Automated Code Review

Ask about this topic

Overview

Automated code review studies how software tools can inspect code changes for bugs, security risks, policy violations, and readiness to merge. Systems combine static analysis and tests with large language models that interpret diffs, repository context, and developer intent; some use multiple agents or staged checks to filter findings. Benchmarks based on real pull requests increasingly test not only defect detection but also false positives, security attacks, and how issues change over multiple review rounds. A central challenge is making reviews technically reliable and grounded in evidence while keeping them useful to developers and preserving human oversight.

Latest papers

CardsList

50 papers13 papers in the last four weeks, with none the four weeks before. 0.1% of all new papers.

  1. CIVER: Causal Intervention Verification for Reliable Code Review

    Oct 26, 2026Xinyuan Song, Hasibul Haque, Jay Somasundaram +3Automated Code ReviewLLM Agent Reliability

    Causal Dynamics Lab USA

  2. CyberDual: AI Attackers versus AI Code Reviewers in Real Software Maintenance

    Oct 25, 2026Chenyuan Yang, Hwiwon Lee, Jongseong Kim +4AI Agent Security BenchmarksAutomated Code Review

  3. Can Agentic Code Review Catch Vulnerabilities Before They Are Merged?

    Oct 24, 2026Yihan Yang, Chenyuan Yang, Zijie Zhao +5AI Agent Security BenchmarksAutomated Code Review

    University of Illinois Urbana-Champaign · Quantum AI & Cyber Security Institute, FPT Corporation; work done during an internship at UIUC.

  4. VeeReview: Measuring Build-Verify Pairs in Agent-Authored Pull Requests from a V-Model Perspective

    Oct 21, 2026Gabriel Dautovi, Jie JW WuAutomated Code ReviewAutomated Agent Evaluation

    Department of Computer Science, Michigan Technological University, Houghton, Michigan, United States

  5. SPLASH: Contrastive Audit Pressure for Detecting and Localizing Security Hallucinations in Generated Code

    Oct 19, 2026Mirza Masfiqur Rahman, MD Ajwad Akil, Imtiaz Karim +3LLM SecuritySoftware Vulnerability Detection

    Purdue University, USA · University of Texas at Dallas, USA · Cisco Research, USA

  6. Peer Pressure: Execution-Verified Co-Evolution of Attacker and Defender Populations for Code Security

    Oct 17, 2026Khushbu Pahwa, Yubin Ge, Daniele Bonadiman +2AI Agent SecurityAdversarial Training

    AWS AI

  7. CodeHealth Predicts the Token Cost of Agentic Code Review: A Pre-Registered Study of 465 Agent-Authored Pull Requests

    Oct 15, 2026Lo Gullstrand Heander, Markus Borg, Emma Söderberg +1Software EngineeringAutomated Code Review

    Lund University, Lund, Sweden · CodeScene AB, Malmö, Sweden

  8. Co-Modifying Application Code and Deployment Infrastructure: A Causal Study of AI Agent Pull Requests

    Oct 9, 2026Mohammad Wathiq Soualhi, Basem SuleimanSoftware Engineering AgentsAI Coding Agents

    Independent Researcher, Malaysia · University of New South Wales, Australia

  9. SWE-Duel: Towards a Self-Scaling Arena for Coding Agents

    Oct 8, 2026Wei Minn, Zhensu Sun, Lwin Khin Shar +1Benchmark DesignCoding Agents

    School of Computing and Information Systems Singapore Management University

  10. Cross-Provider Review as a Runtime Contract for Coding Agents: A Controlled Pilot and Fault-Injection Study

    Oct 7, 2026Bowen Xu, Boyu ChenCoding AgentsRuntime Enforcement for AI Agents

    Department of Biology, Stanford University, Stanford, CA, USA · Institute of Health Informatics, University College London, London, UK

  11. A Case Study in Assuring AI-Written Software

    Oct 6, 2026Lindsey Ferris, Sierra BonillaAI Agent ReliabilityAI Assurance

    Independent Researcher · University College London London, United Kingdom

  12. When Does a Second Model Help? Cross-Model Review in LLM Verification

    Oct 1, 2026Tae-Eun SongLLM EvaluationLanguage Model Error Detection

    Daejeon Jungang Cheonggua Co., Ltd.

  13. Groundability, Not Scale Alone: When Weak Reviewers Can Audit Strong Coding Agents

    Oct 1, 2026Junyu Guo, Shangding Gu, Ming Jin +1AI Agent AuditingCode Generation Evaluation

    University of California, Berkeley · Virginia Tech

  14. CRJudgeBench: Can AI Detect Plausible but Invalid Code Reviews?

    Sep 29, 2026Yue Pan, Jiawei Li, Ziyuan Zhang +2LLM EvaluationLLM-as-a-Judge

    University College London · Amazon · Zhejiang University

  15. From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench

    Aug 27, 2026Dewu Zheng, Yanlin Wang, Xiwen Wang +5Automated Code ReviewSoftware Engineering

    Sun Yat-sen University, Zhuhai Key Laboratory of Trusted Large Language Models, Zhuhai, China · Chongqing University, Chongqing, China · Huawei Cloud Computing Technologies Co., Ltd., Dongguan, China

  16. Adversarial Review: Structured Disagreement for Grounded Agentic Code Review

    Aug 16, 2026Eric S. Qiu, Joyce GillAutomated Code ReviewMulti-Agent Coding

    Cornell University · Stanford University

  17. Activation Probes Surface Code-Security Signals that the Model's Output Misses

    Aug 10, 2026Ivan WiryadiLLM AuditingSoftware Vulnerability Detection

    Independent.

  18. When Policies Change Probabilities: Modular Decision-Making for LLM Code Review

    Aug 2, 2026Rasvik Kudum, Max Corbett, Hitansh Paliwal +3LLM EvaluationLLM Decision-Making

  19. From Code Review to Code Critique: Intent, Drift, and Spotlight for AI-Generated Diffs at Scale

    Jul 31, 2026Chandra Maddila, Mashrur Rashik, Euna Mehnaz Khan +4Automated Code ReviewAI-Assisted Software Development

    Meta, USA · †Concordia University, Montreal, Canada

  20. Evaluating the Impact of Explainable AI on Trust in AI-Assisted Code Review

    Jul 27, 2026Zhenhan Gao, Marvin Muñoz Barón, Umm-e Habiba +2Explainable Artificial IntelligenceAutomated Code Review

    Technical University of Munich, Heilbronn, Germany · University of Hohenheim, Hohenheim, Germany

  21. Code Monitor Red Teaming for Public-Test-Passing Code

    Jul 23, 2026Junchi Liao, Jiawen Deng, Fuji RenLLM AuditingCode Generation Evaluation

    University of Electronic Science and Technology of China Chengdu, China

  22. Cross-Model LLM Code Review: Should you use Claude to review Codex or vice versa?

    Jul 22, 2026Zuodong Xiang, Yike Zhang, YueMing Zhang +1Code Generation EvaluationAutomated Code Review

    University of California, Davis USA · Johns Hopkins University USA · California State University, Long Beach USA

  23. They'll Verify. They Just Won't Act. How Authority Framing and Laundered Code Turn a Trusted Agentic CI/CD Pipeline Into an Attack Surface

    Jul 21, 2026Yohann SidotLLM Agent SecurityIndirect Prompt Injection

    Senthex Research

  24. Is Agentic Code Review Helpful? Mining Developers' Feedback to CodeRabbit Reviews in the Wild

    Jul 3, 2026Hong Yi Lin, Mingzhao Liang, Kla Tantithamthavorn +1Automated Code Review

    The University of Melbourne, Melbourne, Victoria, Australia · Monash University, Melbourne, Victoria, Australia

  25. A Preliminary Study on Explaining Risk of Code Changes using LLM-Based Prediction Models

    Jul 2, 2026Yalin Liu, Kosay Jabre, Rui Abreu +10Automated Code Review

    Meta Platforms, Inc. · Concordia University

  26. Steerability via constraints: a substrate for scalable oversight of coding agents

    Jul 2, 2026Thomas WinningerScalable OversightCoding Agents

    Télécom SudParis, Évry-Courcouronnes, France · ENS Paris-Saclay, Gif-sur-Yvette, France

  27. When AI Reviews Its Own Code: Recursive Self-Training Collapse in Code LLMs

    Jun 26, 2026Xinyuan Song, Zekun Cai, Liang ZhaoSelf-TrainingModel Collapse

    Emory University, Atlanta, GA, USA · The University of Tokyo, Tokyo, Japan · LocationMind, Tokyo, Japan

  28. SEVRA-BENCH: Social Engineering of Vulnerabilities in Review Agents

    Jun 11, 2026Rui Melo, Riccardo Fogliato, Sean Zhou +2Software Vulnerability DetectionAI Agent Security

    1Carnegie Mellon University · 2Microsoft Core AI · 3Independent Researcher +1

  29. Automating Low-Risk Code Review at Meta: RADAR, Risk Calibration, and Review Efficiency

    May 28, 2026Chris Adams, Arjun Singh Banga, Parveen Bansal +28Automated Code ReviewAI-Assisted Software Development

    Meta · USA, UK, Canada

  30. Beyond Summaries: Structure-Aware Labeling of Code Changes with Large Language Models

    May 25, 2026Bar Weiss, Antonio Abu-Nassar, Adi Sosnovich +1Automated Code Review

    Viterbi Faculty of Electrical and Computer Engineering Technion, Haifa, Israel · IBM Research Haifa, Israel