# RepoAtlas: Guiding Coding Agents via Evolving Multimodal Repository Views

arXiv: https://arxiv.org/abs/2609.16936 · HTML: https://mlsanity.com/paper/2609.16936/

## 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 11 of its 25 references that are in the map.
- First posted on arXiv 15 Sep 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, 11 of 11)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph](https://mlsanity.com/paper/2410.14684/) (2024)
- [OrcaLoca: An LLM Agent Framework for Software Issue Localization](https://mlsanity.com/paper/2502.00350/) (2025)
- [GITA: Graph to Visual and Textual Integration for Vision-Language Graph Reasoning](https://mlsanity.com/paper/2402.02130/) (2024)
- [Issue Localization via LLM-Driven Iterative Code Graph Searching](https://mlsanity.com/paper/2503.22424/) (2025)
- [Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning](https://mlsanity.com/paper/2412.13540/) (2024)
- [PyCG: Practical Call Graph Generation in Python](https://mlsanity.com/paper/2103.00587/) (2021)
- [Prometheus: Towards Long-Horizon Codebase Navigation for Repository-Level Problem Solving](https://mlsanity.com/paper/2507.19942/) (2025)
- [Graph Drawing for LLMs: An Empirical Evaluation](https://mlsanity.com/paper/2505.03678/) (2025)
- [LARGER: Lexically Anchored Repository Graph Exploration and Retrieval](https://mlsanity.com/paper/2605.16352/) (2026)
- [Scalable and Precise Application-Centered Call Graph Construction for Python](https://mlsanity.com/paper/2305.05949/) (2023)

## Abstract (arXiv)

Large language model (LLM)-powered coding agents have made rapid progress in automating software engineering tasks, yet repository-level issue resolution remains challenging. Beyond generating a plausible patch, an agent must localize relevant code across interdependent files and maintain repository context that is both sufficient and focused. Code graphs expose non-local relations, but linear text interfaces obscure their topology; rendering the full repository graph yields visual representations that are too dense to perceive reliably, whereas a one-shot local view becomes stale as exploration proceeds. We present RepoAtlas, a training-free module that maintains evolving multimodal repository views through a select--project--refresh loop over a repository code graph. RepoAtlas combines evidence from the issue with the agent's current exploration state to select a task-relevant region under a fixed budget, projects the selected structure into complementary visual and textual representations, and refreshes the view when changes in the exploration state render it outdated. We evaluate RepoAtlas on SWE-bench Verified, where it improves the resolve rate by 2.4 points while reducing input tokens and model calls by 5.8% and 7.8% on average, relative to the strongest multimodal graph baseline, with consistent gains across three models of different families and scales.