Does code cleanliness affect coding agents? A controlled minimal-pair study
1–10 of 112 posts
Re: Does code cleanliness affect coding agents? A controlled minimal-pair study
#2"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 [...]"
Re: Does code cleanliness affect coding agents? A controlled minimal-pair study
#3In my experience, the delta in agent performance is substantial if the codebase is littered with dead code, redundant code, unreachable fallbacks, leaking abstractions and half-baked design patterns vs if the code is well-organized, with clear data flow, with good encapsulation and clean architecture. Like, I've seen all the frontier models have to do several rounds of code review / QA and fix when the code is bad vs just getting it right at the 1st/2nd attempt.
Re: Does code cleanliness affect coding agents? A controlled minimal-pair study
#4"agent pipelines that [...] clean a messy [repository]"
This feels like a terrible approach, sufficient to condemn the entire study.
Apparently half of the "minimal pairs" in this work were constructed in this way. I simply am not going to trust any conclusion that requires assuming these AI "cleaned" repos are in any way representative of actually-good codebases.
Re: Does code cleanliness affect coding agents? A controlled minimal-pair study
#5Even if agents can learn to navigate all the stubs and WET crap they leave behind do we really want a code base that no human can follow what's actually going on?
Re: Does code cleanliness affect coding agents? A controlled minimal-pair study
#6I can't imagine how it wouldn't. None of them can fit a real codebase in context and have to browse the code the same way a person would. Doing searches and reading files. If the files are in the places they would be expected to be and things are called what the model or a person would first guess to search then it gets found in the first attempt rather than requiring a deep search and multiple attempts.
Re: Does code cleanliness affect coding agents? A controlled minimal-pair study
#7Even if agents can learn to navigate all the stubs and WET crap they leave behind do we really want a code base that no human can follow what's actually going on?
Even if the agent does everything, English is an imprecise description of what the code does.
So I personally at a minimum will want to talk “in code” about what code does.
Re: Does code cleanliness affect coding agents? A controlled minimal-pair study
#8In my experience, the delta in agent performance is substantial if the codebase is littered with dead code, redundant code, unreachable fallbacks, leaking abstractions and half-baked design patterns vs if the code is well-organized, with clear data flow, with good encapsulation and clean architecture. Like, I've seen all the frontier models have to do several rounds of code review / QA and fix when the code is bad vs…
I was reading your comment, agreeing with it but still feeling why this is a bad comment. It just occurred to me that an anecdotal statement like this is the antithesis of scientific discourse. We have a paper here, trying to answer a question, and anecdotal testimonials can only harm the discussion by biasing readers without adding anything of value to let anyone objectively conclude anything on the problem.
The most useful discussion would be if we all read the paper and critique its methodology or results.
Re: Does code cleanliness affect coding agents? A controlled minimal-pair study
#9"agent pipelines that [...] clean a messy [repository]" This feels like a terrible approach, sufficient to condemn the entire study. Apparently half of the "minimal pairs" in this work were constructed in this way. I simply am not going to trust any conclusion that requires assuming these AI "cleaned" repos are in any way representative of actually-good codebases.
Would you trust clean repos that are messed up by AI?
Re: Does code cleanliness affect coding agents? A controlled minimal-pair study
#10Another consideration: written by hand, the trade-off of development velocity vs well organised code means that it can be worth taking some tech debt now in order to deliver some value now. (Especially when prototyping etc.).
With coding agents, agents can produce code quicker. The same trade-off still applies.. but, the time it takes an LLM coding agent to write well organised code is still going to be quicker than the time it takes me to write scrappy code.