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

arXiv: https://arxiv.org/abs/2605.20049 · HTML: https://mlsanity.com/paper/2605.20049/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 10 of its 15 references that are in the map.
- First posted on arXiv 19 May 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 10 of 10)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks](https://mlsanity.com/paper/2604.22750/) (2026)
- [Agentic Much? Adoption of Coding Agents on GitHub](https://mlsanity.com/paper/2601.18341/) (2026)
- [SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks](https://mlsanity.com/paper/2603.24755/) (2026)
- [SWE-Effi: Re-Evaluating Software AI Agent System Effectiveness Under Resource Constraints](https://mlsanity.com/paper/2509.09853/) (2025)
- [Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering](https://mlsanity.com/paper/2601.14470/) (2026)
- [When Names Disappear: Revealing What LLMs Actually Understand About Code](https://mlsanity.com/paper/2510.03178/) (2025)
- [Measuring how changes in code readability attributes affect code quality evaluation by Large Language Models](https://mlsanity.com/paper/2507.05289/) (2025)

## Built on by (most cited first, 1 of 1)

- [Can Agents Design Libraries for Agents?](https://mlsanity.com/paper/2609.36730/) (2026)

## Abstract (arXiv)

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.