DoubleAgents: Human-Agent Alignment in a Socially Embedded Workflow

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Long, Tao, Zhang, Xuanming, Wang, Sitong, Yu, Zhou, Chilton, Lydia B
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914447171256320
author Long, Tao
Zhang, Xuanming
Wang, Sitong
Yu, Zhou
Chilton, Lydia B
author_facet Long, Tao
Zhang, Xuanming
Wang, Sitong
Yu, Zhou
Chilton, Lydia B
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_12626
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DoubleAgents: Human-Agent Alignment in a Socially Embedded Workflow
Long, Tao
Zhang, Xuanming
Wang, Sitong
Yu, Zhou
Chilton, Lydia B
Human-Computer Interaction
Artificial Intelligence
Computers and Society
Emerging Technologies
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.
title DoubleAgents: Human-Agent Alignment in a Socially Embedded Workflow
topic Human-Computer Interaction
Artificial Intelligence
Computers and Society
Emerging Technologies
url https://arxiv.org/abs/2509.12626