mlsanityData to 7 Oct 2026

S-Agents: Self-organizing Agents in Open-ended Environments

arXiv 2402.04578 ↗First posted 7 Feb 2024cs.AI cs.MAcited by 22

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

Abstract (arXiv)

Leveraging large language models (LLMs), autonomous agents have significantly improved, gaining the ability to handle a variety of tasks. In open-ended settings, optimizing collaboration for efficiency and effectiveness demands flexible adjustments. Despite this, current research mainly emphasizes fixed, task-oriented workflows and overlooks agent-centric organizational structures. Drawing inspiration from human organizational behavior, we introduce a self-organizing agent system (S-Agents) with a "tree of agents" structure for dynamic workflow, an "hourglass agent architecture" for balancing information priorities, and a "non-obstructive collaboration" method to allow asynchronous task execution among agents. This structure can autonomously coordinate a group of agents, efficiently addressing the challenges of open and dynamic environments without human intervention. Our experiments demonstrate that S-Agents proficiently execute collaborative building tasks and resource collection in the Minecraft environment, validating their effectiveness.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 43 of its 99 references that are in the map. First posted on arXiv 7 Feb 2024.

Builds on

43 of 99 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors21 Aug
  2. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug
  3. 2023Building Cooperative Embodied Agents Modularly with Large Language Models5 Jul
  4. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents3 Feb

Other references · 39

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  6. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  7. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  8. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  9. 2023Mastering Diverse Domains through World Modelscited by 1,193
  10. 2023Teaching Large Language Models to Self-Debugcited by 963
  11. 2022Socratic Models: Composing Zero-Shot Multimodal Reasoning with Languagecited by 513
  12. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledgecited by 469
27 more
  1. 2022Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videoscited by 338
  2. 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoningcited by 311
  3. 2023Large Language Models as Tool Makerscited by 293
  4. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 288
  5. 2023Self-collaboration Code Generation via ChatGPTcited by 255
  6. 2023Playing repeated games with Large Language Modelscited by 213
  7. 2019MineRL: A Large-Scale Dataset of Minecraft Demonstrationscited by 210
  8. 2023RoCo: Dialectic Multi-Robot Collaboration with Large Language Modelscited by 171
  9. 2023JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Modelscited by 170
  10. 2023Language Models Meet World Models: Embodied Experiences Enhance Language Modelscited by 123
  11. 2023Mindstorms in Natural Language-Based Societies of Mindcited by 105
  12. 2023Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?cited by 104
  13. 2023MindAgent: Emergent Gaming Interactioncited by 87
  14. 2023See and Think: Embodied Agent in Virtual Environmentcited by 54
  15. 2021The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priorscited by 40
  16. 2021Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraftcited by 34
  17. 2021JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learningcited by 28
  18. 2019CraftAssist: A Framework for Dialogue-enabled Interactive Agentscited by 27
  19. 2022MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learnedcited by 26
  20. 2022Interactive Grounded Language Understanding in a Collaborative Environment: IGLU 2021cited by 23
  21. 2021SEIHAI: A Sample-efficient Hierarchical AI for the MineRL Competitioncited by 20
  22. 2023ThinkBot: Embodied Instruction Following with Thought Chain Reasoningcited by 19
  23. 2021NeurIPS 2021 Competition IGLU: Interactive Grounded Language Understanding in a Collaborative Environmentcited by 15
  24. 2022Masked Vision-Language Transformer in Fashioncited by 14
  25. 2023Transforming Human-Centered AI Collaboration: Redefining Embodied Agents Capabilities through Interactive Grounded Language Instructionscited by 13
  26. 2022Collecting Interactive Multi-modal Datasets for Grounded Language Understandingcited by 10
  27. 2015Open Ended Intelligence: The individuation of Intelligent Agentscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 9; 2025: 9; 2026: 4.

22 papers.

Sort:

By area:

  1. 2024Data Interpreter: An LLM Agent For Data Sciencecited by 222
  2. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  3. 2024ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulationcited by 106
  4. 2024A Survey on Large Language Model-Based Game Agentscited by 106
  5. 2024Embodied LLM Agents Learn to Cooperate in Organized Teamscited by 81
  6. 2025ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learningcited by 78
  7. 2024From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agentscited by 76
  8. 2024Project Sid: Many-agent simulations toward AI civilizationcited by 46
  9. 2024PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videoscited by 21
  10. 2025Virtual Agent Economiescited by 17
  11. 2025Generative Multi-Agent Collaboration in Embodied AI: A Systematic Reviewcited by 13
  12. 2024MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agentscited by 11
10 more
  1. 2024Transforming Agency. On the mode of existence of Large Language Modelscited by 7
  2. 2025BetaWeb: Towards a Blockchain-enabled Trustworthy Agentic Webcited by 7
  3. 2025Thinking Beyond Tokens: From Brain-Inspired Intelligence to Cognitive Foundations for Artificial General Intelligence and its Societal Impactcited by 6
  4. 2025AI Agent Behavioral Sciencecited by 5
  5. 2025An Entity Linking Agent for Question Answeringcited by 2
  6. 2026Mixing Expert Knowledge: Bring Human Thoughts Back To the Game of Gocited by 1
  7. 2026Order from Chaos: Physical World Understanding from Glitchy Gameplay Videoscited by 1
  8. 2025Is the `Agent' Paradigm a Limiting Framework for Next-Generation Intelligent Systems?cited by 0
  9. 2026CHAL: Council of Hierarchical Agentic Languagecited by 0
  10. 2026Workerville: Towards an Organizational Behavior Account of Agent Safetycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024MorphAgent: Empowering Agents through Self-Evolving Profiles and Decentralized Collaboration
  2. 2025Orchestrating Human-AI Teams: The Manager Agent as a Unifying Research Challenge
  3. 2026Multi-agent Framework for Time-Sensitive Complementary Collaboration in Minecraft
  4. 2026Architecting Agentic Communities using Design Patterns
  5. 2024Towards Effective GenAI Multi-Agent Collaboration: Design and Evaluation for Enterprise Applications
  6. 2025Self-Organizing Agent Network for LLM-based Workflow Automation
  7. 2025Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning
  8. 2025Stochastic Self-Organization in Multi-Agent Systems