, in which a single model is trained with reinforcement learning to generate bugs and fix them.<n>On BugSourceBench, we find that self-play drifts toward difficult but unrealistic bugs.<n>We propose Anchored Self-Play (ASP), which anchors self-play with a small reference set by adding a code-embedding similarity reward for generation and mixing reference bugs into fixer training.
  arXiv  Detail & Related papers  (2026-07-03T17:51:52Z)
• QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization [50.722636027998]
  Large Language Models (LLMs) achieve strong program repair performance but often suffer from over-editing.<n>We propose PRepair, a framework that mitigates over-editing and improves repair accuracy.
  arXiv  Detail & Related papers  (2026-04-07T14:56:38Z)
• Repair Ingredients Are All You Need: Improving Large Language Model-Based Program Repair via Repair Ingredients Search [41.50068103527948]
  We propose ReinFix, a framework that searches for repair ingredients throughout the reasoning and solution phases of bug fixing.<n>During the solution phase, ReinFix searches for external ingredients from historical bug fixes with similar bug patterns.<n> Evaluations on two popular benchmarks demonstrate the effectiveness of our approach over SOTA baselines.
  arXiv  Detail & Related papers  (2025-06-29T06:02:11Z)
• MultiMend: Multilingual Program Repair with Context Augmentation and Multi-Hunk Patch Generation [2.7036595757881323]
  MultiMend is a learning-based APR approach designed to improve repair performance on multiple programming languages.<n>It embeds source code lines and applies retrieval-augmented generation to augment the buggy context with relevant lines during patch generation.<n>We evaluate MultiMend on four benchmarks with four programming languages and compare it with state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-01-27T13:37:43Z)
• ThinkRepair: Self-Directed Automated Program Repair [11.598008952093487]
  Large language models (LLMs) instructed by prompt engineering have attracted much attention for their powerful ability to address many kinds of tasks including bug-fixing. We propose a self-directed LLM-based automated program repair, ThinkRepair, with two main phases: collection phase and fixing phase. Evaluations on two widely studied datasets (Defects4J and QuixBugs) by comparing ThinkRepair with 12 SOTA APRs indicate the priority of ThinkRepair in fixing bugs.
  arXiv  Detail & Related papers  (2024-07-30T15:17:07Z)
• MCRepair: Multi-Chunk Program Repair via Patch Optimization with Buggy Block [0.0]
  We propose a novel APR technique called multi-code repair (MCRepair), which applies a buggy block, patch optimization, and CodeBERT to target multi-chunk bugs. In the experiments using Defects4J, MCRepair repaired 65 bugs, including 21 multi-chunk bugs. Moreover, it fixed 18 unique bugs, including eight multi-chunk bugs, and improved 40 to 250 percent performance than the baselines.
  arXiv  Detail & Related papers  (2023-10-12T09:21:40Z)
• RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair [75.40584530380589]
  We propose a novel Retrieval-Augmented Patch Generation framework (RAP-Gen) RAP-Gen explicitly leveraging relevant fix patterns retrieved from a list of previous bug-fix pairs. We evaluate RAP-Gen on three benchmarks in two programming languages, including the TFix benchmark in JavaScript, and Code Refinement and Defects4J benchmarks in Java.
  arXiv  Detail & Related papers  (2023-09-12T08:52:56Z)

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.