# Avatar Intelligence: Amplifying Human Agency Through Persistent Personal Agents

DevFeed: [Avatar Intelligence: Amplifying Human Agency Through Persistent Personal Agents](<https://devfeed.tech/articles/avatar-intelligence-amplifying-human-agency-through-persistent-personal-agents-115419.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.03092>)

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

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [ai alignment](<https://devfeed.tech/topics/ai-alignment.md>), [Human-AI evaluation](<https://devfeed.tech/topics/human-ai-evaluation.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [human review](<https://devfeed.tech/topics/human-review.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>)

Tags: [accountability](<https://devfeed.tech/tags/accountability.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [avatar](<https://devfeed.tech/tags/avatar.md>), [control](<https://devfeed.tech/tags/control.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [delegation](<https://devfeed.tech/tags/delegation.md>), [domains](<https://devfeed.tech/tags/domains.md>), [human-oversight](<https://devfeed.tech/tags/human-oversight.md>), [identity](<https://devfeed.tech/tags/identity.md>), [index](<https://devfeed.tech/tags/index.md>), [less](<https://devfeed.tech/tags/less.md>), [maturity](<https://devfeed.tech/tags/maturity.md>), [operational](<https://devfeed.tech/tags/operational.md>), [oversight](<https://devfeed.tech/tags/oversight.md>), [personal-agents](<https://devfeed.tech/tags/personal-agents.md>), [personal-ai](<https://devfeed.tech/tags/personal-ai.md>), [personal-ai-agents](<https://devfeed.tech/tags/personal-ai-agents.md>), [personalization](<https://devfeed.tech/tags/personalization.md>)

## AI overview

The paper proposes Avatar Intelligence: persistent personal agents that carry a user's goals, values, and constraints across contexts and time, delegating decisions while preserving user control over consequential choices. It outlines a maturity path from human-directed execution to autonomy within delegated domains and introduces the Agentic Oversight Index (AOI), which weighs delivered value against agents' operating costs and users' oversight burden. Its research agenda covers personalization that maintains identity across tasks, user-situated agent evolution through Rehearsal Engineering, and safety that pairs technical controls with accountability and recourse. These are proposed directions for reducing routine supervision; the supplied abstract does not report empirical results.

## Source excerpt

arXiv:2611.03092v1 Announce Type: new 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.