Human-AI Synergy in Agentic Code Review

• URL: http://arxiv.org/abs/2603.15911v1
• Date: Mon, 16 Mar 2026 20:56:18 GMT
• Title: Human-AI Synergy in Agentic Code Review
• Abstract summary: We compare the feedback differences provided by human reviewers and AI agents.<n>Human reviewers exchange 11.8% more rounds when reviewing AI-generated code than human-written code.<n>Over half of unadopted suggestions from AI agents are either incorrect or addressed through alternative fixes by developers.
• Score: 3.7086626614863984
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Code review is a critical software engineering practice where developers review code changes before integration to ensure code quality, detect defects, and improve maintainability. In recent years, AI agents that can understand code context, plan review actions, and interact with development environments have been increasingly integrated into the code review process. However, there is limited empirical evidence to compare the effectiveness of AI agents and human reviewers in collaborative workflows. To address this gap, we conduct a large-scale empirical analysis of 278,790 code review conversations across 300 open-source GitHub projects. In our study, we aim to compare the feedback differences provided by human reviewers and AI agents. We investigate human-AI collaboration patterns in review conversations to understand how interaction shapes review outcomes. Moreover, we analyze the adoption of code suggestions provided by human reviewers and AI agents into the codebase and how adopted suggestions change code quality. We find that human reviewers provide additional feedback than AI agents, including understanding, testing, and knowledge transfer. Human reviewers exchange 11.8% more rounds when reviewing AI-generated code than human-written code. Moreover, code suggestions made by AI agents are adopted into the codebase at a significantly lower rate than suggestions proposed by human reviewers. Over half of unadopted suggestions from AI agents are either incorrect or addressed through alternative fixes by developers. When adopted, suggestions provided by AI agents produce significantly larger increases in code complexity and code size than suggestions provided by human reviewers. Our findings suggest that while AI agents can scale defect screening, human oversight remains critical for ensuring suggestion quality and providing contextual feedback that AI agents lack.

Related papers

• Evaluating the Impact of Explainable AI on Trust in AI-Assisted Code Review [3.08933193053743]
  We studied the influence of Explainable AI (XAI) on developer trust in AI-assisted code reviews.<n>We measured trust perceptions, agreement with the AI recommendation, the reasoning given for each decision, and the time taken.
  arXiv  Detail & Related papers  (2026-07-27T16:04:24Z)
• Code Review is a Conversation: Toward Conversational AI Review Assistants [7.335667281862373]
  We argue for conversational AI review assistants that participate in code review as interactive partners rather than static comment generators.<n>Such assistants should identify when conversation is needed, ask grounded questions, respond to developer explanations, summarize unresolved issues, help capture rationale, and know when to abstain or escalate to human reviewers.
  arXiv  Detail & Related papers  (2026-07-24T08:44:05Z)
• From Human-Centric to Agentic Code Review: The Impact of Different Generations of Generative AI Technology on Review Quality [3.7086626614863984]
  We study 1.02 million reviewed pull requests from 207 GitHub projects that transition across three code review eras.<n>Agent-involved collaboration patterns are associated with faster review decisions under Gradual AI Adoption and Rapid AI Agent Adoption.<n>These findings provide empirical guidance for designing AI-supported code review processes that improve efficiency without weakening review quality.
  arXiv  Detail & Related papers  (2026-07-14T18:48:20Z)
• The End of Code Review: Coding Agents Supersede Human Inspection [7.017303286271101]
  We argue that coding agents have crossed a threshold of capability at which traditional human code review is no longer a necessary component of a software quality pipeline.<n>Our argument rests on two claims: every stated goal of code review can be served by agents at lower cost and higher throughput.
  arXiv  Detail & Related papers  (2026-06-11T10:43:48Z)
• Code as Agent Harness [107.31925305395957]
  In emerging agentic systems, code is no longer only a target output.<n>Code increasingly serves as an operational substrate for agent reasoning, acting, environment modeling, and execution-based verification.<n>This survey provides a unified roadmap toward executable, verifiable, and stateful AI agent systems.
  arXiv  Detail & Related papers  (2026-05-18T17:59:03Z)
• Rethinking Code Review in the Age of AI: A Vision for Agentic Code Review [2.2807488730605296]
  We present a vision for an AI-powered code review workflow combining specialized agents with human-controlled quality.<n>We identify major open challenges for responsible adoption, including reliability, bias, privacy, automation bias, transparency, and evaluation.
  arXiv  Detail & Related papers  (2026-05-17T17:04:21Z)
• Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation [87.47155146067962]
  We provide a standardized evaluation harness that orchestrates parallel evaluations across hundreds of tasks.<n>We conduct three-dimensional analysis spanning models, scaffolds, and benchmarks.<n>Our analysis reveals surprising insights, such as higher reasoning effort reducing accuracy in the majority of runs.
  arXiv  Detail & Related papers  (2025-10-13T22:22:28Z)
• CoCoNUTS: Concentrating on Content while Neglecting Uninformative Textual Styles for AI-Generated Peer Review Detection [60.52240468810558]
  We introduce CoCoNUTS, a content-oriented benchmark built upon a fine-grained dataset of AI-generated peer reviews.<n>We also develop CoCoDet, an AI review detector via a multi-task learning framework, to achieve more accurate and robust detection of AI involvement in review content.
  arXiv  Detail & Related papers  (2025-08-28T06:03:11Z)
• Code Review as Decision-Making -- Building a Cognitive Model from the Questions Asked During Code Review [2.8299846354183953]
  We build a cognitive model of code review bottom up through thematic, statistical, temporal, and sequential analysis of the transcribed material.<n>The model shows how developers move through two phases during the code review; first an orientation phase to establish context and rationale, then an analytical phase to understand, assess, and plan the rest of the review.
  arXiv  Detail & Related papers  (2025-07-13T14:04:16Z)
• Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows [60.04362496037186]
  We present the first controlled study of developer interactions with coding agents.<n>We evaluate two leading copilot and agentic coding assistants.<n>Our results show agents can assist developers in ways that surpass copilots.
  arXiv  Detail & Related papers  (2025-07-10T20:12:54Z)
• The AI Imperative: Scaling High-Quality Peer Review in Machine Learning [49.87236114682497]
  We argue that AI-assisted peer review must become an urgent research and infrastructure priority.<n>We propose specific roles for AI in enhancing factual verification, guiding reviewer performance, assisting authors in quality improvement, and supporting ACs in decision-making.
  arXiv  Detail & Related papers  (2025-06-09T18:37:14Z)
• Do Comments and Expertise Still Matter? An Experiment on Programmers' Adoption of AI-Generated JavaScript Code [8.673467364360857]
  The adoption of AI-generated code was gauged by code similarity between AI-generated solutions and participants' submitted solutions.<n>Our findings revealed that, within the context of function-level programming tasks, the presence of comments significantly influences programmers' adoption of AI-generated code.
  arXiv  Detail & Related papers  (2025-03-14T14:42:51Z)
• Human and Machine: How Software Engineers Perceive and Engage with AI-Assisted Code Reviews Compared to Their Peers [4.734450431444635]
  We investigate how software engineers perceive and engage with Large Language Model (LLM)-assisted code reviews.<n>We found that engagement in code review is multi-dimensional, spanning cognitive, emotional, and behavioral dimensions.<n>Our findings contribute to a deeper understanding of how AI tools are impacting SE socio-technical processes.
  arXiv  Detail & Related papers  (2025-01-03T20:42:51Z)
• CodeAgent: Autonomous Communicative Agents for Code Review [12.163258651539236]
  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. Results demonstrate CodeAgent's effectiveness, contributing to a new state-of-the-art in code review automation.
  arXiv  Detail & Related papers  (2024-02-03T14:43:14Z)
• Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions [54.55334589363247]
  We study whether conveying information about uncertainty enables programmers to more quickly and accurately produce code. We find that highlighting tokens with the highest predicted likelihood of being edited leads to faster task completion and more targeted edits.
  arXiv  Detail & Related papers  (2023-02-14T18:43:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.