mlsanityData to 7 Oct 2026

CodeAgent: Autonomous Communicative Agents for Code Review

arXiv 2402.02172 ↗First posted 3 Feb 2024cs.SEcited by 33

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

Code review, which aims at ensuring the overall quality and reliability of software, is a cornerstone of software development. Unfortunately, while crucial, Code review is a labor-intensive process that the research community is looking to automate. Existing automated methods rely on single input-output generative models and thus generally struggle to emulate the collaborative nature of code review. This work introduces tool, a novel multi-agent Large Language Model (LLM) system for code review automation. CodeAgent incorporates a supervisory agent, QA-Checker, to ensure that all the agents' contributions address the initial review question. We evaluated CodeAgent on critical code review tasks: (1) detect inconsistencies between code changes and commit messages, (2) identify vulnerability introductions, (3) validate code style adherence, and (4) suggest code revision. The results demonstrate CodeAgent's effectiveness, contributing to a new state-of-the-art in code review automation. Our data and code are publicly available (urlhttps://github.com/Code4Agent/codeagent).

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 27 of its 54 references that are in the map. First posted on arXiv 3 Feb 2024.

Builds on

27 of 54 references.

References · 27

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  3. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  4. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  5. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  6. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 890
  7. 2020GraphCodeBERT: Pre-training Code Representations with Data Flowcited by 600
  8. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 580
  9. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agentscited by 329
  10. 2023Large Language Models as Tool Makerscited by 293
  11. 2020Deep Learning based Vulnerability Detection: Are We There Yet?cited by 142
  12. 2023MetaAgents: Large Language Model Based Agents for Decision-Making on Teamingcited by 85
15 more
  1. 2023Is ChatGPT the Ultimate Programming Assistant -- How far is it?cited by 72
  2. 2022Using Pre-Trained Models to Boost Code Review Automationcited by 63
  3. 2021Towards Automating Code Review Activitiescited by 54
  4. 2023Multi-Party Chat: Conversational Agents in Group Settings with Humans and Modelscited by 53
  5. 2023LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuningcited by 47
  6. 2023Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agentscited by 41
  7. 2021NL-EDIT: Correcting semantic parse errors through natural language interactioncited by 33
  8. 2020Deep Just-In-Time Inconsistency Detection Between Comments and Source Codecited by 20
  9. 2019CORE: Automating Review Recommendation for Code Changescited by 14
  10. 2023Generation-based Code Review Automation: How Far Are We?cited by 9
  11. 2021A Systematic Literature Review and Taxonomy of Modern Code Reviewcited by 7
  12. 2022Is this Change the Answer to that Problem? Correlating Descriptions of Bug and Code Changes for Evaluating Patch Correctnesscited by 7
  13. 2023Just-in-Time Detection of Silent Security Patchescited by 7
  14. 2022Less is More: Supporting Developers in Vulnerability Detection during Code Reviewcited by 6
  15. 2022A Systematic Literature Review on the Impact of Formatting Elements on Code Legibilitycited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 14; 2026: 18.

33 papers.

Sort:

By area:

  1. 2024A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Applicationcited by 54
  2. 2025Reinforce LLM Reasoning through Multi-Agent Reflectioncited by 26
  3. 2025An Empirical Study of Agent Developer Practices in AI Agent Frameworkscited by 14
  4. 2025From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligencecited by 13
  5. 2025FinSight: Towards Real-World Financial Deep Researchcited by 9
  6. 2025SimuGen: Multi-modal Agentic Framework for Constructing Block Diagram-Based Simulation Modelscited by 7
  7. 2025CallNavi, A Challenge and Empirical Study on LLM Function Calling and Routingcited by 6
  8. 2025AgentBay: A Hybrid Interaction Sandbox for Seamless Human-AI Intervention in Agentic Systemscited by 5
  9. 2026AACR-Bench: Evaluating Automatic Code Review with Holistic Repository-Level Contextcited by 5
  10. 2025Using LLMs in Generating Design Rationale for Software Architecture Decisionscited by 4
  11. 2025Issue-Oriented Agent-Based Framework for Automated Review Comment Generationcited by 4
  12. 2025DRAFT-RL: Multi-Agent Chain-of-Draft Reasoning for Reinforcement Learning-Enhanced LLMscited by 4
21 more
  1. 2026Code Review Agent Benchmarkcited by 4
  2. 2026SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Reviewcited by 4
  3. 2025DART: Leveraging Multi-Agent Disagreement for Tool Recruitment in Multimodal Reasoningcited by 3
  4. 2026CR-Bench: Evaluating the Real-World Utility of AI Code Review Agentscited by 3
  5. 2026The End of Code Review: Coding Agents Supersede Human Inspectioncited by 3
  6. 2025When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?cited by 2
  7. 2026AgenticSCR: An Autonomous Agentic Secure Code Review for Immature Vulnerabilities Detectioncited by 2
  8. 2026LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Reviewcited by 2
  9. 2026Rethinking Code Review in the Age of AI: A Vision for Agentic Code Reviewcited by 1
  10. 2026SEVRA-BENCH: Social Engineering of Vulnerabilities in Review Agentscited by 1
  11. 2025Automated detection of atomicity violations in large-scale systemscited by 0
  12. 2025Reformulate, Retrieve, Localize: Agents for Repository-Level Bug Localizationcited by 0
  13. 2026SWE-Spot: Building Small Repo-Experts with Repository-Centric Learningcited by 0
  14. 2026Assessing Spear-Phishing Website Generation in Large Language Model Coding Agentscited by 0
  15. 2026XSearch: Explainable Code Search via Concept-to-Code Alignmentcited by 0
  16. 2026AgensFlow: A Coordination-Policy Substrate for Multi-Agent Systemscited by 0
  17. 2026Converted, Not Equivalent: Benchmarking Codebase Conversion via Observational Equivalencecited by 0
  18. 2026More than a Judge: An Empirical Study of Agent-Human Interaction in Crowdsourced Testing Assessmentcited by 0
  19. 2026Archer: Towards Agentic Review for Compiler Optimizationscited by 0
  20. 2026From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Benchcited by 0
  21. 2026CRJudgeBench: Can AI Detect Plausible but Invalid Code Reviews?cited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges
  2. 2023AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation
  3. 2025DocAgent: A Multi-Agent System for Automated Code Documentation Generation
  4. 2026Using Agentic AI for contextualized and multifaceted code review at Ericsson
  5. 2026Is Agentic Code Review Helpful? Mining Developers' Feedback to CodeRabbit Reviews in the Wild
  6. 2026Human-AI Synergy in Agentic Code Review
  7. 2026Code Broker: A Multi-Agent System for Automated Code Quality Assessment
  8. 2024Agent-Driven Automatic Software Improvement