# Characterizing Multi-Hunk Patches: Divergence, Proximity, and LLM Repair Challenges

arXiv: https://arxiv.org/abs/2506.04418 · HTML: https://mlsanity.com/paper/2506.04418/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jun 2025.

## Built on by (most cited first, 7 of 7)

- [Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub](https://mlsanity.com/paper/2601.15195/) (2026)
- [HAFixAgent: History-Aware Program Repair Agent](https://mlsanity.com/paper/2511.01047/) (2025)
- [Beyond Accuracy: Behavioral Dynamics of Agentic Multi-Hunk Repair](https://mlsanity.com/paper/2511.11012/) (2025)
- [MultiFixer: A Coordinator-Proposer Based Multi-Agent Framework For Fixing Multi-Hunk Bugs](https://mlsanity.com/paper/2607.26591/) (2026)
- [Does Fault Localization Beat a Fresh Attempt? A Placebo-Controlled Study of Test-Guided Code Repair](https://mlsanity.com/paper/2609.00854/) (2026)
- [What Does an Agentic Software Engineering Benchmark Measure? Profiling Task Demands and Agent Behaviour Beyond What Category Labels Reveal](https://mlsanity.com/paper/2609.01271/) (2026)
- [Diagnosing Generalization Boundaries in AI-Based Vulnerability Detection via Calibrated Embedding Distances](https://mlsanity.com/paper/2610.14296/) (2026)

## Abstract (arXiv)

Multi-hunk bugs, where fixes span disjoint regions of code, are common in practice, yet remain underrepresented in automated repair. Existing techniques and benchmarks pre-dominantly target single-hunk scenarios, overlooking the added complexity of coordinating semantically related changes across the codebase. In this work, we characterize HUNK4J, a dataset of multi-hunk patches derived from 372 real-world defects. We propose hunk divergence, a metric that quantifies the variation among edits in a patch by capturing lexical, structural, and file-level differences, while incorporating the number of hunks involved. We further define spatial proximity, a classification that models how hunks are spatially distributed across the program hierarchy. Our empirical study spanning six LLMs reveals that model success rates decline with increased divergence and spatial dispersion. Notably, when using the LLM alone, no model succeeds in the most dispersed Fragment class. These findings highlight a critical gap in LLM capabilities and motivate divergence-aware repair strategies.