mlsanityData to 7 Oct 2026

Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration

arXiv 2406.01422 ↗First posted 3 Jun 2024cs.SE cs.CLcited by 58

Not on the map. Why?

Cited by 35 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

This paper presents Alibaba LingmaAgent, a novel Automated Software Engineering method designed to comprehensively understand and utilize whole software repositories for issue resolution. Deployed in TONGYI Lingma, an IDE-based coding assistant developed by Alibaba Cloud, LingmaAgent addresses the limitations of existing LLM-based agents that primarily focus on local code information. Our approach introduces a top-down method to condense critical repository information into a knowledge graph, reducing complexity, and employs a Monte Carlo tree search based strategy enabling agents to explore and understand entire repositories. We guide agents to summarize, analyze, and plan using repository-level knowledge, allowing them to dynamically acquire information and generate patches for real-world GitHub issues. In extensive experiments, LingmaAgent demonstrated significant improvements, achieving an 18.5% relative improvement on the SWE-bench Lite benchmark compared to SWE-agent. In production deployment and evaluation at Alibaba Cloud, LingmaAgent automatically resolved 16.9% of in-house issues faced by development engineers, and solved 43.3% of problems after manual intervention. Additionally, we have open-sourced a Python prototype of LingmaAgent for reference by other industrial developers https://github.com/RepoUnderstander/RepoUnderstander. In fact, LingmaAgent has been used as a developed reference by many subsequently agents.

Key facts. Cited by 58 papers in the map (data through 7 Oct 2026). Builds on 28 of its 52 references that are in the map. First posted on arXiv 3 Jun 2024.

Builds on

28 of 52 references.

References · 28

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  3. 2021Program Synthesis with Large Language Modelscited by 3,509
  4. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  5. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
  6. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332
  7. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
  8. 2021CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generationcited by 732
  9. 2022A Survey on In-context Learningcited by 717
  10. 2019CodeSearchNet Challenge: Evaluating the State of Semantic Code Searchcited by 638
  11. 2024Executable Code Actions Elicit Better LLM Agentscited by 537
  12. 2024StarCoder 2 and The Stack v2: The Next Generationcited by 484
16 more
  1. 2023RepoBench: Benchmarking Repository-Level Code Auto-Completion Systemscited by 346
  2. 2023CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-Xcited by 294
  3. 2024CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challengescited by 278
  4. 2023Secrets of RLHF in Large Language Models Part I: PPOcited by 226
  5. 2023CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completioncited by 181
  6. 2024Secrets of RLHF in Large Language Models Part II: Reward Modelingcited by 170
  7. 2023CodePlan: Repository-level Coding using LLMs and Planningcited by 139
  8. 2022Repository-Level Prompt Generation for Large Language Models of Codecited by 106
  9. 2024Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimizationcited by 84
  10. 2024RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generationcited by 69
  11. 2022CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Contextcited by 64
  12. 2024AgentFL: Scaling LLM-based Fault Localization to Project-Level Contextcited by 47
  13. 2024CYCLE: Learning to Self-Refine the Code Generationcited by 39
  14. 2024UniDebugger: Hierarchical Multi-Agent Framework for Unified Software Debuggingcited by 35
  15. 2024ContrastRepair: Enhancing Conversation-Based Automated Program Repair via Contrastive Test Case Pairscited by 19
  16. 2023Survey of Code Search Based on Deep Learningcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 9; 2025: 20; 2026: 29.

58 papers.

Sort:

By area:

  1. 2024Agentless: Demystifying LLM-based Software Engineering Agentscited by 400
  2. 2024SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinementcited by 124
  3. 2024RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graphcited by 88
  4. 2025SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agentscited by 66
  5. 2025SWE-Exp: Experience-Driven Software Issue Resolutioncited by 64
  6. 2024Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvementcited by 57
  7. 2025SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolutioncited by 52
  8. 2025GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoningcited by 38
  9. 2025EnvBench: A Benchmark for Automated Environment Setupcited by 36
  10. 2024Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agentscited by 35
  11. 2024TDD-Bench Verified: Can LLMs Generate Tests for Issues Before They Get Resolved?cited by 32
  12. 2025Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Computecited by 25
38 more
  1. 2025Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approachescited by 20
  2. 2025Code Researcher: Deep Research Agent for Large Systems Code and Commit Historycited by 19
  3. 2026In Line with Context: Repository-Level Code Generation via Context Inliningcited by 18
  4. 2024Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?cited by 17
  5. 2025GraphCodeAgent: Dual Graph-Guided LLM Agent for Retrieval-Augmented Repo-Level Code Generationcited by 17
  6. 2025A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic Systemcited by 15
  7. 2026AIDev: Studying AI Coding Agents on GitHubcited by 15
  8. 2025Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixingcited by 11
  9. 2024LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issuescited by 10
  10. 2025Self-Abstraction from Grounded Experience for Plan-Guided Policy Refinementcited by 9
  11. 2026Scaling Coding Agents via Atomic Skillscited by 8
  12. 2025RefAgent: A Multi-agent LLM-based Framework for Automatic Software Refactoringcited by 7
  13. 2025InfCode: Adversarial Iterative Refinement of Tests and Patches for Reliable Software Issue Resolutioncited by 7
  14. 2026AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completioncited by 7
  15. 2025Agentic Software Issue Resolution with Large Language Models: A Surveycited by 6
  16. 2025GraphLocator: Graph-guided Causal Reasoning for Issue Localizationcited by 4
  17. 2025Empirical Research on Utilizing LLM-based Agents for Automated Bug Fixing via LangGraphcited by 3
  18. 2025InfCode-C++: Intent-Guided Semantic Retrieval and AST-Structured Search for C++ Issue Resolutioncited by 3
  19. 2026DRAINCODE: Stealthy Energy Consumption Attacks on Retrieval-Augmented Code Generation via Context Poisoningcited by 3
  20. 2026DockSmith: Scaling Reliable Coding Environments via an Agentic Docker Buildercited by 3
  21. 2026EviACT: An Evidence-to-Action Framework for Agentic Program Repaircited by 3
  22. 2024MOSS: Enabling Code-Driven Evolution and Context Management for AI Agentscited by 2
  23. 2025LinkAnchor: An Autonomous LLM-Based Agent for Issue-to-Commit Link Recoverycited by 2
  24. 2026LIDL: LLM Integration Defect Localization via Knowledge Graph-Enhanced Multi-Agent Analysiscited by 2
  25. 2026SVRepair: Structured Visual Reasoning for Automated Program Repaircited by 2
  26. 2026FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repaircited by 2
  27. 2026Credit-Budgeted ICPC-Style Coding: When Agents Must Pay for Every Decisioncited by 2
  28. 2026ARISE: A Repository-level Graph Representation and Toolset for Agentic Program Repair and Fault Localizationcited by 2
  29. 2026What Context Does a Coding Agent Actually Need to Act?cited by 2
  30. 2026PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agentscited by 2
  31. 2026Turning Interaction History into Execution State: A Runtime Layer for Long-Horizon Coding Agentscited by 2
  32. 2026Independent Patch Verification for Coding Agents with a Bidirectional Reconstruct-and-Verify Frameworkcited by 2
  33. 2025Towards Iterative End-to-End Software Development: A Feature-Driven Multi-Agent Frameworkcited by 1
  34. 2026ORACLE-SWE: Quantifying the Contribution of Oracle Information Signals on SWE Agentscited by 1
  35. 2026DeepDiscovery: A Location-Inference Framework for Task-Level Repository Understandingcited by 1
  36. 2026Writing Bug Reports for Software Repair Agents: What Information Matters Most?cited by 1
  37. 2026Effective and Efficient Context Retrieval via Partial Dependency Graph for Repository-Level Code Generationcited by 1
  38. 2026RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworkscited by 1

50 most cited of 58 All 58 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Lingxi: Repository-Level Issue Resolution Framework Enhanced by Procedural Knowledge Guided Scaling
  2. 2024MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution
  3. 2026XAgent: eXecution-guided Agentic AI for Effective Localization and Resolution of GitHub Issues
  4. 2026SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution
  5. 2026CodeTeam: An LLM-Powered Multi-Agent Framework for Repository-Level Code Generation
  6. 2026Know Before Fix: QA-Driven Repository Knowledge Acquisition for Software Issue Resolution
  7. 2026SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolution
  8. 2026FastContext: Training Efficient Repository Explorer for Coding Agents