Avatar Intelligence: Amplifying Human Agency Through Persistent Personal Agents
cs.AI, cs.CL
Submitted: 2026-11-02
Updated: 2026-11-02
License: http://creativecommons.org/licenses/by/4.0/
The gist: 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…
Terminology
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.
Sources
- Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
- You Only Look at Screens: Multimodal Chain-of-Action Agents
- Personalized Language Modeling from Personalized Human Feedback
- TagPR: Tag-Guided Process Supervision for Personalization Reasoning in Large Language Models
- Preference-Aware Memory Update for Long-Term LLM Agents
- ColorEcosystem: Powering Personalized, Standardized, and Trustworthy Agentic Service in massive-agent Ecosystem
- LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark
- Quick on the Uptake: Eliciting Implicit Intents from Human Demonstrations for Personalized Mobile-Use Agents
- AgentEvolver: Towards Efficient Self-Evolving Agent System
- EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
- AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
- Quantifying Trust: Financial Risk Management for Trustworthy AI Agents
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents