RepoAtlas: Guiding Coding Agents via Evolving Multimodal Repository Views

arXiv:2609.16936 · cs.SE, cs.AI · Submitted 2026-09-15 · Read on arXiv

cs.SE, cs.AI

Submitted: 2026-09-15

Updated: 2026-09-15

Code: https://github.com/treesitter/tree-sitter

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Ablation — 5× in this paper · explained in 1 episode
• Trace — 3× in this paper · explained in 2 episodes
• Adaptive Layout — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• In International Conference on Learning Representations — 2× in this paper
• International Conference on Machine Learning — 2× in this paper
• Large Language Model (LLM) — 2× in this paper · explained in 3 episodes
• ACM International Conference on Automated Software Engineering — 1× in this paper
• Accuracy — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Agentic Coding — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Code Graph Model — 1× in this paper
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Graph Construction — 1× in this paper · explained in 3 episodes
• Grounding — 1× in this paper · explained in 3 episodes

Sources

• Graph Drawing for LLMs: An Empirical Evaluation
• LARGER: Lexically Anchored Repository Graph Exploration and Retrieval
• Scalable and Precise Application-Centered Call Graph Construction for Python
• SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
• VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems in Visual Context
• LLM Agents Can See Code Repositories
• RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph
• ARISE: A Repository-level Graph Representation and Toolset for Agentic Program Repair and Fault Localization
• Kimi K2.5: Visual Agentic Intelligence
• DynamicGTR: Leveraging Graph Topology Representation Preferences to Boost VLM Capabilities on Graph QAs
• OrcaLoca: An LLM Agent Framework for Software Issue Localization

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties