Saved in:
Bibliographic Details
Main Authors: Zhang, Qingyu, Li, Junzhe, Lin, Jiayi, Luo, Changhua, Qian, Chenxiong
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.17279
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916020369752064
author Zhang, Qingyu
Li, Junzhe
Lin, Jiayi
Luo, Changhua
Qian, Chenxiong
author_facet Zhang, Qingyu
Li, Junzhe
Lin, Jiayi
Luo, Changhua
Qian, Chenxiong
contents Code merging is a significant challenge, particularly in large-scale projects. Existing solutions, including program analysis and machine learning, show promise but face critical limitations. Program analysis lacks the ability to infer developers' intentions, relying on conservative strategies that offload unresolved conflicts for manual handling. Meanwhile, model-based approaches struggle with conflicts involving complex code dependencies due to insufficient contextual awareness. To address these gaps, we introduce Rover, a novel conflict resolution system that integrates program analysis with large language models (LLMs). To obtain context-aware prompts, we propose Multi-layer Code Property Graph (MtCPG), a new representation capturing inter-file dependencies and enabling contextual analysis for a given conflict. Using graph connectivity algorithms, Rover further clusters conflicting code and associated changes into meaningful "contexts" that guide the LLM in generating accurate resolutions. We compared Rover with standalone LLMs, machine learning baseline MergeGen, and suggestion provider tool WizardMerge with adjacent code as the contexts. Evaluation results show that Rover surpasses all of these approaches in terms of conflict resolution, achieving higher similarity to ground-truth resolutions at character, lexical, and semantic levels.
format Preprint
id arxiv_https___arxiv_org_abs_2605_17279
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Rover: Context-aware Conflict Resolution with LLM
Zhang, Qingyu
Li, Junzhe
Lin, Jiayi
Luo, Changhua
Qian, Chenxiong
Software Engineering
Artificial Intelligence
Code merging is a significant challenge, particularly in large-scale projects. Existing solutions, including program analysis and machine learning, show promise but face critical limitations. Program analysis lacks the ability to infer developers' intentions, relying on conservative strategies that offload unresolved conflicts for manual handling. Meanwhile, model-based approaches struggle with conflicts involving complex code dependencies due to insufficient contextual awareness. To address these gaps, we introduce Rover, a novel conflict resolution system that integrates program analysis with large language models (LLMs). To obtain context-aware prompts, we propose Multi-layer Code Property Graph (MtCPG), a new representation capturing inter-file dependencies and enabling contextual analysis for a given conflict. Using graph connectivity algorithms, Rover further clusters conflicting code and associated changes into meaningful "contexts" that guide the LLM in generating accurate resolutions. We compared Rover with standalone LLMs, machine learning baseline MergeGen, and suggestion provider tool WizardMerge with adjacent code as the contexts. Evaluation results show that Rover surpasses all of these approaches in terms of conflict resolution, achieving higher similarity to ground-truth resolutions at character, lexical, and semantic levels.
title Rover: Context-aware Conflict Resolution with LLM
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2605.17279