让AI理解用户隐性需求，通过协作与可视化实现任务委托
DoubleAgents: Human-Agent Alignment in a Socially Embedded Workflow
- 用协调代理+可视化仪表盘+策略模块，让人类可感知并修正AI决策
- 实验显示用户对AI信任度随时间提升，任务依赖度显著增加
- 适合需长期协作、有社交情境的复杂任务，如团队管理
将智能体与用户意图对齐对于委派复杂且具有社会嵌入性的任务至关重要，但用户偏好常为隐含、动态变化且难以预先明确。我们提出DoubleAgents系统，基于分布式认知理论，用于协调任务中的人机对齐。该系统包含三个组件：（1）协调代理，负责维护状态并提出计划与行动；（2）仪表盘可视化，使代理推理过程可被用户评估；（3）策略模块，将用户修改转化为可复用的对齐工具，包括协调策略、邮件模板和停止钩子，持续优化系统行为。通过为期两天的实验室研究（n=10）、三次真实场景部署及技术评估验证了本系统。参与者在任务委派中的舒适度与对DoubleAgents的依赖程度随时间上升，且与三大分布式认知组件相关。参与者在不确定性节点（如边缘案例标记、上下文依赖操作）仍需介入控制。本文贡献了一种面向社会嵌入性任务的人机对齐的分布式认知方法。
原文摘要 · Abstract (English)
Aligning agentic AI with user intent is critical for delegating complex, socially embedded tasks, yet user preferences are often implicit, evolving, and difficult to specify upfront. We present DoubleAgents, a system for human-agent alignment in coordination tasks, grounded in distributed cognition. DoubleAgents integrates three components: (1) a coordination agent that maintains state and proposes plans and actions, (2) a dashboard visualization that makes the agent's reasoning legible for user evaluation, and (3) a policy module that transforms user edits into reusable alignment artifacts, including coordination policies, email templates, and stop hooks, which improve system behavior over time. We evaluate DoubleAgents through a two-day lab study (n=10), three real-world deployments, and a technical evaluation. Participants' comfort in offloading tasks and reliance on DoubleAgents both increased over time, correlating with the three distributed cognition components. Participants still required control at points of uncertainty - edge-case flagging and context-dependent actions. We contribute a distributed cognition approach to human-agent alignment in socially embedded tasks.
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。