RepoAtlas: Guiding Coding Agents via Evolving Multimodal Repository Views

• URL: http://arxiv.org/abs/2609.16936v1
• Date: Tue, 15 Sep 2026 10:11:51 GMT
• Title: RepoAtlas: Guiding Coding Agents via Evolving Multimodal Repository Views
• Abstract summary: We present textbfRepoAtlas, a training-free module that maintains evolving multimodal repository views.<n>RepoAtlas combines evidence from the issue with the agent's current exploration state to select a task-relevant region under a fixed budget.<n>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.
• Score: 14.618487825419328
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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visual and textual representations, and refreshes the view when changes in the exploration state render it outdated.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.

Related papers

• WeAgent-MMSearch: Native Text-Vision Interaction for Multimodal Search Agents [53.426679066400844]
  We introduce WeAgent-Harness, a multimodal agentic harness that supports native text-vision interaction and runtime recovery.<n>We develop WeAgent-MMSearch, an integrated system spanning data construction, agentic post-training, and multimodal rollout.<n>We also introduce VisTarget-Bench, a 150-task human-verified benchmark that pairs each question with a held-out target image.
  arXiv  Detail & Related papers  (2026-08-28T08:28:43Z)
• CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents [5.400196370175265]
  Coding agents repeatedly search, navigate, and retain context from evolving repositories.<n> disconnected indexes, language servers, and task-local histories force repeated discovery and obscure lifecycle costs.<n>CodeNib builds reusable lexical, dense, and structural views per repository commit.
  arXiv  Detail & Related papers  (2026-07-28T08:25:30Z)
• Beyond Textual Repository Exploration: Dual-Modal Structural Reasoning for Agentic Issue Resolution [24.103118645295655]
  CouplingVIEW brings visual reasoning into repository exploration for issue-resolution agents.<n>VIEW consistently improves issue-resolution performance across different agent architectures and model families.
  arXiv  Detail & Related papers  (2026-07-02T09:23:48Z)
• FastContext: Training Efficient Repository Explorer for Coding Agents [29.359764163872473]
  Large Language Model (LLM) coding agents have achieved strong results on software engineering tasks.<n> repository exploration remains a major bottleneck: locating relevant code consumes substantial token budget and pollutes the agent's context with irrelevant snippets.<n>We present FastContext, a dedicated exploration subagent that separates repository exploration from solving.
  arXiv  Detail & Related papers  (2026-06-12T03:23:59Z)
• LLM Agents Can See Code Repositories [14.881212557304414]
  Coding agents powered by large language models have demonstrated strong performance on software engineering tasks.<n>Most agents consume repositories almost entirely as text.<n>Visual graphs of repository structure as a supplementary modality alongside standard text interfaces helps agents understand structure more efficiently.
  arXiv  Detail & Related papers  (2026-06-12T03:14:40Z)
• RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations [51.43574078961796]
  We introduce RepoMirage, a two-stage evaluation suite built on SWE-Bench Verified.<n>RepoMirage-Perturb applies three types of semantics-preserving repository-level perturbations, revealing a clear performance drop when correct solving requires broader context access.<n>We propose RepoAnchor, a structure-first prototype workflow that separates repository exploration from downstream problem solving.
  arXiv  Detail & Related papers  (2026-05-25T06:26:43Z)
• Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning [62.640169289390535]
  SPLIT-RAG is a multi-agent RAG framework that addresses the limitations with question-driven semantic graph partitioning and collaborative subgraph retrieval.<n>The innovative framework first create Semantic Partitioning of Linked Information, then use the Type-Specialized knowledge base to achieve Multi-Agent RAG.<n>The attribute-aware graph segmentation manages to divide knowledge graphs into semantically coherent subgraphs, ensuring subgraphs align with different query types.<n>A hierarchical merging module resolves inconsistencies across subgraph-derived answers through logical verifications.
  arXiv  Detail & Related papers  (2025-05-20T06:44:34Z)
• RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph [63.87660059104077]
  We present RepoGraph, a plug-in module that manages a repository-level structure for modern AI software engineering solutions.<n>RepoGraph substantially boosts the performance of all systems, leading to a new state-of-the-art among open-source frameworks.
  arXiv  Detail & Related papers  (2024-10-03T05:45:26Z)
• Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detection [54.041049052843604]
  We present STEMD, a novel end-to-end framework that enhances the DETR-like paradigm for multi-frame 3D object detection. First, to model the inter-object spatial interaction and complex temporal dependencies, we introduce the spatial-temporal graph attention network. Finally, it poses a challenge for the network to distinguish between the positive query and other highly similar queries that are not the best match.
  arXiv  Detail & Related papers  (2023-07-01T13:53:14Z)
• Semantic Tracklets: An Object-Centric Representation for Visual Multi-Agent Reinforcement Learning [126.57680291438128]
  We study whether scalability can be achieved via a disentangled representation. We evaluate semantic tracklets' on the visual multi-agent particle environment (VMPE) and on the challenging visual multi-agent GFootball environment. Notably, this method is the first to successfully learn a strategy for five players in the GFootball environment using only visual data.
  arXiv  Detail & Related papers  (2021-08-06T22:19:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.