pith. sign in

arxiv: 2402.02172 · v5 · pith:H2U3T42Inew · submitted 2024-02-03 · 💻 cs.SE

CodeAgent: Autonomous Communicative Agents for Code Review

classification 💻 cs.SE
keywords codereviewcodeagentagentsautomationsoftwareaddressadherence
0
0 comments X
read the original abstract

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 (\url{https://github.com/Code4Agent/codeagent}).

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Delta-Based Neural Architecture Search: LLM Fine-Tuning via Code Diffs

    cs.LG 2026-05 unverdicted novelty 7.0

    Fine-tuned 7B LLMs generating unified diffs for neural architecture refinement achieve 66-75% valid rates and 64-66% mean first-epoch accuracy, outperforming full-generation baselines by large margins while cutting ou...

  2. Towards Personalizing Secure Programming Education with LLM-Injected Vulnerabilities

    cs.CR 2026-04 conditional novelty 7.0

    LLM agents inject CWEs into student-authored code to generate personalized security examples; in a 71-student deployment, participants rated them more relevant than textbook cases but quantitative differences remained...

  3. AgensFlow: A Coordination-Policy Substrate for Multi-Agent Systems

    cs.MA 2026-05 unverdicted novelty 6.0

    AgensFlow learns coordination policies from task trajectories and outperforms fixed pipelines on distributed-systems incident and security-advisory tasks.

  4. XSearch: Explainable Code Search via Concept-to-Code Alignment

    cs.SE 2026-05 unverdicted novelty 6.0

    XSearch achieves explainable code search by breaking queries into functional concepts and matching them directly to code statements, delivering large gains on out-of-distribution benchmarks.

  5. XSearch: Explainable Code Search via Concept-to-Code Alignment

    cs.SE 2026-05 unverdicted novelty 6.0

    XSearch achieves 15x gains on out-of-distribution code search benchmarks by replacing global embedding similarity with explicit concept-to-statement alignment.

  6. Memory in the Age of AI Agents

    cs.CL 2025-12 unverdicted novelty 6.0

    The paper maps agent memory research via three forms (token-level, parametric, latent), three functions (factual, experiential, working), and dynamics of formation/evolution/retrieval, plus benchmarks and future directions.

  7. The End of Code Review: Coding Agents Supersede Human Inspection

    cs.SE 2026-06 unverdicted novelty 4.0

    Coding agents have reached a capability level where human code review is no longer necessary because agents can serve every review goal more efficiently and the hybrid human-reviewer model does not scale.