SOURCE-LINKED INTELLIGENCE

RepoAtlas: Guiding Coding Agents via Evolving Multimodal Repository Views

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

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 explorati

Read original source ↗ Open in workspace

recordType

paper

region

Global