🛰️ Daily AI Frontier
‹ back to 2026-08-23

From Agent Behaviour to Agent-Friendly Documentation: An Empirical Study of How Coding Agents Discover, Read, and Write Technical Documentation

arXiv cs.SE LLM Agents Zhijun Gao, Jing Chen 2026-08-20
Representative image for From Agent Behaviour to Agent-Friendly Documentation: An Empirical Study of How Coding Agents Discover, Read, and Write Technical Documentation

TL;DR - An empirical study of more than 33,000 agentic pull requests and 557 coding-agent sessions finds that agents primarily use instruction files and working notes rather than conventional technical documentation. The results challenge assumptions that agent-friendly documentation reliably prompts action or validation.

  • Agent-facing artifacts represented 60.5% of documentation interactions, versus 10.6% for classical technical documentation and 1.3% for API references.
  • Evidence that documentation consultation leads to code editing was mixed: the adjacent transition probability was 0.002, while a stage-adjusted model found elevated odds (OR 1.33).
  • No explicit documentation-based validation sequence was observed; consultation correlated with less immediate testing (adjusted OR 0.39).
  • Consultation was usually self-initiated (70.2%), and code was touched before documentation 4.7 times more often in multi-commit pull requests changing both.

view merged work →