AI编程代理需从自主执行转向人机协同，提升可验证与可引导性。
Humans are Missing from AI Coding Agent Research
- 提出人机协作四维度：任务对齐、可验证性、可引导性、适应性
- 强调用户参与环境与交互质量评估是突破瓶颈的关键
- 适合关注AI工程落地与人机交互的研究者阅读
近期AI编程代理研究在自主完成复杂软件工程任务方面取得显著进展，涵盖大型代码库编辑和长期开发流程执行。然而，随着任务解决能力提升，实际应用的瓶颈正从纯技术能力转向用户如何与代理沟通、监督和信任其行为。本文主张将研究重心从完全自主的代理转向以人类为中心的协作式代理：不仅完成任务，更要与人高效协作。我们识别出人机任务解决循环中的四个核心交互维度：任务对齐、可验证性、可引导性和适应性。最后，提出具体研究方向，包括用户参与的编码环境、全面的验证机制以及量化的交互质量评估方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。