Does code cleanliness affect coding agents? A controlled minimal-pair study
Why CEREBRO kept it
Code cleanliness impact on coding agents. Direct research on agent behavior.
The text below is an automated extraction of the article at https://arxiv.org/abs/2605.20049, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (arxiv.org).
Computer Science > Software Engineering [Submitted on 19 May 2026] Title:Does Code Cleanliness Affect Coding Agents? A Controlled Minimal-Pair Study View PDF HTML (experimental)Abstract:As autonomous coding agents see rapid adoption, their evaluation has primarily focused on task completion rates holding the target codebase fixed. This leaves a critical question unanswered: does the structural and stylistic quality, or ``cleanliness'' of the underlying code affect an agent's ability to navigate and modify it? To isolate the effect of code cleanliness from agent capability, we introduce a
Community take
Study's minimal pairs are fundamentally flawed—using AI-cleaned repos as the 'clean' condition instead of human-organized codebases invalidates its conclusion that cleanliness doesn't affect agent performance.
Backlinks
Appeared in 1 briefing