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

arXiv: https://arxiv.org/abs/2607.26591 · HTML: https://mlsanity.com/paper/2607.26591/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 34 of its 61 references that are in the map.
- First posted on arXiv 29 Jul 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 30 of 34)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution](https://mlsanity.com/paper/2502.18449/) (2025)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model](https://mlsanity.com/paper/1902.04094/) (2019)
- [Keep the Conversation Going: Fixing 162 out of 337 bugs for 0.42 each using ChatGPT](https://mlsanity.com/paper/2304.00385/) (2023)
- [An Analysis of the Automatic Bug Fixing Performance of ChatGPT](https://mlsanity.com/paper/2301.08653/) (2023)
- [Neural Machine Translation: A Review and Survey](https://mlsanity.com/paper/1912.02047/) (2019)
- [RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair](https://mlsanity.com/paper/2312.15698/) (2023)
- [CoditT5: Pretraining for Source Code and Natural Language Editing](https://mlsanity.com/paper/2208.05446/) (2022)
- [Applying CodeBERT for Automated Program Repair of Java Simple Bugs](https://mlsanity.com/paper/2103.11626/) (2021)
- [Evaluating Agent-based Program Repair at Google](https://mlsanity.com/paper/2501.07531/) (2025)
- [A study on Prompt Design, Advantages and Limitations of ChatGPT for Deep Learning Program Repair](https://mlsanity.com/paper/2304.08191/) (2023)
- [A Survey of LLM-based Automated Program Repair: Taxonomies, Design Paradigms, and Applications](https://mlsanity.com/paper/2506.23749/) (2025)
- [GAMMA: Revisiting Template-based Automated Program Repair via Mask Prediction](https://mlsanity.com/paper/2309.09308/) (2023)
- [Hybrid Automated Program Repair by Combining Large Language Models and Program Analysis](https://mlsanity.com/paper/2406.00992/) (2024)
- [ContrastRepair: Enhancing Conversation-Based Automated Program Repair via Contrastive Test Case Pairs](https://mlsanity.com/paper/2403.01971/) (2024)
- [Generating Bug-Fixes Using Pretrained Transformers](https://mlsanity.com/paper/2104.07896/) (2021)
- [ITER: Iterative Neural Repair for Multi-Location Patches](https://mlsanity.com/paper/2304.12015/) (2023)
- [How Far Can We Go with Practical Function-Level Program Repair?](https://mlsanity.com/paper/2404.12833/) (2024)
- [A Large-scale Empirical Study on Fine-tuning Large Language Models for Unit Testing](https://mlsanity.com/paper/2412.16620/) (2024)
- [SemAgent: A Semantics Aware Program Repair Agent](https://mlsanity.com/paper/2506.16650/) (2025)
- [Automated Program Repair: Emerging trends pose and expose problems for benchmarks](https://mlsanity.com/paper/2405.05455/) (2024)
- [Can GPT-O1 Kill All Bugs? An Evaluation of GPT-Family LLMs on QuixBugs](https://mlsanity.com/paper/2409.10033/) (2024)
- [Characterizing Multi-Hunk Patches: Divergence, Proximity, and LLM Repair Challenges](https://mlsanity.com/paper/2506.04418/) (2025)
- [Repair-R1: Better Test Before Repair](https://mlsanity.com/paper/2507.22853/) (2025)
- [DynaFix: Iterative Automated Program Repair Driven by Execution-Level Dynamic Information](https://mlsanity.com/paper/2512.24635/) (2025)
- [MultiMend: Multilingual Program Repair with Context Augmentation and Multi-Hunk Patch Generation](https://mlsanity.com/paper/2501.16044/) (2025)
- [Beyond Accuracy: Behavioral Dynamics of Agentic Multi-Hunk Repair](https://mlsanity.com/paper/2511.11012/) (2025)
- [EvoRepair: Enhancing Vulnerability Repair Agents Through Experience-Based Self-Evolution](https://mlsanity.com/paper/2605.30105/) (2026)

## Abstract (arXiv)

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.