mlsanityData to 14 Oct 2026

Towards Pervasive Distributed Agentic Generative AI -- A State of The Art

arXiv 2506.13324 ↗First posted 16 Jun 2025cs.AI cs.MAcited by 4

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

The rapid advancement of intelligent agents and Large Language Models (LLMs) is reshaping the pervasive computing field. Their ability to perceive, reason, and act through natural language understanding enables autonomous problem-solving in complex pervasive environments, including the management of heterogeneous sensors, devices, and data. This survey outlines the architectural components of LLM agents (profiling, memory, planning, and action) and examines their deployment and evaluation across various scenarios. Than it reviews computational and infrastructural advancements (cloud to edge) in pervasive computing and how AI is moving in this field. It highlights state-of-the-art agent deployment strategies and applications, including local and distributed execution on resource-constrained devices. This survey identifies key challenges of these agents in pervasive computing such as architectural, energetic and privacy limitations. It finally proposes what we called "Agent as a Tool", a conceptual framework for pervasive agentic AI, emphasizing context awareness, modularity, security, efficiency and effectiveness.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 86 of its 149 references that are in the map. First posted on arXiv 16 Jun 2025.

Builds on

86 of 149 references.

Closest ancestors · 15

Same direction, newest first

  1. 2025Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks12 Mar
  2. 2025Division-of-Thoughts: Harnessing Hybrid Language Model Synergy for Efficient On-Device Agents6 Feb
  3. 2025MASTER: A Multi-Agent System with LLM Specialized MCTS24 Jan
  4. 2025IntellAgent: A Multi-Agent Framework for Evaluating Conversational AI Systems19 Jan
  5. 2024TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks18 Dec
  6. 2024Agent-as-a-Judge: Evaluate Agents with Agents14 Oct
  7. 2024WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Exploration28 Aug
  8. 2024Recursive Introspection: Teaching Language Model Agents How to Self-Improve25 Jul
  9. 2024AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning17 Jun
  10. 2024ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation23 May
  11. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agents2 Feb
  12. 2024Can Large Language Models be Trusted for Evaluation? Scalable Meta-Evaluation of LLMs as Evaluators via Agent Debate30 Jan
3 more
  1. 2024AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents24 Jan
  2. 2023The Rise and Potential of Large Language Model Based Agents: A Survey14 Sep
  3. 2023A Survey on Large Language Model based Autonomous Agents22 Aug

Other references · 71

  1. 2017Attention Is All You Needcited by 60,361
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  6. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  7. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  8. 2023Let's Verify Step by Stepcited by 3,789
  9. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  10. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 2,006
  11. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,737
  12. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,251
38 more
  1. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
  2. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,071
  3. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
  4. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 1,002
  5. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 634
  6. 2024Generative Verifiers: Reward Modeling as Next-Token Predictioncited by 480
  7. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 425
  8. 2024Titans: Learning to Memorize at Test Timecited by 328
  9. 2024Agent-SafetyBench: Evaluating the Safety of LLM Agentscited by 306
  10. 2024Quiet-STaR: Language Models Can Teach Themselves to Think Before Speakingcited by 301
  11. 2024MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Casescited by 223
  12. 2024V-STaR: Training Verifiers for Self-Taught Reasonerscited by 217
  13. 2024APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasetscited by 198
  14. 2024Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaborationcited by 189
  15. 2023AutoDroid: LLM-powered Task Automation in Androidcited by 184
  16. 2024PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Actioncited by 171
  17. 2024Agent AI: Surveying the Horizons of Multimodal Interactioncited by 170
  18. 2025Qwen2.5-1M Technical Reportcited by 164
  19. 2024Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Makingcited by 144
  20. 2025Magma: A Foundation Model for Multimodal AI Agentscited by 139
  21. 2024MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolutioncited by 134
  22. 2025Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Taskscited by 131
  23. 2024AutoWebGLM: A Large Language Model-based Web Navigating Agentcited by 130
  24. 2024Mobile Edge Intelligence for Large Language Models: A Contemporary Surveycited by 128
  25. 2025CollabLLM: From Passive Responders to Active Collaboratorscited by 124
  26. 2024Limitations of the LLM-as-a-Judge Approach for Evaluating LLM Outputs in Expert Knowledge Taskscited by 106
  27. 2024Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generationcited by 100
  28. 2023EdgeMoE: Empowering Sparse Large Language Models on Mobile Devicescited by 69
  29. 2025InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflectioncited by 67
  30. 2024MobileAgentBench: An Efficient and User-Friendly Benchmark for Mobile LLM Agentscited by 63
  31. 2023Explore, Select, Derive, and Recall: Augmenting LLM with Human-like Memory for Mobile Task Automationcited by 58
  32. 2023See and Think: Embodied Agent in Virtual Environmentcited by 54
  33. 2024Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTScited by 54
  34. 2024Octopus v2: On-device language model for super agentcited by 47
  35. 2024AI Flow at the Network Edgecited by 46
  36. 2024AI-Augmented Brainwriting: Investigating the use of LLMs in group ideationcited by 44
  37. 2024LlamaTouch: A Faithful and Scalable Testbed for Mobile UI Task Automationcited by 36
  38. 2025Firewalls to Secure Dynamic LLM Agentic Networkscited by 36

50 most cited of 71 All 71 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Securing Agentic AI: Threat Modeling and Risk Analysis for Network Monitoring Agentic AI Systemcited by 6
  2. 2026Exploring the Topology and Memory of Consensus: How LLM Agents Agree, Fragment, or Settle When Forming Conventionscited by 3
  3. 2025Reason-Plan-ReAct: A Reasoner-Planner Supervising a ReAct Executor for Complex Enterprise Taskscited by 1
  4. 2026On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026The Path Ahead for Agentic AI: Challenges and Opportunities
  2. 2026Agentic Artificial Intelligence (AI): Architectures, Taxonomies, and Evaluation of Large Language Model Agents
  3. 2025Agentic AI Frameworks: Architectures, Protocols, and Design Challenges
  4. 2025A Survey of AI Agent Protocols
  5. 2025Distinguishing Autonomous AI Agents from Collaborative Agentic Systems: A Comprehensive Framework for Understanding Modern Intelligent Architectures
  6. 2025Large Language Model Powered Intelligent Urban Agents: Concepts, Capabilities, and Applications
  7. 2023Agents: An Open-source Framework for Autonomous Language Agents
  8. 2024Practical Considerations for Agentic LLM Systems