Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Paper list for Personal LLM Agents
| Date | Stars |
|---|---|
| 2026-07-31 | 433 |
| 2026-08-06 | 434 |
Today
+1 stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Personal LLM Agents - Survey
<p align="center">
<a href="https://github.com/MobileLLM/lab-contact"><img src="https://img.shields.io/badge/WeChat-Group-C5EAB4?style=flat&logo=wechat&logoColor=white" alt="WeChat"></a>
<a href="https://discord.gg/3bhPrAarW"><img src="https://img.shields.io/badge/Discord-Group-5865F2?style=flat&logo=discord&logoColor=white" alt="Discord"></a>
</p>
This repo maintains a curated list of papers related to Personal LLM Agents. For more details, please refer to our paper or join our discussion group.
> [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://github.com/MobileLLM/Personal_LLM_Agents_Survey/)
>
> Yuanchun Li, Hao Wen, Weijun Wang, Xiangyu Li, Yizhen Yuan, Guohong Liu, Jiacheng Liu, Wenxing Xu, Xiang Wang, Yi Sun, Rui Kong, Yile Wang, Hanfei Geng, Jian Luan, Xuefeng Jin, Zilong Ye, Guanjing Xiong, Fan Zhang, Xiang Li, Mengwei Xu, Zhijun Li, Peng Li, Yang Liu, Ya-Qin Zhang, Yunxin Liu
>
> [[arxiv]](https://arxiv.org/abs/2401.05459) [[pdf]](https://yuanchun-li.github.io/static/files/personal_llm_agents.pdf) [[cite]](#citation)
### 📣📣📣 News
> 2026.06 -- We introduce AOHP, an OS-level agent harness project, to push forward the R&D of personal agents. Code open-sourced at [https://github.com/aohp-os/aohp](https://github.com/aohp-os/aohp)
**Personal LLM Agents** are defined as a special type of LLM-based agents that are deeply integrated with personal data, personal devices, and personal services.
They are perferably deployed to resource-constrained mobile/edge devices and/or powered by lightweight AI models.
The main purpose of personal LLM agents is to assist end-users and augment their abilities, helping them to focus more and do better on interesting and important affairs.
This paper list covers several main aspects of Personal LLM Agents, including the capabilities, efficiency and security.
Table of content:
- [Personal LLM Agents - Survey](#personal-llm-agents---survey)
- [Key Capabilities of Personal LLM Agents](#key-capabilities-of-personal-llm-agents)
- [Task Automation](#task-automation)
- [UI-grounded Agents for Task Automation](#ui-grounded-agents-for-task-automation)
- [Benchmarks of UI Automation](#benchmarks-of-ui-automation)
- [Sensing](#sensing)
- [LLM-based Approaches](#llm-based-approaches)
- [Traditional Approaches](#traditional-approaches)
- [Memorization](#memorization)
- [Memory Obtaining](#memory-obtaining)
- [Memory Management](#memory-management)
- [Agent Self-evolution](#agent-self-evolution)
- [Efficiency of LLM Agents](#efficiency-of-llm-agents)
- [Efficient LLM Inference \& Training](#efficient-llm-inference--training)
- [Efficient Memory Retrieval \& Management](#efficient-memory-retrieval--management)
- [Organizing the Memory](#organizing-the-memory)
- [Optimizing the Efficiency of Memory](#optimizing-the-efficiency-of-memory)
- [Security \& Privacy of Personal LLM Agents](#security--privacy-of-personal-llm-agents)
- [Confidentiality (of User Data)](#confidentiality-of-user-data)
- [Integrity (of Agent Behavior)](#integrity-of-agent-behavior)
- [Reliability (of Agent Decisions)](#reliability-of-agent-decisions)
## Key Capabilities of Personal LLM Agents
### Task Automation
Task automation is a core capability of personal LLM agents, which determines how well the agent can respond to user commands and/or automatically execute tasks for the user.
We focus on UI-based task automation agents in this list due to their popularity and close relevance to personal devices.
#### UI-grounded Agents for Task Automation
LLM-based Approaches
- WebGPT: Browser-assisted question-answering with human feedback. [[paper](https://arxiv.org/abs/2112.09332)]
- Enabling Conversational Interaction with Mobile UI Using Large Language Models. [CHI 2023] [[paper](https://doi.org/10.1145/3544548.3580895)]
- Language Models can Solve Excerpt of 39,522 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:07687f82b99f337a, desc:paper list