Paper Detail
Shanhui Zhao, Jiacheng Liu, Guohong Liu, Jichao Yan, Jialei Ye, Yuhao Yang, Hao Wen, Shizuo Tian, Yizhen Yuan, Yuxuan Chen, Yunxin Liu, Ju Ren, Ya-Qin Zhang, Chao Huang, Yao Guo, Yuanchun Li
AI agents are driving a new software paradigm, with the ability to autonomously call tools, extract information, manage memory, and complete tasks that span applications and data sources. Most existing end-user operating systems, however, are designed for application-centric workflows and offer little native support for AI agents. This mismatch limits the wider adoption of agents and leads to execution overhead and safety risks when running agents on conventional systems. While the concept of agent-native operating systems is emerging, the research community lacks an open testbed to explore the architectural primitives desired for agent-mediated interaction. We present AOHP (Android Open Harness Project), an OS-level agent harness built on the Android Open Source Project (AOSP). The core design principle of AOHP is to treat agents as first-class OS actors, enabling adaptive user interfaces and agent-friendly runtime environments. AOHP preserves the mature Android software and hardware ecosystem while introducing three agent-oriented system mechanisms: personalized service composition, efficient agent interfaces, and secure information flow. Based on preliminary experiments on challenging tasks covering key capabilities of OS agents, AOHP shows clear advantages in task completion (+21.12% completion rate), execution cost (-51.55% token cost), and security-policy compliance.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{zhao2026aohp,
title = {AOHP: An Open-Source OS-Level Agent Harness for Personalized, Efficient and Secure Interaction},
author = {Shanhui Zhao and Jiacheng Liu and Guohong Liu and Jichao Yan and Jialei Ye and Yuhao Yang and Hao Wen and Shizuo Tian and Yizhen Yuan and Yuxuan Chen and Yunxin Liu and Ju Ren and Ya-Qin Zhang and Chao Huang and Yao Guo and Yuanchun Li},
year = {2026},
abstract = {AI agents are driving a new software paradigm, with the ability to autonomously call tools, extract information, manage memory, and complete tasks that span applications and data sources. Most existing end-user operating systems, however, are designed for application-centric workflows and offer little native support for AI agents. This mismatch limits the wider adoption of agents and leads to execution overhead and safety risks when running agents on conventional systems. While the concept of ag},
url = {https://huggingface.co/papers/2606.23449},
keywords = {AI agents, agent-native operating systems, Android Open Source Project, personalized service composition, efficient agent interfaces, secure information flow, task completion, execution cost, token cost, security-policy compliance, code available, huggingface daily},
eprint = {2606.23449},
archiveprefix = {arXiv},
}
{}