# RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving

arXiv: https://arxiv.org/abs/2505.21577 · HTML: https://mlsanity.com/paper/2505.21577/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 55 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 30 of 36)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs](https://mlsanity.com/paper/2304.08244/) (2023)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://mlsanity.com/paper/2410.07095/) (2024)
- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation](https://mlsanity.com/paper/2310.03302/) (2023)
- [DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence](https://mlsanity.com/paper/2406.11931/) (2024)
- [PaperBench: Evaluating AI's Ability to Replicate AI Research](https://mlsanity.com/paper/2504.01848/) (2025)
- [Large Language Models as Tool Makers](https://mlsanity.com/paper/2305.17126/) (2023)
- [Tool Learning with Foundation Models](https://mlsanity.com/paper/2304.08354/) (2023)
- [CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges](https://mlsanity.com/paper/2401.07339/) (2024)
- [ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings](https://mlsanity.com/paper/2305.11554/) (2023)
- [AIDE: AI-Driven Exploration in the Space of Code](https://mlsanity.com/paper/2502.13138/) (2025)
- [Tool Learning with Large Language Models: A Survey](https://mlsanity.com/paper/2405.17935/) (2024)
- [DebugBench: Evaluating Debugging Capability of Large Language Models](https://mlsanity.com/paper/2401.04621/) (2024)
- [TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks](https://mlsanity.com/paper/2401.12869/) (2024)

## Built on by (most cited first, 19 of 19)

- [GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging](https://mlsanity.com/paper/2508.18993/) (2025)
- [Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches](https://mlsanity.com/paper/2510.04905/) (2025)
- [AutoMLGen: Navigating Fine-Grained Optimization for Coding Agents](https://mlsanity.com/paper/2510.08511/) (2025)
- [Current Agents Fail to Leverage World Model as Tool for Foresight](https://mlsanity.com/paper/2601.03905/) (2026)
- [Code2MCP: Transforming Code Repositories into MCP Services](https://mlsanity.com/paper/2509.05941/) (2025)
- [MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models](https://mlsanity.com/paper/2510.19457/) (2025)
- [Learning to Ideate for Machine Learning Engineering Agents](https://mlsanity.com/paper/2601.17596/) (2026)
- [EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines](https://mlsanity.com/paper/2601.09465/) (2026)
- [MV-Debate: Multi-view Agent Debate with Dynamic Reflection Gating for Multimodal Harmful Content Detection in Social Media](https://mlsanity.com/paper/2508.05557/) (2025)
- [Gistify! Codebase-Level Understanding via Runtime Execution](https://mlsanity.com/paper/2510.26790/) (2025)
- [HarmonyCell: Automating Single-Cell Perturbation Modeling under Semantic and Distribution Shifts](https://mlsanity.com/paper/2603.01396/) (2026)
- [ToolRosella: Translating Code Repositories into Standardized Tools for Scientific Agents](https://mlsanity.com/paper/2603.09290/) (2026)
- [Agentic Agile-V: From Vibe Coding to Verified Engineering in Software and Hardware Development](https://mlsanity.com/paper/2605.20456/) (2026)
- [DeepDiscovery: A Location-Inference Framework for Task-Level Repository Understanding](https://mlsanity.com/paper/2606.22906/) (2026)
- [SW-A2-Bench: Benchmarking Autonomous Software Agent Generation for Agentic Web](https://mlsanity.com/paper/2604.04226/) (2026)
- [AblateCell: A Reproduce-then-Ablate Agent for Virtual Cell Repositories](https://mlsanity.com/paper/2604.19606/) (2026)
- [MCPEvol-Bench: Benchmarking LLM Agent Performance Across Dynamic Evolutions of MCP Servers](https://mlsanity.com/paper/2607.14642/) (2026)
- [MADE: Belief-Driven Dual-Agent Coordination for Autonomous Model Deployment](https://mlsanity.com/paper/2608.01189/) (2026)
- [FeatLens: Feature-Guided Dynamic Code Graph Construction and Retrieval for Repository-Level Code Generation](https://mlsanity.com/paper/2609.26480/) (2026)

## Abstract (arXiv)

The ultimate goal of code agents is to solve complex tasks autonomously. Although large language models (LLMs) have made substantial progress in code generation, real-world tasks typically demand full-fledged code repositories rather than simple scripts. Building such repositories from scratch remains a major challenge. Fortunately, GitHub hosts a vast, evolving collection of open-source repositories, which developers frequently reuse as modular components for complex tasks. Yet, existing frameworks like OpenHands and SWE-Agent still struggle to effectively leverage these valuable resources. Relying solely on README files provides insufficient guidance, and deeper exploration reveals two core obstacles: overwhelming information and tangled dependencies of repositories, both constrained by the limited context windows of current LLMs. To tackle these issues, we propose RepoMaster, an autonomous agent framework designed to explore and reuse GitHub repositories for solving complex tasks. For efficient understanding, RepoMaster constructs function-call graphs, module-dependency graphs, and hierarchical code trees to identify essential components, providing only identified core elements to the LLMs rather than the entire repository. During autonomous execution, it progressively explores related components using our exploration tools and prunes information to optimize context usage. Evaluated on the adjusted MLE-bench, RepoMaster achieves a 110% relative boost in valid submissions over the strongest baseline OpenHands. On our newly released GitTaskBench, RepoMaster lifts the task-pass rate from 40.7% to 62.9% while reducing token usage by 95%. Our code and demonstration materials are publicly available at https://github.com/QuantaAlpha/RepoMaster.