# Rover: Context-aware Conflict Resolution with LLM

arXiv: https://arxiv.org/abs/2605.17279 · HTML: https://mlsanity.com/paper/2605.17279/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 50 references that are in the map.
- First posted on arXiv 17 May 2026.

## Builds on (most cited first, 11 of 11)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [When Attention Sink Emerges in Language Models: An Empirical View](https://mlsanity.com/paper/2410.10781/) (2024)
- [RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation](https://mlsanity.com/paper/2402.16667/) (2024)
- [Fixing Rust Compilation Errors using LLMs](https://mlsanity.com/paper/2308.05177/) (2023)
- [Program Merge Conflict Resolution via Neural Transformers](https://mlsanity.com/paper/2109.00084/) (2021)
- [Spork: Structured Merge for Java with Formatting Preservation](https://mlsanity.com/paper/2202.05329/) (2022)
- [Detecting Semantic Conflicts with Unit Tests](https://mlsanity.com/paper/2310.02395/) (2023)
- [WizardMerge -- Save Us From Merging Without Any Clues](https://mlsanity.com/paper/2407.02818/) (2024)

## Built on by (most cited first, 1 of 1)

- [ATM: CID-Brokered Pre-Write Admission for Multi-Agent Code Co-Synthesis](https://mlsanity.com/paper/2607.00041/) (2026)

## Abstract (arXiv)

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.