A journal of IEEE and CAA , publishes high-quality papers in English on original theoretical/experimental research and development in all areas of automation
Advanced Search
Volume 13 Issue 5
May  2026

IEEE/CAA Journal of Automatica Sinica

  • JCR Impact Factor: 19.2, Top 1 (SCI Q1)
    CiteScore: 28.2, Top 1% (Q1)
    Google Scholar h5-index: 95， TOP 5
Turn off MathJax
Article Contents
Article Navigation >  IEEE/CAA Journal of Automatica Sinica  > 2026  >  13(5): 1007-1023
Z. Wang, M. Gong, Q. Sun, J. Xu, S. Mao, X. Jin, Q.-L. Han, and Y. Tang, “Multi-agent systems: From classical paradigms to large foundation model-enabled futures,” IEEE/CAA J. Autom. Sinica, vol. 13, no. 5, pp. 1007–1023, May 2026. doi: 10.1109/JAS.2026.126113
Citation: Z. Wang, M. Gong, Q. Sun, J. Xu, S. Mao, X. Jin, Q.-L. Han, and Y. Tang, “Multi-agent systems: From classical paradigms to large foundation model-enabled futures,” IEEE/CAA J. Autom. Sinica, vol. 13, no. 5, pp. 1007–1023, May 2026. doi: 10.1109/JAS.2026.126113
shu

Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures

doi: 10.1109/JAS.2026.126113
Funds:  This work was supported in part by the National Natural Science Foundation of China (62233005, U2441245, U25B6002, 62503247), Shanghai Municipal Commission of Economy and Informatization (RZ-RGZN-01-25-0951), and Natural Science Foundation of Jiangsu Province (BK20230605)
More Information
    Abstract
  • With the rapid advancement of artificial intelligence, multi-agent systems (MASs) are evolving from classical paradigms toward architectures built upon large foundation models (LFMs). This survey provides a systematic review and comparative analysis of classical MASs (CMASs) and LFM-based MASs (LMASs). First, within a closed-loop coordination framework, CMASs are reviewed across four fundamental dimensions: perception, communication, decision-making, and control. Beyond this framework, LMASs integrate LFMs to lift collaboration from low-level state exchanges to semantic-level reasoning, enabling more flexible coordination and improved adaptability across diverse scenarios. Then, a comparative analysis is conducted to contrast CMASs and LMASs across architecture, operating mechanism, adaptability, and application. Finally, future perspectives on MASs are presented, summarizing open challenges and potential research opportunities.

     

    • FullText(HTML)
  • loading
    • 1 https://modelcontextprotocol.io/introduction
    2 https://github.com/a2aproject/A2A
    3 https://agent-network-protocol.com/
    4 https://github.com/openclaw/openclaw
    5 https://www.moltbook.com/
    6 https://github.com/anthropics/claude-code
    7 https://github.com/openai/codex
    Zixiang Wang and Mengjia Gong contributed equally to this work.
    References(144)
  • [1]
    Z. Mandi, S. Jain, and S. Song, “RoCo: Dialectic multi-robot collaboration with large language models,” in Proc. IEEE Int. Conf. Robotics and Automation, Yokohama, Japan, 2024, pp. 286−299.
    [2]
    J. S. Park, J. O’Brien, C. J. Cai, M. R. Morris, P. Liang, and M. S. Bernstein, “Generative agents: Interactive simulacra of human behavior,” in Proc. 36th Annu. ACM Symp. User Interface Software and Technology, San Francisco, USA, 2023, Art. no. 2.
    [3]
    G. Fan, P. Wu, M. Yang, J. Wang, D. Ran, J. Dai, Y. Zhang, L. Cao, W. Xu, and P. Zhang, “Internet of satellites (IoS) for intelligent satellite cluster: Applications, methods, and challenges,” Engineering, vol. 54, pp. 155–170, Nov. 2025. doi: 10.1016/j.eng.2025.08.024
    [4]
    K. Bojappa and J. Lee, “Review on particle swarm optimization: Application toward autonomous dynamical systems,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 9, pp. 1762–1775, Sep. 2025. doi: 10.1109/JAS.2024.125028
    [5]
    Y. Cao, W. Yu, W. Ren, and G. Chen, “An overview of recent progress in the study of distributed multi-agent coordination,” IEEE Trans. Ind. Inf., vol. 9, no. 1, pp. 427–438, Feb. 2013. doi: 10.1109/TII.2012.2219061
    [6]
    T.-Y. Chen, W.-N. Chen, F.-F. Wei, X.-Q. Guo, W.-X. Song, R. Zhu, Q. Lin, and J. Zhang, “The confluence of evolutionary computation and multi-agent systems: A survey,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 11, pp. 2175–2193, Nov. 2025. doi: 10.1109/JAS.2025.125246
    [7]
    P. Stone and M. Veloso, “Multiagent systems: A survey from a machine learning perspective,” Auton. Robots, vol. 8, no. 3, pp. 345–383, Jun. 2000. doi: 10.1023/A:1008942012299
    [8]
    K.-T. Tran, D. Dao, M.-D. Nguyen, Q.-V. Pham, B. O’Sullivan, and H. D. Nguyen, “Multi-agent collaboration mechanisms: A survey of LLMs,” arXiv preprint arXiv: 2501.06322, 2025.
    [9]
    R. Olfati-Saber, J. A. Fax, and R. M. Murray, “Consensus and cooperation in networked multi-agent systems,” Proc. IEEE, vol. 95, no. 1, pp. 215–233, Jan. 2007. doi: 10.1109/JPROC.2006.887293
    [10]
    D. Huh and P. Mohapatra, “Multi-agent reinforcement learning: A comprehensive survey,” arXiv preprint arXiv: 2312.10256, 2023.
    [11]
    C. Zhang, L. Ji, S. Yang, X. Guo, and H. Li, “Distributed optimal consensus control for multiagent systems based on event-triggered and prioritized experience replay strategies,” Sci. China Inf. Sci., vol. 68, no. 1, Art. no. 112206, 2025. doi: 10.1007/s11432-023-4183-4
    [12]
    Z. Peng, B. Wu, G. Wen, C. Pan, and T. Huang, “Distributed adaptive formation with state constraints for multi-agent systems: NE and RNE searching in aggregative games,” Sci. China Inf. Sci., vol. 69, no. 6, Art. no. 162201, Jan. 2026. doi: 10.1007/s11432-025-4738-4
    [13]
    J. Xu, J. Luo, X. Cao, Y. Gao, S. Mao, M. Wang, et al., “Cooperative task scheduling and resource allocation of embodied multi-satellite systems: AI-driven perspective,” Sci. China Technol. Sci., vol. 69, no. 1, Art. no. 1100301, Jan. 2026. doi: 10.1007/s11431-025-3156-1
    [14]
    A. Chakraborty and A. K. Kar, “Swarm intelligence: A review of algorithms,” in Nature-Inspired Computing and Optimization, S. Patnaik, X.-S. Yang, and K. Nakamatsu, Eds. Cham, Germany: Springer, 2017, pp. 475−494.
    [15]
    T. Li, K. Zhu, N. C. Luong, D. Niyato, Q. Wu, Y. Zhang, and B. Chen, “Applications of multi-agent reinforcement learning in future internet: A comprehensive survey,” IEEE Commun. Surv. Tutorials, vol. 24, no. 2, pp. 1240–1279, 2022. doi: 10.1109/COMST.2022.3160697
    [16]
    L. Yuan, Z. Zhang, L. Li, C. Guan, and Y. Yu, “A survey of progress on cooperative multi-agent reinforcement learning in open environment,” arXiv preprint arXiv: 2312.01058, 2023.
    [17]
    T. Guo, X. Chen, Y. Wang, R. Chang, S. Pei, N. V. Chawla, O. Wiest, and X. Zhang, “Large language model based multi-agents: A survey of progress and challenges,” in Proc. 33rd Int. Joint Conf. Artificial Intelligence, Jeju, Korea, 2024, Art. no. 890.
    [18]
    Z. Xi, W. Chen, X. Guo, W. He, Y. Ding, B. Hong, et al., “The rise and potential of large language model based agents: A survey,” Sci. China Inf. Sci., vol. 68, no. 2, Art. no. 121101, Jan. 2025. doi: 10.1007/s11432-024-4222-0
    [19]
    Y. Wang, Y. Pan, Z. Su, Y. Deng, Q. Zhao, L. Du, T. H. Luan, J. Kang, and D. Niyato, “Large model-based agents: State-of-the-art, cooperation paradigms, security and privacy, and future trends,” IEEE Commun. Surv. Tutorials, vol. 28, pp. 1906–1949, 2026. doi: 10.1109/COMST.2025.3576176
    [20]
    M. A. Ferrag, N. Tihanyi, and M. Debbah, “From LLM reasoning to autonomous AI agents: A comprehensive review,” arXiv preprint arXiv: 2504.19678, 2025.
    [21]
    F. Wu, T. Shen, T. Bäck, J. Chen, G. Huang, Y. Jin, et al., “Knowledge-empowered, collaborative, and co-evolving AI models: The post-LLM roadmap,” Engineering, vol. 44, pp. 87–100, Jan. 2025. doi: 10.1016/j.eng.2024.12.008
    [22]
    G. Zhang, H. Geng, X. Yu, Z. Yin, Z. Zhang, Z. Tan, et al., “The landscape of agentic reinforcement learning for LLMs: A survey,” Trans. Mach. Learn. Res., Jan. 2026. [Online]. Available: https://openreview.net/forum?id=RY19y2RI1O.
    [23]
    M. Abou Ali, F. Dornaika, and J. Charafeddine, “Agentic AI: A comprehensive survey of architectures, applications, and future directions,” Artif. Intell. Rev., vol. 59, no. 1, Art. no. 11, 2026. doi: 10.1007/s10462-025-11422-4
    [24]
    S. Du, J. Zhao, J. Shi, Z. Xie, X. Jiang, Y. Bai, and L. He, “A survey on the optimization of large language model-based agents,” ACM Comput. Surv., vol. 58, no. 9, Art. no. 223, Jul. 2026.
    [25]
    B. Zhao, L. G. Foo, P. Hu, C. Theobalt, H. Rahmani, and J. Liu, “LLM-based agentic reasoning frameworks: A survey from methods to scenarios,” arXiv preprint arXiv: 2508.17692, 2025.
    [26]
    M. Wooldridge, An Introduction to Multiagent Systems. 2nd ed. Hoboken, USA: John Wiley & Sons, 2009.
    [27]
    H. L. Chen, Q. Y. Sun, F. F. Li, and Y. Tang, “Computer vision tasks for intelligent aerospace perception: An overview,” Sci. China Technol. Sci., vol. 67, no. 9, pp. 2727–2748, Aug. 2024. doi: 10.1007/s11431-024-2714-4
    [28]
    Q. Chen, S. Tang, Q. Yang, and S. Fu, “Cooper: Cooperative perception for connected autonomous vehicles based on 3D point clouds,” in Proc. IEEE 39th Int. Conf. Distributed Computing Systems, Dallas, USA, 2019, pp. 514−524.
    [29]
    H. Yu, Y. Luo, M. Shu, Y. Huo, Z. Yang, Y. Shi, et al., “DAIR-V2X: A large-scale dataset for vehicle-infrastructure cooperative 3D object detection,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, New Orleans, USA, 2022, pp. 21361−21370.
    [30]
    B. Liu, J. Teng, H. Xue, E. Wang, C. Zhu, P. Wang, and L. Wu, “mmCooper: A multi-agent multi-stage communication-efficient and collaboration-robust cooperative perception framework,” in Proc. IEEE/CVF Int. Conf. Computer Vision, Honolulu, HI, USA, 2025, pp. 28396−28406.
    [31]
    S. Zhang, C. Wang, H. Dong, X. Zhao, and C. Guan, “A novel fusion attention-based lightweight model for pipeline weld multiscale defect detection,” IEEE Trans. Ind. Inf., 2026, DOI: 10.1109/TII.2026.3659675.
    [32]
    K. Yang, D. Yang, J. Zhang, M. Li, Y. Liu, J. Liu, H. Wang, P. Sun, and L. Song, “Spatio-temporal domain awareness for multi-agent collaborative perception,” in Proc. IEEE/CVF Int. Conf. Computer Vision, Paris, France, 2023, pp. 23383−23392.
    [33]
    S. Hong, Y. Liu, Z. Li, S. Li, and Y. He, “Multi-agent collaborative perception via motion-aware robust communication network,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Seattle, USA, 2024, pp. 15301−15310.
    [34]
    J. Zhou, P. Dai, Q. Wei, B. Liu, X. Wu, and J. Wang, “Pragmatic heterogeneous collaborative perception via generative communication mechanism,” arXiv preprint arXiv: 2510.19618, 2025.
    [35]
    L. Sun, Y. Yang, Q. Duan, Y. Shi, C. Lyu, Y.-C. Chang, C.-T. Lin, and Y. Shen, “Multi-agent coordination across diverse applications: A survey,” arXiv preprint arXiv: 2502.14743, 2025.
    [36]
    X. Zhang, S. Cheng, Z. Zhong, and J. Yu, “Network topology and information efficiency of multi-agent systems: Study based on MARL,” arXiv preprint arXiv: 2510.07888v1, 2025.
    [37]
    S. Ding, W. Du, L. Ding, J. Zhang, L. Guo, and B. An, “Robust multi-agent communication with graph information bottleneck optimization,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 46, no. 5, pp. 3096–3107, May 2024. doi: 10.1109/TPAMI.2023.3337534
    [38]
    G. Hu, Y. Zhu, D. Zhao, M. Zhao, and J. Hao, “Event-triggered communication network with limited-bandwidth constraint for multi-agent reinforcement learning,” IEEE Trans. Neural Netw. Learn. Syst., vol. 34, no. 8, pp. 3966–3978, Aug. 2023. doi: 10.1109/TNNLS.2021.3121546
    [39]
    Y. Tang, X. Jin, Y. Shi, and W. Du, “Event-triggered attitude synchronization of multiple rigid body systems with velocity-free measurements,” Automatica, vol. 143, Art. no. 110460, Sep. 2022. doi: 10.1016/j.automatica.2022.110460
    [40]
    X. Jin, Y. Shi, Y. Tang, H. Werner, and J. Kurths, “Event-triggered fixed-time attitude consensus with fixed and switching topologies,” IEEE Trans. Automat. Control, vol. 67, no. 8, pp. 4138–4145, Aug. 2022. doi: 10.1109/TAC.2021.3108514
    [41]
    H. Wang, B. Chen, T. Zhang, and B. Wang, “Learning to communicate through implicit communication channels,” in Proc. 13th Int. Conf. Learning Representations, Singapore, Singapore, 2025, pp. 55179−55195.
    [42]
    W. Jin, H. Du, B. Zhao, X. Tian, B. Shi, and G. Yang, “A comprehensive survey on multi-agent cooperative decision-making: Scenarios, approaches, challenges and perspectives,” arXiv preprint arXiv: 2503.13415, 2025.
    [43]
    L. Panait and S. Luke, “Cooperative multi-agent learning: The state of the art,” Auton. Agent Multi-Agent Syst., vol. 11, no. 3, pp. 387–434, Nov. 2005. doi: 10.1007/s10458-005-2631-2
    [44]
    L. Wang, Z. Liu, S. Yuan, and Z. Pu, “Distributed Nash equilibrium for pursuit-evasion game with one evader and multiple pursuers,” Sci. China Inf. Sci., vol. 68, no. 9, Art. no. 192205, Apr. 2025. doi: 10.1007/s11432-024-4274-8
    [45]
    J. Qin, Q. Ma, Y. Shi, and L. Wang, “Recent advances in consensus of multi-agent systems: A brief survey,” IEEE Trans. Ind. Electron., vol. 64, no. 6, pp. 4972–4983, Jun. 2017. doi: 10.1109/TIE.2016.2636810
    [46]
    A. Amirkhani and A. H. Barshooi, “Consensus in multi-agent systems: A review,” Artif. Intell. Rev., vol. 55, no. 5, pp. 3897–3935, Jun. 2022. doi: 10.1007/s10462-021-10097-x
    [47]
    W. Ren and R. W. Beard, “Consensus seeking in multiagent systems under dynamically changing interaction topologies,” IEEE Trans. Automat. Control, vol. 50, no. 5, pp. 655–661, May 2005. doi: 10.1109/TAC.2005.846556
    [48]
    S. E. Tuna, “Synchronizing linear systems via partial-state coupling,” Automatica, vol. 44, no. 8, pp. 2179–2184, Aug. 2008. doi: 10.1016/j.automatica.2008.01.004
    [49]
    S. Liu, T. Li, and L. Xie, “Distributed consensus for multiagent systems with communication delays and limited data rate,” SIAM J. Control Optim., vol. 49, no. 6, pp. 2239–2262, Jan. 2011. doi: 10.1137/100783091
    [50]
    A. Luo, Q. Zhou, H. Ma, and H. Li, “Observer-based consensus control for MASs with prescribed constraints via reinforcement learning algorithm,” IEEE Trans. Neural Netw. Learn. Syst., vol. 35, no. 12, pp. 17281–17291, Dec. 2024. doi: 10.1109/TNNLS.2023.3301538
    [51]
    Y. Zhang, Y. Wu, S. Ma, and K. H. Cheong, “Adaptive prescribed-time dynamic self-triggered time-varying bipartite formation control for uncertain nonlinear multiagent systems with actuator faults,” IEEE Trans. Cybern., vol. 56, no. 4, pp. 1945–1957, Apr. 2026. doi: 10.1109/TCYB.2026.3662437
    [52]
    K.-K. Oh, M.-C. Park, and H.-S. Ahn, “A survey of multi-agent formation control,” Automatica, vol. 53, pp. 424–440, Mar. 2015. doi: 10.1016/j.automatica.2014.10.022
    [53]
    W. Zhao, H. Liu, and F. L. Lewis, “Robust formation control for cooperative underactuated quadrotors via reinforcement learning,” IEEE Trans. Neural Netw. Learn. Syst., vol. 32, no. 10, pp. 4577–4587, Oct. 2021. doi: 10.1109/TNNLS.2020.3023711
    [54]
    T. Wu, S. He, J. Liu, S. Sun, K. Liu, Q.-L. Han, and Y. Tang, “A brief overview of ChatGPT: The history, status quo and potential future development,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 5, pp. 1122–1136, May 2023. doi: 10.1109/JAS.2023.123618
    [55]
    L. Xiong, H. Wang, X. Chen, L. Sheng, Y. Xiong, J. Liu, Y. Xiao, H. Chen, Q.-L. Han, and Y. Tang, “DeepSeek: Paradigm shifts and technical evolution in large AI models,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 5, pp. 841–858, May 2025. doi: 10.1109/JAS.2025.125495
    [56]
    C. Qian, W. Liu, H. Liu, N. Chen, Y. Dang, J. Li, et al., “ChatDev: Communicative agents for software development,” in Proc. 62nd Annu. Meeting of the Association for Computational Linguistics, Bangkok, Thailand, 2024, pp. 15174−15186.
    [57]
    S. Hong, M. Zhuge, J. Chen, X. Zheng, Y. Cheng, J. Wang, et al., “MetaGPT: Meta programming for a multi-agent collaborative framework,” in Proc. 12th Int. Conf. Learning Representation, Vienna, Austria, 2024, pp. 23247−23275.
    [58]
    S. Hu, C. Lu, and J. Clune, “Automated design of agentic systems,” in Proc. 13th Int. Conf. Learning Representations, Singapore, Singapore, 2025.
    [59]
    K. Swanson, W. Wu, N. L. Bulaong, J. E. Pak, and J. Zou, “The Virtual Lab of AI agents designs new SARS-CoV-2 nanobodies,” Nature, vol. 646, no. 8085, pp. 716–723, Jul. 2025. doi: 10.1038/s41586-025-09442-9
    [60]
    J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proc. Conf. North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, USA, 2019, pp. 4171−4186.
    [61]
    K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Las Vegas, USA, 2016, pp. 770−778.
    [62]
    H. Chae, N. Kim, K. T.-I. Ong, M. Gwak, G. Song, J. Kim, S. Kim, D. Lee, and J. Yeo, “Web agents with world models: Learning and leveraging environment dynamics in web navigation,” in Proc. 13th Int. Conf. Learning Representations, Singapore, Singapore, 2025.
    [63]
    S. Qiao, R. Fang, N. Zhang, Y. Zhu, X. Chen, S. Deng, Y. Jiang, P. Xie, F. Huang, and H. Chen, “Agent planning with world knowledge model,” in Proc. 38th Int. Conf. Neural Information Processing Systems, Vancouver, Canada, 2024, Art. no. 3646.
    [64]
    H. Wei, Z. Zhang, S. He, T. Xia, S. Pan, and F. Liu, “PlanGenLLMs: A modern survey of LLM planning capabilities,” in Proc. 63rd Annu. Meeting of the Association for Computational Linguistics, Vienna, Austria, 2025.
    [65]
    J. Wei, X. Wang, D. Schuurmans, M. Bosma, B. Ichter, F. Xia, E. H. Chi, Q. V. Le, and D. Zhou, “Chain-of-thought prompting elicits reasoning in large language models,” in Proc. 36th Int. Conf. Neural Information Processing Systems, New Orleans, USA, 2022, Art. no. 1800.
    [66]
    Z. Liu, X. Bai, K. Chen, X. Chen, X. Li, Y. Xiang, et al., “A survey on the feedback mechanism of LLM-based AI agents,” in Proc. 34th Int. Joint Conf. Artificial Intelligence, Montreal, Canada, 2025, Art. no. 1175.
    [67]
    Q. Wu, G. Bansal, J. Zhang, Y. Wu, B. Li, E. Zhu, et al., “AutoGen: Enabling next-gen LLM applications via multi-agent conversation,” arXiv preprint arXiv: 2308.08155, 2023.
    [68]
    X. Huang, J. Lian, Y. Lei, J. Yao, D. Lian, and X. Xie, “Recommender AI agent: Integrating large language models for interactive recommendations,” ACM Trans. Inf. Syst., vol. 43, no. 4, Art. no. 96, Jul. 2025.
    [69]
    Z. Zhou, J. Song, K. Yao, Z. Shu, and L. Ma, “ISR-LLM: Iterative self-refined large language model for long-horizon sequential task planning,” in Proc. IEEE Int. Conf. Robotics and Automation, Yokohama, Japan, 2024, pp. 2081−2088.
    [70]
    Z. Shi, M. Fang, and L. Chen, “Monte Carlo planning with large language model for text-based game agents,” in Proc. 13th Int. Conf. Learning Representations, Singapore, Singapore, 2025.
    [71]
    M. Hu, P. Zhao, C. Xu, Q. Sun, J.-G. Lou, Q. Lin, P. Luo, and S. Rajmohan, “AgentGen: Enhancing planning abilities for large language model based agent via environment and task generation,” in Proc. 31st ACM SIGKDD Conf. Knowledge Discovery and Data Mining V.1, Toronto, Canada, 2025, pp. 496−507.
    [72]
    Q. Zheng, H. Liu, X. Zhang, C. Yan, X. Cao, T. Gong, et al., “Machine memory intelligence: Inspired by human memory mechanisms,” Engineering, vol. 55, pp. 24–35, Dec. 2025. doi: 10.1016/j.eng.2025.01.012
    [73]
    Z. Zhang, Q. Dai, X. Bo, C. Ma, R. Li, X. Chen, J. Zhu, Z. Dong, and J.-R. Wen, “A survey on the memory mechanism of large language model-based agents,” ACM Trans. Inf. Syst., vol. 43, no. 6, Art. no. 155, Nov. 2025.
    [74]
    S. Yao, J. Zhao, D. Yu, N. Du, I. Shafran, K. R. Narasimhan, and Y. Cao, “ReAct: Synergizing reasoning and acting in language models,” in Proc. 11th Int. Conf. Learning Representations, Kigali, Rwanda, 2023.
    [75]
    A. Zhao, D. Huang, Q. Xu, M. Lin, Y.-J. Liu, and G. Huang, “ExpeL: LLM agents are experiential learners,” in Proc. 38th AAAI Conf. Artificial Intelligence, Vancouver, Canada, 2024, pp. 19632−19642.
    [76]
    S. S. Chowa, R. Alvi, S. S. Rahman, A. Rahman, M. A. K. Raiaan, R. Islam, M. Hussain, and S. Azam, “From language to action: A review of large language models as autonomous agents and tool users,” Artif. Intell. Rev., vol. 59, no. 2, Art. no. 71, Jan. 2026. doi: 10.1007/s10462-025-11471-9
    [77]
    Y. Shen, K. Song, X. Tan, D. Li, W. Lu, and Y. Zhuang, “HuggingGPT: Solving AI tasks with ChatGPT and its friends in Hugging Face,” in Proc. 37th Int. Conf. Neural Information Processing Systems, New Orleans, USA, 2023, Art. no. 1657.
    [78]
    S. G. Patil, T. Zhang, X. Wang, and J. E. Gonzalez, “Gorilla: Large language model connected with massive APIs,” in Proc. 38th Int. Conf. Neural Information Processing Systems, Vancouver, Canada, 2024, Art. no. 4020.
    [79]
    Z. Feng, R. Xue, L. Yuan, Y. Yu, N. Ding, M. Liu, B. Gao, J. Sun, X. Zheng, and G. Wang, “Multi-agent embodied AI: Advances and future directions,” Sci. China Inf. Sci., vol. 69, no. 5, Art. no. 151202, Mar. 2026. doi: 10.1007/s11432-025-4820-4
    [80]
    T. Liang, Z. He, W. Jiao, X. Wang, Y. Wang, R. Wang, Y. Yang, S. Shi, and Z. Tu, “Encouraging divergent thinking in large language models through multi-agent debate,” in Proc. Conf. Empirical Methods in Natural Language Processing, Miami, USA, 2024.
    [81]
    W. Hu, W. Zhang, Y. Jiang, C. J. Zhang, X. Wei, and Q. Li, “Removal of hallucination on hallucination: Debate-augmented RAG,” in Proc. 63rd Annu. Meeting of the Association for Computational Linguistics, Vienna, Austria, 2025.
    [82]
    J. Shi, J. Zhao, Y. Wang, X. Wu, J. Li, and L. He, “CGMI: Configurable general multi-agent interaction framework,” arXiv preprint arXiv: 2308.12503, 2023.
    [83]
    X. Zhang, J. Lin, X. Mou, S. Yang, X. Liu, L. Sun, et al., “SocioVerse: A world model for social simulation powered by LLM agents and a pool of 10 million real-world users,” arXiv preprint arXiv: 2504.10157, 2025.
    [84]
    H. Zhou, H. Geng, X. Xue, L. Kang, Y. Qin, Z. Wang, Z. Yin, and L. Bai, “ReSo: A reward-driven self-organizing LLM-based multi-agent system for reasoning tasks,” in Proc. Conf. Empirical Methods in Natural Language Processing, Suzhou, China, 2025.
    [85]
    P. Trirat, W. Jeong, and S. J. Hwang, “AutoML-agent: A multi-agent LLM framework for full-pipeline AutoML,” arXiv preprint arXiv: 2410.02958, 2024.
    [86]
    N. Tastan, S. Horvath, and K. Nandakumar, “Stochastic self-organization in multi-agent systems,” arXiv preprint arXiv: 2510.00685, 2025.
    [87]
    K. Wang, G. Zhang, M. Ye, X. Deng, D. Wang, X. Hu, J. Guo, Y. Liu, and Y. Guo, “MAS.2: Self-generative, self-configuring, self-rectifying multi-agent systems,” arXiv preprint arXiv: 2509.24323, 2025.
    [88]
    B. Yan, Z. Zhou, L. Zhang, L. Zhang, Z. Zhou, D. Miao, Z. Li, C. Li, and X. Zhang, “Beyond self-talk: A communication-centric survey of LLM-based multi-agent systems,” arXiv preprint arXiv: 2502.14321, 2025.
    [89]
    G. Zhang, Y. Yue, Z. Li, S. Yun, G. Wan, K. Wang, D. Cheng, J. X. Yu, and T. Chen, “Cut the crap: An economical communication pipeline for LLM-based multi-agent systems,” in Proc. 13th Int. Conf. Learning Representations, Singapore, Singapore, 2025.
    [90]
    Z. Wang, Y. Wang, X. Liu, L. Ding, M. Zhang, J. Liu, and M. Zhang, “AgentDropout: Dynamic agent elimination for token-efficient and high-performance LLM-based multi-agent collaboration,” in Proc. 63rd Annu. Meeting of the Association for Computational Linguistics, Vienna, Austria, 2025.
    [91]
    Y. Lu, S. Yang, C. Qian, G. Chen, Q. Luo, Y. Wu, et al., “Proactive agent: Shifting LLM agents from reactive responses to active assistance,” arXiv preprint arXiv: 2410.12361, 2024.
    [92]
    W. Hua, M. Wan, S. Vadrevu, R. Nadel, Y. Zhang, and C. Wang, “Interactive speculative planning: Enhance agent efficiency through co-design of system and user interface,” arXiv preprint arXiv: 2410.00079, 2024.
    [93]
    Y. Shao, V. Samuel, Y. Jiang, J. Yang, and D. Yang, “Collaborative gym: A framework for enabling and evaluating human-agent collaboration,” arXiv preprint arXiv: 2412.15701, 2024.
    [94]
    W. Wang, Z. Ma, Z. Wang, C. Wu, J. Ji, W. Chen, X. Li, and Y. Yuan, “A survey of LLM-based agents in medicine: How far are we from Baymax?” in Proc. Findings of the Association for Computational Linguistics, Vienna, Austria, 2025.
    [95]
    G. Solak, G. J. G. Lahr, I. Ozdamar, and A. Ajoudani, “Context-aware collaborative pushing of heavy objects using skeleton-based intention prediction,” in Proc. IEEE Int. Conf. Robotics and Automation, Atlanta, USA, 2025, pp. 3110−3116.
    [96]
    S. Zhang, L. Dong, X. Li, S. Zhang, X. Sun, S. Wang, et al., “Instruction tuning for large language models: A survey,” ACM Comput. Surv., vol. 58, no. 7, Art. no. 169, May 2026.
    [97]
    Z. Wang, K. Wang, Q. Wang, P. Zhang, L. Li, Z. Yang, et al., “RAGEN: Understanding self-evolution in LLM agents via multi-turn reinforcement learning,” arXiv preprint arXiv: 2504.20073, 2025.
    [98]
    P. Cheng, Z. Wu, Z. Wu, A. Zhang, Z. Zhang, and G. Liu, “OS-Kairos: Adaptive interaction for MLLM-powered GUI agents,” in Proc. Findings of the Association for Computational Linguistics, Vienna, Austria, 2025.
    [99]
    Z. Xi, J. Huang, C. Liao, B. Huang, H. Guo, J. Liu, et al., “AgentGym-RL: Training LLM agents for long-horizon decision making through multi-turn reinforcement learning,” arXiv preprint arXiv: 2509.08755, 2025.
    [100]
    X. Luo, Y. Zhang, Z. He, Z. Wang, S. Zhao, D. Li, L. K. Qiu, and Y. Yang, “Agent Lightning: Train ANY AI agents with reinforcement learning,” arXiv preprint arXiv: 2508.03680, 2025.
    [101]
    X. Xue, Y. Zhou, G. Zhang, Z. Zhang, Y. Li, C. Zhang, Z. Yin, P. Torr, W. Ouyang, and L. Bai, “CoMAS: Co-evolving multi-agent systems via interaction rewards,” arXiv preprint arXiv: 2510.08529, 2025.
    [102]
    Y. Gao, Y. Xiong, X. Gao, K. Jia, J. Pan, Y. Bi, Y. Dai, J. Sun, H. Wang, and H. Wang, “Retrieval-augmented generation for large language models: A survey,” arXiv preprint arXiv: 2312.10997, 2023.
    [103]
    Y. Xiao, E. Sun, D. Luo, and W. Wang, “TradingAgents: Multi-agents LLM financial trading framework,” arXiv preprint arXiv: 2412.20138, 2024.
    [104]
    N. Shinn, F. Cassano, A. Gopinath, K. Narasimhan, and S. Yao, “Reflexion: Language agents with verbal reinforcement learning,” in Proc. 37th Int. Conf. Neural Information Processing Systems, New Orleans, USA, 2023, Art. no. 377.
    [105]
    Y. Hu, Y. Cai, Y. Du, X. Zhu, X. Liu, Z. Yu, Y. Hou, S. Tang, and S. Chen, “Self-evolving multi-agent collaboration networks for software development,” in Proc. 13th Int. Conf. Learning Representations, Singapore, Singapore, 2025.
    [106]
    Y. Guan, H. Liao, Z. Li, J. Hu, R. Yuan, G. Zhang, and C. Xu, “World models for autonomous driving: An initial survey,” IEEE Trans. Intell. Veh., 2024, DOI: 10.1109/TIV.2024.3398357.
    [107]
    C. Fang, Z. Hu, X. Meng, S. Tu, Z. Wang, D. Zeng, W. Ni, S. Guo, and Z. Han, “DRL-driven joint task offloading and resource allocation for energy-efficient content delivery in cloud-edge cooperation networks,” IEEE Trans. Veh. Technol., vol. 72, no. 12, pp. 16195–16207, Dec. 2023. doi: 10.1109/TVT.2023.3297362
    [108]
    Y. Wang, C. Yang, S. Lan, L. Zhu, and Y. Zhang, “End-edge-cloud collaborative computing for deep learning: A comprehensive survey,” IEEE Commun. Surv. Tutorials, vol. 26, no. 4, pp. 2647–2683, 2024. doi: 10.1109/COMST.2024.3393230
    [109]
    W. Fan, P. Chen, X. Chun, and Y. Liu, “MADRL-based model partitioning, aggregation control, and resource allocation for cloud-edge-device collaborative split federated learning,” IEEE Trans. Mobile Comput., vol. 24, no. 6, pp. 5324–5341, Jun. 2025. doi: 10.1109/TMC.2025.3530482
    [110]
    H. Jin and Y. Wu, “CE-CoLLM: Efficient and adaptive large language models through cloud-edge collaboration,” in Proc. IEEE Int. Conf. Web Services, Helsinki, Finland, 2025, pp. 316−323.
    [111]
    B. Yi, X. Hu, Y. Chen, S. Zhang, H. Yang, F. Wu, and F. Wu, “EcoAgent: An efficient device-cloud collaborative multi-agent framework for mobile automation,” in Proc. 40th AAAI Conf. Artificial Intelligence, Singapore, Singapore, 2026.
    [112]
    H. Tan, X. Hao, C. Chi, M. Lin, Y. Lyu, M. Cao, et al., “RoboOS: A hierarchical embodied framework for cross-embodiment and multi-agent collaboration,” arXiv preprint arXiv: 2505.03673, 2025.
    [113]
    C. Niu, Y. Ding, J. Lu, Z. Huang, H. Zeng, Y. Dai, X. Tu, C. Lv, F. Wu, and G. Chen, “Collaborative learning of on-device small model and cloud-based large model: Advances and future directions,” arXiv preprint arXiv: 2504.15300, 2025.
    [114]
    Y. Gan, M. Pan, R. Zhang, Z. Ling, L. Zhao, J. Liu, and S. Zhang, “Cloud-device collaborative adaptation to continual changing environments in the real-world,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Vancouver, Canada, 2023, pp. 12157−12166.
    [115]
    G. Wang, J. Liu, C. Li, Y. Zhang, J. Ma, X. Wei, et al., “Cloud-device collaborative learning for multimodal large language models,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Seattle, USA, 2024, pp. 12646−12655.
    [116]
    W. Chen, Y. Su, J. Zuo, C. Yang, C. Yuan, C.-M. Chan, et al., “AgentVerse: Facilitating multi-agent collaboration and exploring emergent behaviors,” in Proc. 12th Int. Conf. Learning Representations, Vienna, Austria, 2024.
    [117]
    C. Qian, Z. Xie, Y. Wang, W. Liu, K. Zhu, H. Xia, et al., “Scaling large language model-based multi-agent collaboration,” in Proc. 13th Int. Conf. Learning Representations, Singapore, Singapore, 2025.
    [118]
    B. Liu, X. Li, J. Zhang, J. Wang, T. He, S. Hong, et al., “Advances and challenges in foundation agents: From brain-inspired intelligence to evolutionary, collaborative, and safe systems,” arXiv preprint arXiv: 2504.01990, 2025.
    [119]
    H. Li, Y. Chong, S. Stepputtis, J. Campbell, D. Hughes, M. Lewis, and K. Sycara, “Theory of mind for multi-agent collaboration via large language models,” in Proc. Conf. Empirical Methods in Natural Language Processing, Singapore, Singapore, 2023.
    [120]
    Z. Yang, Z. Zhang, Z. Zheng, Y. Jiang, Z. Gan, Z. Wang, et al., “OASIS: Open agent social interaction simulations with one million agents,” arXiv preprint arXiv: 2411.11581, 2024.
    [121]
    G. De Marzo and D. Garcia, “Collective behavior of AI agents: The case of moltbook,” arXiv preprint arXiv: 2602.09270, 2026.
    [122]
    B. Yee and K. Sharma, “Molt dynamics: Emergent social phenomena in autonomous AI agent populations,” arXiv preprint arXiv: 2603.03555, 2026.
    [123]
    C. Bădică, A. Bădică, M. Ganzha, M. Ivanović, M. Paprzycki, D. Selişteanu, and Z. Wrona, “Contemporary agent technology: LLM-driven advancements vs classic multi-agent systems,” arXiv preprint arXiv: 2509.02515, 2025.
    [124]
    R. Patel, E. Rudnick-Cohen, S. Azarm, M. Otte, H. Xu, and J. W. Herrmann, “Decentralized task allocation in multi-agent systems using a decentralized genetic algorithm,” in Proc. IEEE Int. Conf. Robotics and Automation, Paris, France, 2020, pp. 3770−3776.
    [125]
    H. Du, S. Thudumu, R. Vasa, and K. Mouzakis, “A survey on context-aware multi-agent systems: Techniques, challenges and future directions,” arXiv preprint arXiv: 2402.01968, 2024.
    [126]
    H. Ge, Y. Jia, Z. Li, Y. Li, Z. Chen, R. Huang, and G. Zhou, “FILIC: Dual-loop force-guided imitation learning with impedance torque control for contact-rich manipulation tasks,” arXiv preprint arXiv: 2509.17053, 2025.
    [127]
    D. Zhang, G. Feng, Y. Shi, and D. Srinivasan, “Physical safety and cyber security analysis of multi-agent systems: A survey of recent advances,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 2, pp. 319–333, Feb. 2021. doi: 10.1109/JAS.2021.1003820
    [128]
    J. Wang, J. Wang, B. Athiwaratkun, C. Zhang, and J. Zou, “Mixture-of-agents enhances large language model capabilities,” arXiv preprint arXiv: 2406.04692, 2024.
    [129]
    H. Luo, G. Sun, Y. Liu, D. Zhao, D. Niyato, H. Yu, and S. Dustdar, “A weighted byzantine fault tolerance consensus driven trusted multiple large language models network,” IEEE Trans. Cogn. Commun. Netw., vol. 12, pp. 3815–3830, 2026. doi: 10.1109/TCCN.2025.3620286
    [130]
    Y. Yang, H. Chai, S. Shao, Y. Song, S. Qi, R. Rui, and W. Zhang, “AgentNet: Decentralized evolutionary coordination for LLM-based multi-agent systems,” in Proc. 39th Conf. Neural Information Processing Systems, San Diego, USA, 2025.
    [131]
    C. Sun, S. Huang, and D. Pompili, “LLM-based multi-agent reinforcement learning: Current and future directions,” arXiv preprint arXiv: 2405.11106, 2024.
    [132]
    P. Zhao, S. Suryanarayanan, and M. G. Simoes, “An energy management system for building structures using a multi-agent decision-making control methodology,” IEEE Trans. Ind. Appl., vol. 49, no. 1, pp. 322–330, Jan.-Feb. 2013. doi: 10.1109/TIA.2012.2229682
    [133]
    J. Xu, Q. Sun, Q.-L. Han, and Y. Tang, “When embodied AI meets industry 5.0: Human-centered smart manufacturing,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 3, pp. 485–501, Mar. 2025. doi: 10.1109/JAS.2025.125327
    [134]
    W. Li, J. Wu, G. Yang, B. Wang, Q. Zhang, Y. Wu, and J. Tan, “Humanoid robots: Progress, challenges, and future research directions,” Sci. China Inf. Sci., vol. 68, no. 11, Art. no. 216201, Sep. 2025. doi: 10.1007/s11432-025-4532-0
    [135]
    J. Zhang, H. Wang, Z. Jia, J. Dong, and L. Ren, “CoMA-IKG: LLM-driven multiagent framework for automated construction of industrial knowledge graph,” IEEE Trans. Ind. Inf., 2026, DOI: 10.1109/TII.2026.3660116.
    [136]
    S. Ma, J. Huang, F. Zhang, J. Wu, Y. Shen, G. Fan, Z. Zhang, and Z. Zang, “MedLA: A logic-driven multi-agent framework for complex medical reasoning with large language models,” in Proc. 40th AAAI Conf. Artificial Intelligence, Singapore, Singapore, 2026.
    [137]
    W. Xiang, L. Yu, X. Chen, and M. J. Herold, “Artificial intelligence in cancer immunotherapy: Navigating challenges and unlocking opportunities,” Engineering, vol. 44, pp. 12–16, Jan. 2025. doi: 10.1016/j.eng.2024.12.014
    [138]
    J. Li, X. Liu, and Y. Feng, “From single to societal: Analyzing persona-induced bias in multi-agent interactions,” in Proc. 40th AAAI Conf. Artificial Intelligence, Singapore, Singapore, 2026.
    [139]
    J. Zhao, N. Kuppuswamy, S. Feng, B. Burchfiel, and E. Adelson, “PolyTouch: A robust multi-modal tactile sensor for contact-rich manipulation using tactile-diffusion policies,” in Proc. IEEE Int. Conf. Robotics and Automation, Atlanta, USA, 2025, pp. 104−110.
    [140]
    J. Liu, Y. Du, K. Yang, J. Wu, Y. Wang, X. Hu, et al., “Edge-cloud collaborative computing on distributed intelligence and model optimization: A survey,” IEEE Commun. Surv. Tutorials, vol. 28, pp. 5049–5080, Mar. 2026. doi: 10.1109/COMST.2026.3669216
    [141]
    Y. Hong, H. Huang, M. Li, L. Fei-Fei, J. Wu, and Y. Choi, “Learning from trials and errors: Reflective test-time planning for embodied LLMs,” arXiv preprint arXiv: 2602.21198, 2026.
    [142]
    K. Liu, Z. Tang, D. Wang, Z. Wang, X. Li, and B. Zhao, “COHERENT: Collaboration of heterogeneous multi-robot system with large language models,” in Proc. IEEE Int. Conf. Robotics and Automation, Atlanta, USA, 2025, pp. 10208−10214.
    [143]
    M. Huang, Y. Wang, S. Cui, P. Ke, and J. Tang, “The superalignment of superhuman intelligence with large language models,” Sci. China Inf. Sci., vol. 68, no. 6, Art. no. 160107, May 2025. doi: 10.1007/s11432-024-4348-6
    [144]
    I. Gabriel, G. Keeling, A. Manzini, and J. Evans, “We need a new ethics for a world of AI agents,” Nature, vol. 644, no. 8075, pp. 38–40, Aug. 2025. doi: 10.1038/d41586-025-02454-5
    • Related Articles
    • Supplements(0)

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(7)  / Tables(1)

    Get Citation
    PDF
    XML

    Article Metrics

    Article views (239) PDF downloads(40) Cited by()

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return