Skip to content

How Do Developers Maintain and Evolve Their Agents' Instructions? An Empirical Study

Jun 2026 · arXiv.org · Vol abs/2606.25257 · 0 citations · 28 references
Computer Science

TL;DR

A large-scale mining study combining repositories with ACFs and agent-generated commits is conducted, reconstructing ACF evolution at the commit level, classify changes using a qualitative approach, and analyze their association with code quality metrics.

Abstract

Context. Autonomous coding agents are increasingly used in software development, shifting parts of the engineering process to AI assistance. While this automation brings clear benefits, it introduces challenges in governance, traceability, and control over agent behavior. Agent Context Files (ACFs) have emerged as a practical mechanism to guide agents through structured instructions, yet little is known about how these artifacts are maintained and how their evolution relates to code development. Objective. This paper plans to investigate the evolution of ACFs and their role in agent-driven development. Specifically, we (1) classify ACF changes through a taxonomy grounded in software maintenance theory, (2) analyze how different types of changes are associated with code quality outcomes, and (3) examine their temporal patterns across the development lifecycle. Method. We conduct a large-scale mining study combining repositories with ACFs and agent-generated commits. We reconstruct ACF evolution at the commit level, classify changes using a qualitative approach, and analyze their association with code quality metrics. Statistical analyses and hypotheses are used to evaluate differences across maintenance categories, to inform future design of ACFs for governing autonomous coding agents.

View source

Similar papers

Preprint Jul 2026

How Do AI Coding Agents Contribute to Software Development? an Empirical Study of Agentic Pull Requests

This study characterize agentic pull requests (PR) in comparison to human generated PRs and to examine how their properties change across different stages of the development lifecycle, offering a more nuanced understanding of their benefits and limitations in real-world practices.

Iren Mazloomzadeh, Mohammad Mehdi Morovati, F. Khomh · 0 citations
Review Jul 2026

How Do Practitioners Build SE Agents? Insights from a Mixed-Methods Study

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. · 0 citations
Conference Jul 2026

A Preliminary Study on How AI Coding Agents Describe Refactoring Activities

Refactoring is essential for maintaining and evolving software systems, yet we still have limited insight into how automated code-generation agents describe these changes in pull requests. In this study, we analyze refactoring-related pull requests produced by five AI coding agents, with a particular focus on how their intentions are communicated through pull request descriptions. To better understand recurring transformation patterns, we extract refactoring descriptors terms that capture different refactoring activities and use them to identify similarities across agents. We then classify the pull requests into three main categories: internal quality attributes, external quality attributes, and code smells. Our dataset includes 2,288 unique AIgenerated refactoring pull requests from OpenAI Codex, Devin, GitHub Copilot, Cursor, and Claude Code. The results reveal several limitations in how AI systems perform and document refactoring, highlighting the need for clearer and more structured communication in collaborative software development.

Aymen Masmoudi, Belhassen Khefacha, Andrew Haralambous et al. · 0 citations
Conference Jul 2026

A Preliminary Study on How AI Coding Agents Describe Refactoring Activities

Refactoring is essential for maintaining and evolving software systems, yet we still have limited insight into how automated code-generation agents describe these changes in pull requests. In this study, we analyze refactoring-related pull requests produced by five AI coding agents, with a particular focus on how their intentions are communicated through pull request descriptions. To better understand recurring transformation patterns, we extract refactoring descriptors terms that capture different refactoring activities and use them to identify similarities across agents. We then classify the pull requests into three main categories: internal quality attributes, external quality attributes, and code smells. Our dataset includes 2,288 unique AIgenerated refactoring pull requests from OpenAI Codex, Devin, GitHub Copilot, Cursor, and Claude Code. The results reveal several limitations in how AI systems perform and document refactoring, highlighting the need for clearer and more structured communication in collaborative software development.

Aymen Masmoudi, Belhassen Khefacha, Andrew Haralambous et al. · 0 citations
Preprint Jul 2026

Cheap Code, Costly Judgment: A Case Study on Governable Agentic Software Engineering

Generative AI is shifting software engineering from a practice organized around scarce implementation effort toward one organized around abundant, low-cost code production. This shift changes the central engineering problem: not whether AI can generate useful code, but how engineers organize architectures, tools, evidence, and feedback loops so that AI-mediated development remains inspectable, correctable, and maintainable. We study this problem through a first-person case study: a 12-week development effort in which a single expert software engineer used frontier AI coding agents to build a document accessibility remediation system. The empirical record comprises 88 contemporaneous field notes, 420 KLOC of production code, and 1.16 MLOC of tests, lints, supporting documentation, and agent tooling. From this record, we develop a candidate middle-range theory of governance conversion, expressed as a process model explaining how high-velocity agentic implementation becomes governable. The model explains how agentic implementation velocity surfaces recurring structural failure classes, and how engineering judgment sustains velocity by converting those failures into durable governance mechanisms. In contrast to existing governance models that derive controls from known obligations, governance conversion explains how controls are discovered from failures that become visible only during agentic work. We use our model to make testable predictions and to describe implications for software engineering research and practice.

James C. Davis, Paschal C. Amusuo, Tanmay Singla et al. · 3 citations · ⚡1
Review Aug 2026

Self-Evolving Coding Agents

This survey aims to clarify the conceptual boundaries of self-evolving coding agents and provide a foundation for designing more adaptive, reliable, and software-aware agentic systems.

H. Zhou, Haichuan Hu, Ye Shang et al. · 0 citations