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

• URL: http://arxiv.org/abs/2606.23449v1
• Date: Mon, 22 Jun 2026 15:02:42 GMT
• Title: AOHP: An Open-Source OS-Level Agent Harness for Personalized, Efficient and Secure Interaction
• Abstract summary: We present AOHP (Android Open Harness Project), an OS-level agent harness built on the Android Open Source Project (AOSP)<n> AOHP treats agents as first-class OS actors, enabling adaptive user interfaces and agent-friendly runtime environments.<n>Based on preliminary experiments on challenging tasks covering key capabilities of OS agents, AOHP shows clear advantages in task completion rate, execution cost, and security-policy compliance.
• Score: 34.460547579461235
• License: http://creativecommons.org/licenses/by/4.0/
• 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 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.

Related papers

• AgenticOS: An Intent-Oriented Secure Operating System Architecture for Autonomous AI Agents [9.964434409587222]
  AgenticOS is an intent-oriented secure OS architecture.<n>AgenticOS consolidates delegable, auditable software capabilities into OS-native ones.
  arXiv  Detail & Related papers  (2026-06-19T06:14:37Z)
• DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents [121.77550256034]
  DecodingTrust-Agent Platform (DTap) is a controllable and interactive red-teaming platform for AI agents.<n>DTap-Red is the first autonomous red-teaming agent that explores diverse injection vectors and autonomously discovers effective attack strategies.<n>Through DTap, we conduct large-scale evaluations of popular AI agents built on various backbone models.
  arXiv  Detail & Related papers  (2026-05-06T11:59:48Z)
• Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs [65.6660735371212]
  We present textbftextscJustAsk, a framework that autonomously discovers effective extraction strategies through interaction alone.<n>It formulates extraction as an online exploration problem, using Upper Confidence Bound--based strategy selection and a hierarchical skill space spanning atomic probes and high-level orchestration.<n>Our results expose system prompts as a critical yet largely unprotected attack surface in modern agent systems.
  arXiv  Detail & Related papers  (2026-01-29T03:53:25Z)
• AgentBay: A Hybrid Interaction Sandbox for Seamless Human-AI Intervention in Agentic Systems [29.451397580654316]
  We present AgentBay, a novel service designed from ground up for hybrid interaction.<n>AgentBay provides secure, isolated execution environments Windows, Linux, Android, Web Browsers, and interpreters.<n>Our evaluation demonstrates strong results in security, performance, and task completion rates.
  arXiv  Detail & Related papers  (2025-12-04T01:31:00Z)
• ColorAgent: Building A Robust, Personalized, and Interactive OS Agent [48.95201741635228]
  Building operating system (OS) agents capable of executing user instructions and faithfully following user desires is becoming a reality.<n>We present ColorAgent, an OS agent designed to engage in long-horizon, robust interactions with the environment.<n>We explore personalized user intent recognition and proactive engagement, positioning the OS agent as a warm, collaborative partner.
  arXiv  Detail & Related papers  (2025-10-22T09:02:48Z)
• VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents [39.3943822850841]
  We introduce VeriOS-Agent, a trustworthy OS agent trained with a two-stage learning paradigm.<n>We show that VeriOS-Agent improves the average step-wise success rate by 20.64% in untrustworthy scenarios over the state-of-the-art.
  arXiv  Detail & Related papers  (2025-09-09T09:46:01Z)
• OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use [101.57043903478257]
  The dream to create AI assistants as capable and versatile as the fictional J.A.R.V.I.S from Iron Man has long captivated imaginations.<n>With the evolution of (multi-modal) large language models ((M)LLMs), this dream is closer to reality.<n>This survey aims to consolidate the state of OS Agents research, providing insights to guide both academic inquiry and industrial development.
  arXiv  Detail & Related papers  (2025-08-06T14:33:45Z)
• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering [79.07755560048388]
  SWE-agent is a system that facilitates LM agents to autonomously use computers to solve software engineering tasks. SWE-agent's custom agent-computer interface (ACI) significantly enhances an agent's ability to create and edit code files, navigate entire repositories, and execute tests and other programs. We evaluate SWE-agent on SWE-bench and HumanEvalFix, achieving state-of-the-art performance on both with a pass@1 rate of 12.5% and 87.7%, respectively.
  arXiv  Detail & Related papers  (2024-05-06T17:41:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.