Personal AI Agents

Follow this topic Ask about this topic

Personal AI agents aim to understand a user's preferences, history, and current goals, then help by answering, planning, or acting across services and devices. Common approaches combine long-term memory—such as retrieval, temporal or graph structures, and executable user rules—with tool-using language models, reusable skills, feedback, and sometimes on-device runtimes. Benchmarks increasingly test multi-app workflows, evolving or hidden intent, proactive timing, and long-horizon state changes, alongside memory and personalization quality. Systems still struggle with complex tool orchestration and reliable grounding, while persistent access raises open questions about privacy, consent, user control, and whether delegated actions truly serve the user.

Latest papers

64 papers11 papers in the last four weeks, up 120% on the four weeks before. 0.1% of all new papers.

AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
Mar 1, 2026Yutao Yang, Junsong Li, Qianjun Pan +9LLM Agent Skill Learning Lifelong Learning Agents
School of Computer Science and Technology, East China Normal University · Shanghai AI Laboratory
Learning Personalized Agents from Human Feedback
Feb 18, 2026Kaiqu Liang, Julia Kruk, Shengyi Qian +9Personal AI Agents User Preference Modeling
Meta Superintelligence Labs · Princeton University · Duke University
Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents
Jan 12, 2026Miao Su, Yucan Guo, Zhongni Hou +8LLM Agent Memory Conversational Memory
Institute of Computing Technology, Chinese Academy of Sciences · State Key Laboratory of AI Safety · School of Computer Science, University of Chinese Academy of Sciences +1
When Assisting One Disempowers Another
Nov 6, 2025Claire Yang, Claire Jie Zhang, Maya Cakmak +1AI Agent Safety Human-Centered AI
University of Washington

Mar 1, 2026J/K move · Enter open · S save

AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution

Yutao Yang, Junsong Li, Qianjun Pan, Bihao Zhan+8

School of Computer Science and Technology, East China Normal University · Shanghai AI Laboratory

LLM Agent Skill Learning Lifelong Learning Agents Self-Evolving Agents Personal AI Agents LLM Agent Skill Retrieval

Open paper AskPDF arXiv

In practical LLM applications, users repeatedly express stable preferences and requirements, such as reducing hallucinations, following institutional writing conventions, or avoiding overly technical wording, yet such interaction experience is seldom consolidated into reusable knowledge. Consequently, LLM agents often fail to accumulate personalized capabilities across sessions. We present AutoSkill, an experience-driven lifelong learning framework that enables LLM agents to automatically derive, maintain, and reuse skills from dialogue and interaction traces. AutoSkill abstracts skills from user experience, supports their continual self-evolution, and dynamically injects relevant skills into future requests without retraining the underlying model. Designed as a model-agnostic plugin layer, it is compatible with existing LLMs and introduces a standardized skill representation for sharing and transfer across agents, users, and tasks. In this way, AutoSkill turns ephemeral interaction experience into explicit, reusable, and composable capabilities. This paper describes the motivation, architecture, skill lifecycle, and implementation of AutoSkill, and positions it with respect to prior work on memory, retrieval, personalization, and agentic systems. AutoSkill highlights a practical and scalable path toward lifelong personalized agents and personal digital surrogates.

Latest papers

AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution

Learning Personalized Agents from Human Feedback

Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents

When Assisting One Disempowers Another