# AgentOS: From Application Silos to a Natural Language-Driven Data Ecosystem

arXiv: https://arxiv.org/abs/2603.08938 · HTML: https://mlsanity.com/paper/2603.08938/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Builds on (most cited first, 22 of 22)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024)
- [Evaluation and Benchmarking of LLM Agents: A Survey](https://mlsanity.com/paper/2507.21504/) (2025)
- [Establishing Best Practices for Building Rigorous Agentic Benchmarks](https://mlsanity.com/paper/2507.02825/) (2025)
- [Deep Reinforcement Learning for Page-wise Recommendations](https://mlsanity.com/paper/1805.02343/) (2018)
- [AIOS: LLM Agent Operating System](https://mlsanity.com/paper/2403.16971/) (2024)
- [Reinforcement Learning to Optimize Long-term User Engagement in Recommender Systems](https://mlsanity.com/paper/1902.05570/) (2019)
- [Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey](https://mlsanity.com/paper/2503.22458/) (2025)
- [A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents](https://mlsanity.com/paper/2506.23844/) (2025)
- [Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History](https://mlsanity.com/paper/2602.17003/) (2026)
- [An Ecosystem for Personal Knowledge Graphs: A Survey and Research Roadmap](https://mlsanity.com/paper/2304.09572/) (2023)
- [Towards Urban Planing AI Agent in the Age of Agentic AI](https://mlsanity.com/paper/2507.14730/) (2025)
- [AIP: Subverting Retrieval-Augmented Generation via Adversarial Instructional Prompt](https://mlsanity.com/paper/2509.15159/) (2025)
- [Intent Representation Learning with Large Language Model for Recommendation](https://mlsanity.com/paper/2502.03307/) (2025)
- [Blind Gods and Broken Screens: Architecting a Secure, Intent-Centric Mobile Agent Operating System](https://mlsanity.com/paper/2602.10915/) (2026)
- [Constraint-Aware Route Recommendation from Natural Language via Hierarchical LLM Agents](https://mlsanity.com/paper/2510.06078/) (2025)
- [Natural User Interfaces: Trend in Virtual Interaction](https://mlsanity.com/paper/1405.0101/) (2014)
- [City Editing: Hierarchical Agentic Execution for Dependency-Aware Urban Geospatial Modification](https://mlsanity.com/paper/2602.19326/) (2026)

## Built on by (most cited first, 3 of 3)

- [MARS: Efficient, Adaptive Co-Scheduling for Heterogeneous Agentic Systems](https://mlsanity.com/paper/2604.26963/) (2026)
- [Towards an Agent Operating System - Lessons from Classical and Cloud OS](https://mlsanity.com/paper/2607.25076/) (2026)
- [When the Agent Becomes the Kernel: A Systematization of Security on the Path to AI-Native Operating Systems](https://mlsanity.com/paper/2609.23700/) (2026)

## Abstract (arXiv)

The rapid emergence of open-source, locally hosted intelligent agents marks a critical inflection point in human-computer interaction. Systems such as OpenClaw demonstrate that Large Language Model (LLM)-based agents can autonomously operate local computing environments, orchestrate workflows, and integrate external tools. However, within the current paradigm, these agents remain conventional applications running on legacy operating systems originally designed for Graphical User Interfaces (GUIs) or Command Line Interfaces (CLIs). This architectural mismatch leads to fragmented interaction models, poorly structured permission management (often described as "Shadow AI"), and severe context fragmentation. This paper proposes a new paradigm: a Personal Agent Operating System (AgentOS). In AgentOS, traditional GUI desktops are replaced by a Natural User Interface (NUI) centered on a unified natural language or voice portal. The system core becomes an Agent Kernel that interprets user intent, decomposes tasks, and coordinates multiple agents, while traditional applications evolve into modular Skills-as-Modules enabling users to compose software through natural language rules. We argue that realizing AgentOS fundamentally becomes a Knowledge Discovery and Data Mining (KDD) problem. The Agent Kernel must operate as a real-time engine for intent mining and knowledge discovery. Viewed through this lens, the operating system becomes a continuous data mining pipeline involving sequential pattern mining for workflow automation, recommender systems for skill retrieval, and dynamically evolving personal knowledge graphs. These challenges define a new research agenda for the KDD community in building the next generation of intelligent computing systems.