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

arXiv: https://arxiv.org/abs/2608.20195 · HTML: https://mlsanity.com/paper/2608.20195/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 78 references that are in the map.
- First posted on arXiv 20 Aug 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, 25 of 25)

- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [DocPrompting: Generating Code by Retrieving the Docs](https://mlsanity.com/paper/2207.05987/) (2022)
- [CodeRAG-Bench: Can Retrieval Augment Code Generation?](https://mlsanity.com/paper/2406.14497/) (2024)
- [Context as a Tool: Context Management for Long-Horizon SWE-Agents](https://mlsanity.com/paper/2512.22087/) (2025)
- [SWE-chat: Coding Agent Interactions From Real Users in the Wild](https://mlsanity.com/paper/2604.20779/) (2026)
- [Understanding Code Agent Behaviour: An Empirical Study of Success and Failure Trajectories](https://mlsanity.com/paper/2511.00197/) (2025)
- [Agentic Much? Adoption of Coding Agents on GitHub](https://mlsanity.com/paper/2601.18341/) (2026)
- [Learning to Update Natural Language Comments Based on Code Changes](https://mlsanity.com/paper/2004.12169/) (2020)
- [HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?](https://mlsanity.com/paper/2604.09408/) (2026)
- [Agent READMEs: An Empirical Study of Context Files for Agentic Coding](https://mlsanity.com/paper/2511.12884/) (2025)
- [Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?](https://mlsanity.com/paper/2602.11988/) (2026)
- [Categorizing the Content of GitHub README Files](https://mlsanity.com/paper/1802.06997/) (2018)
- [Agentic Refactoring: An Empirical Study of AI Coding Agents](https://mlsanity.com/paper/2511.04824/) (2025)
- [AIDev: Studying AI Coding Agents on GitHub](https://mlsanity.com/paper/2602.09185/) (2026)
- [On the Use of Agentic Coding Manifests: An Empirical Study of Claude Code](https://mlsanity.com/paper/2509.14744/) (2025)
- [Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub](https://mlsanity.com/paper/2601.15195/) (2026)
- [9.6 Million Links in Source Code Comments: Purpose, Evolution, and Decay](https://mlsanity.com/paper/1901.07440/) (2019)
- [Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time](https://mlsanity.com/paper/2604.00917/) (2026)
- [Do Context Files Help Coding Agents? A Two-Agent Ablation Study on Real Repositories](https://mlsanity.com/paper/2607.27250/) (2026)
- [Do AI Coding Agents Log Like Humans? An Empirical Study](https://mlsanity.com/paper/2604.09409/) (2026)
- [Why Does CLAUDE.md Keep Growing? Catastrophic Remembering in Agentic Coding](https://mlsanity.com/paper/2608.11095/) (2026)
- [Context Rot in AI-Assisted Software Development: Repurposing Documentation Consistency for AI Configuration Artifacts](https://mlsanity.com/paper/2606.09090/) (2026)
- [What's Inside a GitHub Repository? An Empirical Study on the Contents of 10K Projects](https://mlsanity.com/paper/2605.16701/) (2026)
- [An Exploratory Study of Agent Plans for Agentic AI Coding Tools in Open-Source Software](https://mlsanity.com/paper/2608.04661/) (2026)

## Abstract (arXiv)

Technical documentation is written for human developers, but an increasing share of software changes is now authored by autonomous coding agents. Which documents they consult, when, and what follows remain unknown. We conduct a behaviour-grounded study of agent-documentation interaction across two public datasets: 557 agentic coding sessions from SWE-chat, yielding 94,813 development events including 3,033 documentation interactions; and 33,097 agentic pull requests from AIDev, with 690,260 classified file-level change records. Four findings challenge current documentation practice. First, agents' documentation work is dominated by agent-facing artefacts: instruction files and working notes account for 60.5% of all documentation interactions, versus 10.6% for classical technical documentation and 1.3% for API references. Second, the link between consultation and code editing is unresolved: the adjacent transition probability is 0.002 and the unadjusted three-event lift 1.05, whereas a stage-adjusted model places it above unity (OR 1.33 [1.09, 1.62]); documentation creation is elevated unadjusted (lift 1.67) but its adjusted interval includes unity. Third, no explicit documentation-based validation sequence was observed, and consultation is associated with less immediate testing (lift 0.23, cluster CI 0.08-0.45; adjusted OR 0.39 [0.25, 0.60]). Fourth, consultation is self-initiated (70.2%) far more often than failure-driven (7.5%), and documentation trails code: among multi-commit pull requests changing both, code is touched first 4.7x more often. From these traces we derive a descriptive model of agent-documentation interaction as a two-lobed cycle rather than a linear journey, and show that two widely assumed properties of "agent-friendly" documentation - actionability and verifiability - lack consistent behavioural support. We release our pipeline, coding scheme, and event-level data.