Metraipolis › archive › dc_73e608e109d4

RepoAtlas: Guiding Coding Agents via Evolving Multimodal Repository Views — arXiv:2609.16936

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.16936
License (as archived)
CC0-1.0
Archived
2026-10-15T18:38:44.816Z
SHA-256 of the archived text
bf8c7c96e733f0142e8162bd003490f8bac6fa40a0705c7116b3a75fd73470d1
Stable URL of this page
https://metraipolis.com/documento/dc_73e608e109d4

How to cite

RepoAtlas: Guiding Coding Agents via Evolving Multimodal Repository Views — arXiv:2609.16936 — arXiv (en), https://arxiv.org/abs/2609.16936 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_73e608e109d4 (Metraipolis archive dc_73e608e109d4, sha256 bf8c7c96e733f0142e8162bd003490f8bac6fa40a0705c7116b3a75fd73470d1)
BibTeX
@misc{dc73e608e109d4,
  title = {RepoAtlas: Guiding Coding Agents via Evolving Multimodal Repository Views — arXiv:2609.16936},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.16936},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_73e608e109d4; sha256 bf8c7c96e733f0142e8162bd003490f8bac6fa40a0705c7116b3a75fd73470d1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16936. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 \textbf{RepoAtlas}, a training-free module that maintains evolving multimodal repository views through a \emph{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visual and textual representations, and refreshes the view when changes in the exploration state render it outdated.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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.AI).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.16936 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T18:03:09.710Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).