mlsanityData to 14 Oct 2026

CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases

arXiv 2408.03910 ↗First posted 7 Aug 2024cs.SE cs.AI cs.CLcited by 65

Not on the map. Why?

Cited by 32 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Large Language Models (LLMs) excel in stand-alone code tasks like HumanEval and MBPP, but struggle with handling entire code repositories. This challenge has prompted research on enhancing LLM-codebase interaction at a repository scale. Current solutions rely on similarity-based retrieval or manual tools and APIs, each with notable drawbacks. Similarity-based retrieval often has low recall in complex tasks, while manual tools and APIs are typically task-specific and require expert knowledge, reducing their generalizability across diverse code tasks and real-world applications. To mitigate these limitations, we introduce CodexGraph, a system that integrates LLM agents with graph database interfaces extracted from code repositories. By leveraging the structural properties of graph databases and the flexibility of the graph query language, CodexGraph enables the LLM agent to construct and execute queries, allowing for precise, code structure-aware context retrieval and code navigation. We assess CodexGraph using three benchmarks: CrossCodeEval, SWE-bench, and EvoCodeBench. Additionally, we develop five real-world coding applications. With a unified graph database schema, CodexGraph demonstrates competitive performance and potential in both academic and real-world environments, showcasing its versatility and efficacy in software engineering. Our application demo: https://github.com/modelscope/modelscope-agent/tree/master/apps/codexgraph_agent.

Key facts. Cited by 65 papers in the map (data through 14 Oct 2026). Builds on 39 of its 58 references that are in the map. First posted on arXiv 7 Aug 2024.

Builds on

39 of 58 references.

References · 39

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  4. 2021Program Synthesis with Large Language Modelscited by 3,637
  5. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  6. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  7. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
  8. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  9. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,737
  10. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  11. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
  12. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
27 more
  1. 2024A Survey on Large Language Models for Code Generationcited by 658
  2. 2024Executable Code Actions Elicit Better LLM Agentscited by 564
  3. 2022Visual Programming: Compositional visual reasoning without trainingcited by 516
  4. 2024Agentless: Demystifying LLM-based Software Engineering Agentscited by 421
  5. 2023RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generationcited by 367
  6. 2022UniXcoder: Unified Cross-Modal Pre-training for Code Representationcited by 361
  7. 2023RepoBench: Benchmarking Repository-Level Code Auto-Completion Systemscited by 353
  8. 2024DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligencecited by 331
  9. 2024CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challengescited by 282
  10. 2024AutoCodeRover: Autonomous Program Improvementcited by 278
  11. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answeringcited by 223
  12. 2023CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completioncited by 183
  13. 2023CodePlan: Repository-level Coding using LLMs and Planningcited by 140
  14. 2024CodeR: Issue Resolving with Multi-Agent and Task Graphscited by 91
  15. 2024EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositoriescited by 72
  16. 2024RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generationcited by 70
  17. 2024MASAI: Modular Architecture for Software-engineering AI Agentscited by 49
  18. 2023RepoFusion: Training Code Models to Understand Your Repositorycited by 40
  19. 2024Dataflow-Guided Retrieval Augmentation for Repository-Level Code Completioncited by 40
  20. 2024GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Modelcited by 40
  21. 2024CodeS: Natural Language to Code Repository via Multi-Layer Sketchcited by 28
  22. 2023DB-GPT: Empowering Database Interactions with Private Large Language Modelscited by 27
  23. 2023ModelScope-Agent: Building Your Customizable Agent System with Open-source Large Language Modelscited by 24
  24. 2024Class-Level Code Generation from Natural Language Using Iterative, Tool-Enhanced Reasoning over Repositorycited by 14
  25. 2024R2C2-Coder: Enhancing and Benchmarking Real-world Repository-level Code Completion Abilities of Code Large Language Modelscited by 9
  26. 2024UniOQA: A Unified Framework for Knowledge Graph Question Answering with Large Language Modelscited by 5
  27. 2024On The Importance of Reasoning for Context Retrieval in Repository-Level Code Editingcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 25; 2026: 36.

65 papers.

Sort:

By area:

  1. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 172
  2. 2024RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graphcited by 91
  3. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 88
  4. 2025LocAgent: Graph-Guided LLM Agents for Code Localizationcited by 86
  5. 2024Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvementcited by 61
  6. 2026Code as Agent Harnesscited by 47
  7. 2025RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Codecited by 30
  8. 2026MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discoverycited by 28
  9. 2025Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approachescited by 23
  10. 2025Improving Code Localization with Repository Memorycited by 20
  11. 2026In Line with Context: Repository-Level Code Generation via Context Inliningcited by 18
  12. 2025GraphCodeAgent: Dual Graph-Guided LLM Agent for Retrieval-Augmented Repo-Level Code Generationcited by 17
38 more
  1. 2025MAPRO: Recasting Multi-Agent Prompt Optimization as Maximum a Posteriori Inferencecited by 17
  2. 2025From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligencecited by 15
  3. 2025Agentic AI Systems Applied to tasks in Financial Services: Modeling and model risk management crewscited by 12
  4. 2025Risk Assessment Framework for Code LLMs via Leveraging Internal Statescited by 9
  5. 2026SGAgent: Suggestion-Guided LLM-Based Multi-Agent Framework for Repository-Level Software Repaircited by 9
  6. 2025Agent That Debugs: Dynamic State-Guided Vulnerability Repaircited by 7
  7. 2025RANGER -- Repository-Level Agent for Graph-Enhanced Retrievalcited by 7
  8. 2025AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Constructioncited by 7
  9. 2025Agentic Software Issue Resolution with Large Language Models: A Surveycited by 6
  10. 2026Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCPcited by 6
  11. 2025Actions Speak Louder than Prompts: A Large-Scale Study of LLMs for Graph Inferencecited by 5
  12. 2025AtomWorld: A Benchmark for Evaluating Spatial Reasoning in Large Language Models on Crystalline Materialscited by 5
  13. 2024Context-Augmented Code Generation Using Programming Knowledge Graphscited by 4
  14. 2025Knowledge Graph Based Repository-Level Code Generationcited by 4
  15. 2025Gistify! Codebase-Level Understanding via Runtime Executioncited by 4
  16. 2026SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolutioncited by 4
  17. 2025CoRet: Improved Retriever for Code Editingcited by 3
  18. 2026Beyond Code Snippets: Benchmarking LLMs on Repository-Level Question Answeringcited by 3
  19. 2026LLM Agents Can See Code Repositoriescited by 3
  20. 2026Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Modelcited by 3
  21. 2026LIDL: LLM Integration Defect Localization via Knowledge Graph-Enhanced Multi-Agent Analysiscited by 2
  22. 2026LogicLens: Leveraging Semantic Code Graph to explore Multi Repository large systemscited by 2
  23. 2026PseudoAct: Leveraging Pseudocode Synthesis for Flexible Planning and Action Control in Large Language Model Agentscited by 2
  24. 2026ARISE: A Repository-level Graph Representation and Toolset for Agentic Program Repair and Fault Localizationcited by 2
  25. 2026LARGER: Lexically Anchored Repository Graph Exploration and Retrievalcited by 2
  26. 2025HDLxGraph: Bridging Large Language Models and HDL Repositories via HDL Graph Databasescited by 1
  27. 2025Hound: Relation-First Knowledge Graphs for Complex-System Reasoning in Security Auditscited by 1
  28. 2026MHRC-Bench: A Multilingual Hardware Repository-Level Code Completion benchmarkcited by 1
  29. 2026KCoEvo: A Knowledge Graph Augmented Framework for Evolutionary Code Generationcited by 1
  30. 2026ReCUBE: Evaluating Repository-Level Context Utilization in Code Generationcited by 1
  31. 2026CODENS: Transforming Code Changes into Living, Accessible, and Queryable Documentationcited by 1
  32. 2026EA-Graph: Artifact-Anchored Verification Memory for Coding Agents under Upstream Driftcited by 1
  33. 2026Executable Code Knowledge: Code as a Native, Validation-Carrying Knowledge Representation for AI Coding Agentscited by 1
  34. 2026SecProbe: Adaptive Evaluation of Coding Agents on Cybersecurity Vulnerabilitiescited by 1
  35. 2025From Benchmark Data To Applicable Program Repair: An Experience Reportcited by 0
  36. 2025DeepCodeSeek: Real-Time API Retrieval for Context-Aware Code Generationcited by 0
  37. 2025Autonomous Issue Resolver: Towards Zero-Touch Code Maintenancecited by 0
  38. 2025One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agentscited by 0

50 most cited of 65 All 65 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks
  2. 2024CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval
  3. 2026Reliable Graph-RAG for Codebases: AST-Derived Graphs vs LLM-Extracted Knowledge Graphs
  4. 2025GRACE: Graph-Guided Repository-Aware Code Completion through Hierarchical Code Fusion
  5. 2026Effective and Efficient Context Retrieval via Partial Dependency Graph for Repository-Level Code Generation
  6. 2026Are you Synthesizing or Recalling? Evaluating LLMs on Algorithmic Code Retrieval
  7. 2025Prometheus: Towards Long-Horizon Codebase Navigation for Repository-Level Problem Solving
  8. 2024CodeNav: Beyond tool-use to using real-world codebases with LLM agents