Humans are Missing from AI Coding Agent Research
This position paper highlights a critical gap in AI coding agent research regarding human interaction, which is important for developers and researchers building practical AI coding tools.
The paper argues that current AI coding agent research focuses too much on autonomous task-solving and too little on human-agent collaboration. It proposes a shift towards human-centered agents, identifying four key interaction dimensions: task alignment, verifiability, steerability, and adaptability.
Recent progress in AI coding agent research has led to rapid improvements in agents' ability to autonomously perform complex software engineering tasks, from editing large codebases to executing long-horizon development workflows. As these systems make strides, however, the primary bottleneck to practical usefulness increasingly shifts away from pure task-solving capability, and toward challenges in how users communicate with, supervise, and trust agents. In this position paper, we argue for a reorientation from autonomous to human-centered coding agents: systems designed not only to complete tasks, but to collaborate effectively with people. We identify four core interaction-level dimensions that characterize the human-agent task-solving loop: task alignment, verifiability, steerability, and adaptability. Finally, we outline concrete research directions to advance these dimensions, including user-involved coding environments, comprehensive verification mechanisms, and principled measures of human-agent interaction quality.