From Human-Centric to Agentic Code Review: The Impact of Different Generations of Generative AI Technology on Review Quality

2026-07-14

AI Summary

This study addresses the lack of empirical analysis on how generative AI impacts efficiency and code quality across the evolving spectrum of code review—from human-led, LLM-assisted workflows to active participation by AI agents. Leveraging a large-scale dataset of 1.02 million pull requests from 207 GitHub projects, the authors systematically compare three collaboration paradigms through data mining and sequential modeling of review interactions. Their findings reveal that AI agent involvement—particularly when initiating reviews or operating in multi-agent teams—significantly enhances review efficiency but does not improve code quality. The human–AI collaborative paradigm emerges as the key driver of efficiency gains, with the study further identifying three archetypal AI adoption practices and elucidating the underlying mechanisms of human–AI interaction sequences.

Abstract

Code review helps maintain software quality before code integration, but it also imposes a substantial workload on human reviewers. As generative artificial intelligence becomes part of software development, code review is shifting from a primarily human review process toward AI-supported review processes in which large language model (LLM) reviewers and AI agent reviewers participate alongside human reviewers. However, we still lack empirical evidence on how this transition affects review efficiency and review quality. In this paper, we study 1.02 million reviewed pull requests from 207 GitHub projects that transition across three code review eras: human-centric review, LLM-assisted review, and agentic code review. We identify three AI reviewer adoption practices: Gradual AI Adoption, Rapid LLM Adoption, and Rapid AI Agent Adoption. We further model pull request review discussions as reviewer interaction sequences to characterize how human, LLM, and AI agent reviewers collaborate during the review process. Our results show that agent-involved collaboration patterns, especially reviews initiated by AI agents or involving multiple AI agents, are associated with faster review decisions under Gradual AI Adoption and Rapid AI Agent Adoption. However, these efficiency gains do not translate into better review quality. We also find that review activity and pull request type remain important across eras, while human-AI collaboration patterns become the strongest explanatory factor for review efficiency once LLM and AI agent reviewers participate. These findings provide empirical guidance for designing AI-supported code review processes that improve efficiency without weakening review quality.

Problem

• code review
• generative AI
• review quality
• AI agents
• LLM

Innovation

• agentic code review
• generative AI
• LLM-assisted review
• human-AI collaboration
• empirical software engineering