mlsanityData to 14 Oct 2026

LLM as OS, Agents as Apps: Envisioning AIOS, Agents and the AIOS-Agent Ecosystem

arXiv 2312.03815 ↗First posted 6 Dec 2023cs.OS cs.AI cs.CLcited by 38

On the map: LLM agents and tool use → GUI and mobile agents

Abstract (arXiv)

This paper envisions a revolutionary AIOS-Agent ecosystem, where Large Language Model (LLM) serves as the (Artificial) Intelligent Operating System (IOS, or AIOS)--an operating system "with soul". Upon this foundation, a diverse range of LLM-based AI Agent Applications (Agents, or AAPs) are developed, enriching the AIOS-Agent ecosystem and signaling a paradigm shift from the traditional OS-APP ecosystem. We envision that LLM's impact will not be limited to the AI application level, instead, it will in turn revolutionize the design and implementation of computer system, architecture, software, and programming language, featured by several main concepts: LLM as OS (system-level), Agents as Applications (application-level), Natural Language as Programming Interface (user-level), and Tools as Devices/Libraries (hardware/middleware-level). We begin by introducing the architecture of traditional OS. Then we formalize a conceptual framework for AIOS through "LLM as OS (LLMOS)", drawing analogies between AIOS and traditional OS: LLM is likened to OS kernel, context window to memory, external storage to file system, hardware tools to peripheral devices, software tools to programming libraries, and user prompts to user commands. Subsequently, we introduce the new AIOS-Agent Ecosystem, where users can easily program Agent Applications (AAPs) using natural language, democratizing the development of software, which is different from the traditional OS-APP ecosystem. Following this, we explore the diverse scope of Agent Applications. We delve into both single-agent and multi-agent systems, as well as human-agent interaction. Lastly, drawing on the insights from traditional OS-APP ecosystem, we propose a roadmap for the evolution of the AIOS-Agent ecosystem. This roadmap is designed to guide the future research and development, suggesting systematic progresses of AIOS and its Agent applications.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use. Builds on 89 of its 128 references that are in the map. First posted on arXiv 6 Dec 2023.

Builds on

89 of 128 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023You Only Look at Screens: Multimodal Chain-of-Action Agents20 Sep

Other references · 88

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2022Training language models to follow instructions with human feedbackcited by 15,971
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  6. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  7. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  8. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  9. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  10. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  11. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  12. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
38 more
  1. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  5. 2020Longformer: The Long-Document Transformercited by 3,413
  6. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  7. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  8. 2017Billion-scale similarity search with GPUscited by 2,497
  9. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  10. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  11. 2023Code Llama: Open Foundation Models for Codecited by 2,139
  12. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 2,022
  13. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  14. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  15. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  16. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  17. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  18. 2020Big Bird: Transformers for Longer Sequencescited by 1,684
  19. 2020Reformer: The Efficient Transformercited by 1,668
  20. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,651
  21. 2020Linformer: Self-Attention with Linear Complexitycited by 1,474
  22. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  23. 2023GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpointscited by 1,346
  24. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
  25. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  26. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,251
  27. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,242
  28. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
  29. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,154
  30. 2021Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolationcited by 1,103
  31. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
  32. 2023Teaching Large Language Models to Self-Debugcited by 988
  33. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  34. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  35. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  36. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 742
  37. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 740
  38. 2019Fast Transformer Decoding: One Write-Head is All You Needcited by 717

50 most cited of 88 All 88 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 16; 2025: 12; 2026: 9.

38 papers.

Sort:

By area:

  1. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 634
  2. 2025TRAIL: Trace Reasoning and Agentic Issue Localizationcited by 104
  3. 2024AIOS: LLM Agent Operating Systemcited by 97
  4. 2024AutoFlow: Automated Workflow Generation for Large Language Model Agentscited by 83
  5. 2023NPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models via Complexity Classescited by 79
  6. 2025UFO2: The Desktop AgentOScited by 41
  7. 2024Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agentscited by 40
  8. 2024RL-GPT: Integrating Reinforcement Learning and Code-as-policycited by 32
  9. 2025LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospectscited by 32
  10. 2025A Survey on Autonomy-Induced Security Risks in Large Model-Based Agentscited by 29
  11. 2024MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistantscited by 24
  12. 2024BattleAgent: Multi-modal Dynamic Emulation on Historical Battles to Complement Historical Analysiscited by 20
26 more
  1. 2024Infogent: An Agent-Based Framework for Web Information Aggregationcited by 19
  2. 2024Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interfacecited by 16
  3. 2025Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compressioncited by 16
  4. 2025Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challengescited by 12
  5. 2024Beyond Memorization: The Challenge of Random Memory Access in Language Modelscited by 8
  6. 2024AIOS Compiler: LLM as Interpreter for Natural Language Programming and Flow Programming of AI Agentscited by 8
  7. 2024APPL: A Prompt Programming Language for Harmonious Integration of Programs and Large Language Model Promptscited by 8
  8. 2024Tulip Agent -- Enabling LLM-Based Agents to Solve Tasks Using Large Tool Librariescited by 7
  9. 2026Right to History: A Sovereignty Kernel for Verifiable AI Agent Executioncited by 7
  10. 2025The Lottery LLM Hypothesis, Rethinking What Abilities Should LLM Compression Preserve?cited by 6
  11. 2025Cerebrum (AIOS SDK): A Platform for Agent Development, Deployment, Distribution, and Discoverycited by 6
  12. 2025Everything is Context: Agentic File System Abstraction for Context Engineeringcited by 6
  13. 2026From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AIcited by 6
  14. 2024CURATe: Benchmarking Personalised Alignment of Conversational AI Assistantscited by 5
  15. 2024Apollonion: Profile-centric Dialog Agentcited by 4
  16. 2025DuetUI: A Bidirectional Context Loop for Human-Agent Co-Generation of Task-Oriented Interfacescited by 4
  17. 2024Elastic On-Device LLM Servicecited by 3
  18. 2026From Everything-is-a-File to Files-Are-All-You-Need: How Unix Philosophy Informs the Design of Agentic AI Systemscited by 2
  19. 2026Model-Native Computing Architecture: Envisioning Future System Architecture Through the Lens of Computer Architecturecited by 2
  20. 2025From Craft to Constitution: A Governance-First Paradigm for Principled Agent Engineeringcited by 1
  21. 2026DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operationscited by 1
  22. 2026Agents in the Large: Perception-Centered Architecture for Persistent Agentscited by 1
  23. 2025StackPilot: Autonomous Function Agents for Scalable and Environment-Free Code Executioncited by 0
  24. 2026When the Agent Becomes the Kernel: A Systematization of Security on the Path to AI-Native Operating Systemscited by 0
  25. 2026AgentKernel: The Trust-Native Agentic Operating Systemcited by 0
  26. 2026Building LLM Agent Systems the Deep Learning Way: From Modular Design to Architecture Searchcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use
  2. 2026Towards an Agent Operating System - Lessons from Classical and Cloud OS
  3. 2024Understanding the Weakness of Large Language Model Agents within a Complex Android Environment
  4. 2024Integrating Artificial Intelligence into Operating Systems: A Survey on Techniques, Applications, and Future Directions
  5. 2026Toward Securing AI Agents Like Operating Systems
  6. 2025From Imperative to Declarative: Towards LLM-friendly OS Interfaces for Boosted Computer-Use Agents
  7. 2024Creating an LLM-based AI-agent: A high-level methodology towards enhancing LLMs with APIs
  8. 2026AOHP: An Open-Source OS-Level Agent Harness for Personalized, Efficient and Secure Interaction