智能体
arxiv.org ·
RepoAtlas：通过不断演进的多模态仓库视图引导编码智能体
该论文提出 RepoAtlas，一个免训练模块，在仓库代码图上通过 select–project–refresh 循环维护不断演进的多模态仓库视图：结合 issue 证据与智能体当前探索状态，在固定预算下选取任务相关区域，投影为互补的视觉与文本表示，并在探索状态变化导致视图过时时刷新。在 SWE-bench Verified 上，相对最强的多模态图基线，resolve 率提升 2.4 个百分点，输入 token 与模型调用平均分别减少 5.8% 和 7.8%，并在三个不同家族与规模的模型上取得一致增益。
AI推荐理由 arXiv 论文摘要，来源可信、事实明确（含具体方法与量化结果）。新信息：提出免训练的 RepoAtlas 模块，通过 select–project–refresh 循环在仓库代码图上维护演进式多模态视图，用于编码智能体的仓库级问题定位；在 SWE-bench Verified 上相对最强多模态图基线提升 2.4 个 resolve 点，同时平均减少 5.8% 输入 token 和 7.8% 模型调用，并在三个不同家族与规模的模型上取得一致增益。局限：仅摘要级证据，未提供代码、复现细节或与更多基线的对比，效果为论文自报。
78
正文
Computer Science > Software Engineering
arXiv:2609.16936 (cs)
[Submitted on 15 Sep 2026]
Title:RepoAtlas: Guiding Coding Agents via Evolving Multimodal Repository Views
Authors:Yunxiang Zhang, Haiquan Wang, JiaWei Guo, Hanyang Xia, Yan Chen, Tong Chen, Zhang Zhiwei, Junchen Ye
View a PDF of the paper titled RepoAtlas: Guiding Coding Agents via Evolving Multimodal Repository Views, by Yunxiang Zhang and 7 other authors
View PDF
HTML (experimental)
Abstract: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visual and textual representations, and refreshes the view when changes in the exploration state render it outdated.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.
Subjects:
Software Engineering (cs.SE); Artificial Intelligence (cs.AI)
Cite as:
arXiv:2609.16936 [cs.SE]
(or
arXiv:2609.16936v1 [cs.SE] for this version)
https://doi.org/10.48550/arXiv.2609.16936
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Yunxiang Zhang [view email]
[v1]
Tue, 15 Sep 2026 10:11:51 UTC (1,016 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled RepoAtlas: Guiding Coding Agents via Evolving Multimodal Repository Views, by Yunxiang Zhang and 7 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.SE
new
|
recent
| 2026-09
Change to browse by:
cs
cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)