mlsanityData to 7 Oct 2026

AIOS: LLM Agent Operating System

arXiv 2403.16971 ↗First posted 25 Mar 2024cs.OS cs.AI cs.CLcited by 94

Not on the map. Why?

Cited by 61 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

LLM-based intelligent agents face significant deployment challenges, particularly related to resource management. Allowing unrestricted access to LLM or tool resources can lead to inefficient or even potentially harmful resource allocation and utilization for agents. Furthermore, the absence of proper scheduling and resource management mechanisms in current agent designs hinders concurrent processing and limits overall system efficiency. To address these challenges, this paper proposes the architecture of AIOS (LLM-based AI Agent Operating System) under the context of managing LLM-based agents. It introduces a novel architecture for serving LLM-based agents by isolating resources and LLM-specific services from agent applications into an AIOS kernel. This AIOS kernel provides fundamental services (e.g., scheduling, context management, memory management, storage management, access control) for runtime agents. To enhance usability, AIOS also includes an AIOS SDK, a comprehensive suite of APIs designed for utilizing functionalities provided by the AIOS kernel. Experimental results demonstrate that using AIOS can achieve up to 2.1x faster execution for serving agents built by various agent frameworks. The source code is available at https://github.com/agiresearch/AIOS.

Key facts. Cited by 94 papers in the map (data through 7 Oct 2026). Builds on 54 of its 94 references that are in the map. First posted on arXiv 25 Mar 2024.

Builds on

54 of 94 references.

References · 54

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  6. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  7. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  8. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  9. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  10. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  11. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  12. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
38 more
  1. 2023Mistral 7Bcited by 3,065
  2. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  3. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  4. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  5. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  6. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  7. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  8. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  9. 2023Pythia: A Suite for Analyzing Large Language Models Across Training and Scalingcited by 1,734
  10. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  11. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  12. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,210
  13. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  14. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  15. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  16. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 876
  17. 2023Reasoning with Language Model is Planning with World Modelcited by 846
  18. 2022Galactica: A Large Language Model for Sciencecited by 736
  19. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 724
  20. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 721
  21. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 609
  22. 2023YaRN: Efficient Context Window Extension of Large Language Modelscited by 584
  23. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 580
  24. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledgecited by 469
  25. 2023Augmented Language Models: a Surveycited by 398
  26. 2022Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)cited by 396
  27. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agentscited by 385
  28. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Casescited by 383
  29. 2023Language Models can Solve Computer Taskscited by 371
  30. 2023MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedbackcited by 293
  31. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 288
  32. 2024OS-Copilot: Towards Generalist Computer Agents with Self-Improvementcited by 203
  33. 2023Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedbackcited by 202
  34. 2022TALM: Tool Augmented Language Modelscited by 197
  35. 2023OpenAGI: When LLM Meets Domain Expertscited by 196
  36. 2023RoCo: Dialectic Multi-Robot Collaboration with Large Language Modelscited by 171
  37. 2023War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Warscited by 143
  38. 2023Emergent autonomous scientific research capabilities of large language modelscited by 127

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 33; 2026: 53.

94 papers.

Sort:

By area:

  1. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,000
  2. 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 235
  3. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  4. 2025Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memorycited by 88
  5. 2025Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agentscited by 66
  6. 2024MoralBench: Moral Evaluation of LLMscited by 50
  7. 2025Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AIcited by 39
  8. 2025UFO2: The Desktop AgentOScited by 38
  9. 2025OmniRouter: Budget and Performance Controllable Multi-LLM Routingcited by 35
  10. 2025OS Agents: A Survey on MLLM-based Agents for General Computing Devices Usecited by 35
  11. 2024How Far Are We From AGI: Are LLMs All We Need?cited by 31
  12. 2025LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospectscited by 31
38 more
  1. 2026Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflowscited by 27
  2. 2024Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trendscited by 26
  3. 2025MCPXKIT: The Unified Toolkit for Analyzing Model Context Protocol Securitycited by 21
  4. 2025Towards Embodied Agentic AI: Review and Classification of LLM- and VLM-Driven Robot Autonomy and Interactioncited by 18
  5. 2026AI Harness Engineering: A Runtime Substrate for Foundation-Model Software Agentscited by 18
  6. 2025Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Taskscited by 17
  7. 2026Learning Personalized Agents from Human Feedbackcited by 16
  8. 2024Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interfacecited by 15
  9. 2024Defining and Detecting the Defects of the Large Language Model-based Autonomous Agentscited by 14
  10. 2025A Measurement Study of Model Context Protocol Ecosystemcited by 13
  11. 2025AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agentscited by 12
  12. 2025SOP-Agent: Empower General Purpose AI Agent with Domain-Specific SOPscited by 11
  13. 2026E-mem: Multi-agent based Episodic Context Reconstruction for LLM Agent Memorycited by 10
  14. 2026Agent libOS: A Runtime Substrate for Capability-Controlled Self-Evolving LLM Agentscited by 8
  15. 2025Modular Task Decomposition and Dynamic Collaboration in Multi-Agent Systems Driven by Large Language Modelscited by 7
  16. 2026Right to History: A Sovereignty Kernel for Verifiable AI Agent Executioncited by 7
  17. 2025Agentic Services Computingcited by 6
  18. 2025ColorAgent: Building A Robust, Personalized, and Interactive OS Agentcited by 6
  19. 2025EvoMem: Improving Multi-Agent Planning with Dual-Evolving Memorycited by 6
  20. 2025LLM-First Search: Self-Guided Exploration of the Solution Spacecited by 5
  21. 2026Advancing Multimodal Agent Reasoning with Long-Term Neuro-Symbolic Memorycited by 5
  22. 2024A Taxonomy of Architecture Options for Foundation Model-based Agents: Analysis and Decision Modelcited by 4
  23. 2025LiteCUA: Computer as MCP Server for Computer-Use Agent on AIOScited by 4
  24. 2025AwareCompiler: Agentic Context-Aware Compiler Optimization via a Synergistic Knowledge-Data Driven Frameworkcited by 4
  25. 2025Trusted AI Agents in the Cloudcited by 4
  26. 2026Holos: A Web-Scale LLM-Based Multi-Agent System for the Agentic Webcited by 4
  27. 2026ClawVM: Harness-Managed Virtual Memory for Stateful Tool-Using LLM Agentscited by 4
  28. 2025Knowledge-Augmented Large Language Model Agents for Explainable Financial Decision-Makingcited by 3
  29. 2026Agentic AI in Remote Sensing: Foundations, Taxonomy, and Emerging Systemscited by 3
  30. 2026Hippocampus: An Efficient and Scalable Memory Module for Agentic AIcited by 3
  31. 2026AgentOS: From Application Silos to a Natural Language-Driven Data Ecosystemcited by 3
  32. 2026Stop Means Stop: Measuring and Repairing the Enforcement Gap in Agent-Framework Control Primitivescited by 3
  33. 2024On-Device LLMs for SMEs: Challenges and Opportunitiescited by 2
  34. 2025ConsumerBench: Benchmarking Generative AI Applications on End-User Devicescited by 2
  35. 2026Architecting AgentOS: From Token-Level Context to Emergent System-Level Intelligencecited by 2
  36. 2026ProbeLogits: Kernel-Level LLM Inference Primitives for AI-Native Operating Systemscited by 2
  37. 2025Towards Machine-Generated Code for the Resolution of User Intentionscited by 1
  38. 2025LA-RCS: LLM-Agent-Based Robot Control Systemcited by 1

50 most cited of 94 All 94 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Cerebrum (AIOS SDK): A Platform for Agent Development, Deployment, Distribution, and Discovery
  2. 2025Agent-S: LLM Agentic workflow to automate Standard Operating Procedures
  3. 2025Towards Agentic OS: An LLM Agent Framework for Linux Schedulers
  4. 2026SARA: SLO-Aware Resource Allocation for Disaggregated Agentic LLM Services
  5. 2025Planet as a Brain: Towards Internet of AgentSites based on AIOS Server
  6. 2026Quine: Realizing LLM Agents as Native POSIX Processes
  7. 2026Agent Operating Systems (AOS): Integrating Agentic Control Planes into, and Beyond, Traditional Operating Systems
  8. 2026Orchestral AI: A Framework for Agent Orchestration