发表机构
Carnegie Mellon University; Stanford University; Princeton University; University of Illinois Urbana-Champaign（卡内基梅隆大学; 斯坦福大学; 普林斯顿大学; 伊利诺伊大学厄巴纳-香槟分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该文指出AI编码智能体研究当前缺失人类维度，主张转向以人为中心的编码智能体，明确了人机交互的四个核心层面并提出相关研究方向。
AI 中文摘要
近期AI编码智能体研究的进展，使得智能体自主执行复杂软件工程任务的能力快速提升，从编辑大型代码库到执行长周期开发工作流皆是如此。然而，随着这些系统取得进步，其实用性的主要瓶颈正逐渐从纯粹的任务解决能力，转向用户如何与智能体沟通、监督并建立信任的挑战。在这篇立场文件中，我们主张将研究方向从自主智能体重新定位为以人为中心的编码智能体：这类系统不仅要能完成任务，还要能与人有效协作。我们确定了描述人机任务解决循环的四个核心交互层面：任务对齐、可验证性、可操控性和适应性。最后，我们概述了推进这些层面的具体研究方向，包括用户参与的编码环境、全面的验证机制，以及人机交互质量的原则性衡量标准。
英文摘要
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.
