paper-with-me

홈 › Papers

AOHP: An Open-Source OS-Level Agent Harness for Personalized, Efficient and Secure Interaction

2026-06-22 · 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 arxiv

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.

📄 PDF Abstract BibTeX arXiv:2606.23449

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

OpenForgeRL: Train Harness-native Agents in Any Environment

2026-07-23 · Xiao Yu, Baolin Peng, Ruize Xu, Hao Zou 외 arxiv

Modern AI agents rely on elaborate inference harnesses such as Claude Code, Codex, and OpenClaw to drive multi-turn reasoning, tool use, and access to external systems. While powerful, these complex harnesses also make a…

Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

2026-07-14 · Ruhan Wang, Yucheng Shi, Zongxia Li, Zhongzhi Li 외 hf

The capability of a modern AI agent depends not only on its foundation model but also on its harness, which constructs prompts, manages state, invokes tools, and coordinates execution. As models, APIs, environments, and …

Code Search

Guava: An Effective and Universal Harness for Embodied Manipulation

2026-06-16 · Haowen Liu, Xirui Li, Shaoxiong Yao, Peng Shi 외 arxiv

Language models trained on large-scale vision-language data have demonstrated strong potential for embodied agents. Harnessing models through embodied tools use offers a promising alternative to end-to-end vision-languag…

What Does Multi-Harness RL Learn? Credit Assignment and Portability in Coding Agents

2026-09-03 · Chenqian Le, Jiayi Cheng, Qijia He, Runhao Li 외 arxiv

Agent reinforcement learning (RL) increasingly runs through full execution harnesses, and a multi-harness recipe mixes two choices: exposing the policy to several harnesses, and comparing their rewards inside one relativ…

Reinforcement Learning

Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence

2026-08-17 · Xin Ding, Liang Mi, Mingzhe Huang, Zixuan Wang 외 arxiv

Embodied agents are increasingly used to close the gap left by end-to-end policy models. Yet the agentic path has not realized closed-loop learning in physical execution: existing harnesses remain largely open-loop, foll…