Sharp Tools: How Developers Wield Agentic AI in Real Software Engineering Tasks

Abstract: Software Engineering Agents (SWE agents) can autonomously perform development tasks on benchmarks like SWE Bench, but still face challenges when tackling complex and ambiguous real-world tasks. Consequently, SWE agents are often designed to allow interactivity with developers, enabling collaborative problem-solving. To understand how developers collaborate with SWE agents and the communication challenges that arise in such interactions, we observed 19 developers using an in-IDE agent to resolve 33 open issues in repositories to which they had previously contributed. Participants successfully resolved about half of these issues, with participants solving issues incrementally having greater success than those using a one-shot approach. Participants who actively collaborated with the agent and iterated on its outputs were also more successful, though they faced challenges in trusting the agent's responses and collaborating on debugging and testing. These results have implications for successful developer-agent collaborations, and for the design of more effective SWE agents.