Skip to content
AI Atlas
PaperActive

Talking to Itself While Coding: What Makes Comments Help Code Generation?

arxiv.org/abs/2609.09242

Updated 50 min ago · first seen 11 Sept 2026

paper_01M294GKWAT3224G791NJ7MT4F

Published
11 Sept 2026
T1 · 50 min ago
arXiv
2609.09242
T1 · 50 min ago
Category
cs.SE
T1 · 50 min ago

Abstract

Large Language Models (LLMs) often generate natural-language comments while writing code, and these comments become part of the context used to generate the code that follows. However, it remains unclear which properties of comments affect code-generation performance. We study this question through observational analyses and controlled interventions. On LiveCodeBench, neither comment frequency nor broad comment intent reliably predicts pass@1. We then prefill weaker recipient models with comment blocks written by stronger source models, allowing us to separate comment surface form from the solution content they convey. Comments from source solutions that pass the tests raise recipient pass@1 by 17.2% on average. In contrast, comments describing failed solutions provide no reliable gain, while comments written for a different problem reduce pass@1 by 20.8%. Finally, across a wide range of models and prompt variants, most recipient models show no significant recovery of the external-comment gain, and the best case recovers only 24%. These results show that comments help code generation not merely because they are comments, but because they can provide correct solution content that prompting cannot reliably elicit.

Authors 5

Dangfeng Pan, Zhensu Sun, Cenyuan Zhang, David Lo, Xiaoning Du

Specification

Official page

Source:arXiv (Atom API + RSS)T1observed 50 min agohigh

Arxiv announce type
cross

Source:arXiv (Atom API + RSS)T1observed 50 min agohigh

arXiv id
2609.09242

Source:arXiv (Atom API + RSS)T1observed 50 min agohigh

Categories
cs.SE, cs.AI

Source:arXiv (Atom API + RSS)T1observed 50 min agohigh

PDF

Source:arXiv (Atom API + RSS)T1observed 50 min agohigh

Primary category
cs.SE

Source:arXiv (Atom API + RSS)T1observed 50 min agohigh

Published
11 Sept 2026

Source:arXiv (Atom API + RSS)T1observed 50 min agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

50 min ago

Conflicts

None