mlsanityData to 7 Oct 2026

Human Machine Social Hybrid Intelligence:A Collaborative Decision Making Framework for Large Model Agent Groups and Human Experts

arXiv 2510.24030 ↗First posted 28 Oct 2025cs.MAcited by 0

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

Abstract (arXiv)

The rapid advancements in large foundation models and multi-agent systems offer unprecedented capabilities, yet current Human-in-the-Loop (HiTL) paradigms inadequately integrate human expertise, often leading to cognitive overload and decision-making bottlenecks in complex, high-stakes environments. We propose the "Human-Machine Social Hybrid Intelligence" (HMS-HI) framework, a novel architecture designed for deep, collaborative decision-making between groups of human experts and LLM-powered AI agents. HMS-HI is built upon three core pillars: (1) a Shared Cognitive Space (SCS) for unified, multi-modal situational awareness and structured world modeling; (2) a Dynamic Role and Task Allocation (DRTA) module that adaptively assigns tasks to the most suitable agent (human or AI) based on capabilities and workload; and (3) a Cross-Species Trust Calibration (CSTC) protocol that fosters transparency, accountability, and mutual adaptation through explainable declarations and structured feedback. Validated in a high-fidelity urban emergency response simulation, HMS-HI significantly reduced civilian casualties by 72% and cognitive load by 70% compared to traditional HiTL approaches, demonstrating superior decision quality, efficiency, and human-AI trust. An ablation study confirms the critical contribution of each module, highlighting that engineered trust and shared context are foundational for scalable, synergistic human-AI collaboration.

Key facts. No citing papers in the map yet (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 37 of its 61 references that are in the map. First posted on arXiv 28 Oct 2025.

Builds on

37 of 61 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Theory of Mind for Multi-Agent Collaboration via Large Language Models16 Oct
  2. 2022A Generalist Agent12 May

Other references · 35

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  5. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  6. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  7. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
  8. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  9. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  10. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  11. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,624
  12. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
23 more
  1. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
  2. 2023Mastering Diverse Domains through World Modelscited by 1,193
  3. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,075
  4. 2022Token Merging: Your ViT But Fastercited by 995
  5. 2021GLaM: Efficient Scaling of Language Models with Mixture-of-Expertscited by 890
  6. 2018Recurrent World Models Facilitate Policy Evolutioncited by 761
  7. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 697
  8. 2023Scaling Vision Transformers to 22 Billion Parameterscited by 690
  9. 2022Transformers are Sample-Efficient World Modelscited by 317
  10. 2024MoE-LLaVA: Mixture of Experts for Large Vision-Language Modelscited by 298
  11. 2023Towards Generalist Biomedical AIcited by 286
  12. 2018Machine Theory of Mindcited by 222
  13. 2022Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directionscited by 116
  14. 2023Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Modelcited by 115
  15. 2020CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learningcited by 109
  16. 2019Open-ended Learning in Symmetric Zero-sum Gamescited by 96
  17. 2018Modeling Others using Oneself in Multi-Agent Reinforcement Learningcited by 64
  18. 2023ReSup: Reliable Label Noise Suppression for Facial Expression Recognitioncited by 14
  19. 2025FedQuad: Adaptive Layer-wise LoRA Deployment and Activation Quantization for Federated Fine-Tuningcited by 10
  20. 2025Accelerating Mixture-of-Expert Inference with Adaptive Expert Split Mechanismcited by 9
  21. 2024Accelerating End-Cloud Collaborative Inference via Near Bubble-free Pipeline Optimizationcited by 7
  22. 2025Mitigating Catastrophic Forgetting with Adaptive Transformer Block Expansion in Federated Fine-Tuningcited by 7
  23. 2025Towards Communication-Efficient Decentralized Federated Graph Learning over Non-IID Datacited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025A Call for Collaborative Intelligence: Why Human-Agent Systems Should Precede AI Autonomy
  2. 2026Human Tool: An MCP-Style Framework for Human-Agent Collaboration
  3. 2025HMCF: A Human-in-the-loop Multi-Robot Collaboration Framework Based on Large Language Models
  4. 2026Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learning
  5. 2025Towards Cognitive Synergy in LLM-Based Multi-Agent Systems: Integrating Theory of Mind and Critical Evaluation
  6. 2026Toward Human-Centered Multi-Agent Systems: Integrating Cognition, Culture, Values, and Cooperation in AI Agents
  7. 2026From Human-Human Collaboration to Human-Agent Collaboration: A Vision, Design Philosophy, and an Empirical Framework for Achieving Successful Partnerships Between Humans and LLM Agents
  8. 2025Human-Artificial Interaction in the Age of Agentic AI: A System-Theoretical Approach