Towards AI as a Collaborative Partner: A Taxonomy of AI Agent Behavior in Software Engineering

Tao Dong, Sherry Y. Shi, Harini Sampath, Andrew Macvean

Keywords: Human-AI Collaboration, Software Engineering, AI Agents, LLM Evaluation

TL;DR: Our main contribution is a taxonomy of desirable AI agent behavior for enterprise software engineering, derived from a qualitative analysis of 91 sets of agent rules and interviews with 15 experienced professional software developers.

Abstract: The ongoing transition of Large Language Models in software engineering from one-shot code generators into agentic partners requires a shift in how we define and measure success. While models are becoming more capable, the industry lacks a clear understanding of the behavioral norms that make an interactive SWE agent effective in collaborative software development in the enterprise. This work addresses this gap by presenting a taxonomy of desirable SWE agent behaviors, synthesized from 91 sets of developer-defined rules for SWE agents and validated through interviewing 15 experienced professional developers. In this taxonomy, we identify four core expectations: Adhere to Standards and Processes, Ensure Code Quality and Reliability, Solve Problems Effectively, and Collaborate with the Developer. These findings offer a concrete vocabulary for aligning SWE agent behavior with developer preferences, enabling researchers and practitioners to move beyond correctness-only benchmarks and start designing evaluations that reflect the socio-technical nature of professional software development in enterprises.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public.

Paper Type: Full-length papers (i.e. case studies, theoretical, applied research papers). 8 pages

Reroute: true

Submission Number: 20