This position paper uses systems thinking to trace how agent-mediated information seeking disrupts the balancing loops that currently contribute to documentation quality and how this disruption would create reinforcing loops that degrade documentation and code quality over time.
Abstract
Software documentation teams rely on developer activity to identify and correct problems in their content. As AI coding assistants reshape how developers seek information, their impact on software documentation feedback channels has gone largely unnoticed. When developers reduce reading documentation and stop posting questions, documentation teams lose the signals they need to find and fix problems. We use systems thinking to trace how agent-mediated information seeking disrupts the balancing loops that currently contribute to documentation quality and how this disruption would create reinforcing loops that degrade documentation and code quality over time. We identify leverage points where researchers can develop quality metrics and self-correcting documentation systems for agent-mediated use, and system designers can surface agent consumption patterns to documentation teams. Through this position paper, we call on the research community to investigate how agent-mediated documentation consumption reshapes documentation and its quality.
A descriptive model of agent-documentation interaction is derived as a two-lobed cycle rather than a linear journey, and it is shown that two widely assumed properties of"agent-friendly"documentation - actionability and verifiability - lack consistent behavioural support.
This paper is the first to study how SE processes are changing in the development of SE agents and what challenges developers face, and describes a seven-stage workflow and five process shifts, including a move toward evaluation-driven development.
Yunbo Lyu, David Williams, Jieke Shi et al.· arXiv.org· 0 citations
AI agents are becoming a fundamental part of modern software creation, helping developers in generating code, debugging, designing systems, etc. But there is a clear difference between how beginners and experienced software engineers get benefits from these tools. Newbies usually depend on agents for one-time prompts and quick answers, whereas mature users utilize them through well-defined, repeated workflows that raise productivity and consistency. In this article, we discuss this difference and emphasize that getting the full potential does not merely depend on better prompts but on workflows driven by instructions developers create clear and reusable instruction files to direct agent behavior across tasks. When developers stop seeing agents only as chat interfaces but as programmable collaborators, they can produce more reliable and high-quality outputs. We offer in our paper methods like designing modular instructions, narrowing down the context, and iterative refinement loops, as well as a case study illustrating how a team made a code review more efficient and minimized the rework by making agent instructions standard. The results stress that structured forms of interaction rather than sporadic use are the main ways to tap into advanced features. Our paper provides a conceptual model for agent usage at large scale, hands-on advice for the implementation of instruction files in actual settings, and validation that skillful developers can far exceed basic usage by adopting orderly, system-like approaches to agent collaboration.
Madhurima Kommuru, Srujana Pulipaka· International Journal of Mod...· 0 citations
The work identifies five distinct stages of the documentation review process: self review, technical review, editorial review, play testing, and post-publication feedback, and draws on practitioners with distinct expertise to address quality across content, presentation, and user experience.
Avinash Bhat, Ian Arawjo, Disha Shrivastava et al.· 1 citation· ⚡1
It is found that a good bug report for an agent overlaps with, but is not identical to, a good report for a human: agents benefit most from concrete, executable, and well-localized information, whereas some qualities long emphasized for human readers, such as natural language steps to reproduce and readable descriptions, contribute little or even correlate with lower success.
Lara Khatib, N. Mathews, M. Nagappan et al.· arXiv.org· 2 citations· ⚡1
The results suggest that agentic-first reports benefit most from information that narrows the agent's search and repair space, and an ablation study removing selected information types confirms that agents benefit less from information traditionally useful to humans, and more from sentences that expose a repair direction, either through bug localization or a suggested fix.
Vincenzo Luigi Bruno, Alessandro Giagnorio, Daniele Bifolco et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
