Does Code Cleanliness Affect Coding Agents? A Controlled Minimal-Pair Study

2026-05-19

AI Summary

This study investigates whether code cleanliness—encompassing structural and stylistic quality—affects the comprehension and modification capabilities of autonomous programming agents. To this end, the authors introduce a novel bidirectional minimal-pair methodology that generates functionally equivalent code pairs differing only in cleanliness, using static analysis rules and cognitive complexity metrics to control for confounding variables. Agent behavior is evaluated at the real API interface level via hidden tests. Across 660 experiments, while task success rates remain unaffected, cleaner code consistently reduces token consumption by 7–8% and decreases repeated file accesses by 34%, demonstrating that code cleanliness significantly lowers computational overhead and enhances navigation efficiency for autonomous agents.

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 an evaluation protocol built around minimal pairs: repositories that match on architecture, dependencies, and external behaviour, but differ on static-analysis rule violations and cognitive complexity. The pairs are constructed in both directions, by agent pipelines that either degrade a clean repository or clean a messy one. We author 33 tasks across six such pairs, evaluated through hidden tests at the application's public surface. Across 660 trials with Claude Code, code cleanliness does not change the agent's pass rate. However, it substantially alters the agent's operational footprint: agents working on cleaner code use 7 to 8% fewer tokens and reduce file revisitations by 34%. Our findings suggest that traditional maintainability principles remain highly relevant in the era of AI-driven development, shaping the computational cost and navigational efficiency of coding agents. Code cleanliness joins model choice, harness, and prompting as a factor that materially affects agent behaviours.

Problem

• code cleanliness
• coding agents
• code quality
• autonomous coding
• software maintainability

Innovation

• code cleanliness
• coding agents
• minimal-pair study
• cognitive complexity
• agent efficiency