Avatar Intelligence：用持久个人智能体放大人类能动性

Authors:Zheng Wu, Xinbei Ma, Yao Yao, Zhaoyuan Huang, Haowen Hu, Yijie Lu, Taolei Wang, Yifei Yang, Wuyue Xiong, Pengzhou Cheng, Zhuosheng Zhang

View PDF HTML (experimental)

Abstract:Personal AI agents are increasingly capable of handling long-horizon tasks across applications, yet users often need to invest substantial effort in specifying goals, resolving ambiguity, and verifying outcomes. We argue that progress should be measured by how effectively agents amplify human agency: enabling people to pursue their goals with less routine supervision while retaining control over consequential decisions. We advocate Avatar Intelligence, a paradigm of persistent personal agents that represent users' goals, values, and constraints through sustained decision delegation across contexts and time. We describe a maturity roadmap from human-directed execution to autonomous operation within delegated domains, and introduce the Agentic Oversight Index (AOI) as a framework for evaluating delivered value against agent-side operational cost and human oversight burden. We identify three core research challenges: identity-continuous personalization that carries user preferences across tasks, user-situated evolution through Rehearsal Engineering, and safety mechanisms that combine technical control with accountability and recourse. These directions define a research agenda for reliable decision delegation to personal agents across tasks and over time.

Subjects:	Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
Cite as:	arXiv:2611.03092 [cs.AI]
	(or arXiv:2611.03092v1 [cs.AI] for this version)
	https://doi.org/10.48550/arXiv.2611.03092 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Zheng Wu [view email]
[v1] Mon, 2 Nov 2026 13:11:57 UTC (2,659 KB)