# Human-AI Synergy in Agentic Code Review

arXiv: https://arxiv.org/abs/2603.15911 · HTML: https://mlsanity.com/paper/2603.15911/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 11 of its 48 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 11 of 11)

- [On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub](https://mlsanity.com/paper/2509.14745/) (2025)
- [Can LLMs Replace Manual Annotation of Software Engineering Artifacts?](https://mlsanity.com/paper/2408.05534/) (2024)
- [Agentic Software Engineering: Foundational Pillars and a Research Roadmap](https://mlsanity.com/paper/2509.06216/) (2025)
- [Code Review Automation: Strengths and Weaknesses of the State of the Art](https://mlsanity.com/paper/2401.05136/) (2024)
- [DeepCRCEval: Revisiting the Evaluation of Code Review Comment Generation](https://mlsanity.com/paper/2412.18291/) (2024)
- [Generative AI for Pull Request Descriptions: Adoption, Impact, and Developer Interventions](https://mlsanity.com/paper/2402.08967/) (2024)
- [Does AI Code Review Lead to Code Changes? A Case Study of GitHub Actions](https://mlsanity.com/paper/2508.18771/) (2025)
- [What Types of Code Review Comments Do Developers Most Frequently Resolve?](https://mlsanity.com/paper/2510.05450/) (2025)
- [Identifying Unmaintained Projects in GitHub](https://mlsanity.com/paper/1809.04041/) (2018)
- [What helped, and what did not? An Evaluation of the Strategies to Improve Continuous Integration](https://mlsanity.com/paper/2102.06666/) (2021)
- [How Do Developers Use Code Suggestions in Pull Request Reviews?](https://mlsanity.com/paper/2502.04835/) (2025)

## Built on by (most cited first, 3 of 3)

- [The Productivity-Reliability Paradox: Specification-Driven Governance for AI-Augmented Software Development](https://mlsanity.com/paper/2605.01160/) (2026)
- [Rethinking Code Review in the Age of AI: A Vision for Agentic Code Review](https://mlsanity.com/paper/2605.17548/) (2026)
- [From Human-Centric to Agentic Code Review: The Impact of Different Generations of Generative AI Technology on Review Quality](https://mlsanity.com/paper/2607.13196/) (2026)

## Abstract (arXiv)

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.