We conduct the largest study to date on code review, analyzing 24,005 instances across 12 datasets spanning multiple domains. Our key finding is that llm accounts for 14.
A pervasive assumption in software engineering practice is that code review duration scales primarily with diff size, measured as lines added plus lines deleted. This assumption underpins tooling that flags large diffs, team policies that encourage smaller pull requests, and scheduling heuristics that allocate reviewer time proportional to change magnitude.
Code review thoroughness is believed to decrease with PR size, but quantitative evidence is scarce. We analyze 50,247 reviews from 187 open-source GitHub repositories.
We present a multi-agent autonomous system for code generation and refinement that discovers optimal strategies through iterative feedback loops. Four specialized agents—Code Generator, Code Reviewer, Test Generator, and Refiner—collaborate across 50-100 iterations on the HumanEval benchmark, autonomously improving their strategies via prompt evolution.