Emergent Strategies in Multi-Agent Systems

Oleksik, Vlad; Mihu, Cantemir; Pitic, Antoniu

doi:10.2478/ijasitels-2025-0015

Abstract

This article aims to present an overview of the emerging protocols and strategies used for achieving scalability of performance- and efficiency-centric multi-agent systems as this field is rapidly developing and focus is shifting towards architectures employing multiple, tool-enabled models that need to both split tasks, working concurrently, and follow step-based problem-solving strategies, while maintaining effective communication throughout the system.

References

A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, I. Polosukhin, Attention is all you need, Advances in Neural Information Processing Systems, 30, Curran Associates, Inc., 2017.
Search in Google Scholar Back to article
J. Wei, X. Wang, D. Schuurmans, M. Bosma, B. Ichter, F. Xia, E. H. Chi, Q. V. Le, D. Zhou, Chain-of-thought prompting elicits reasoning in large language models, Proceedings of the 36th International Conference on Neural Information Processing Systems, pp. 24824–24837, Red Hook, New York, 2022. https://dl.acm.org/doi/10.5555/3600270.3602070
Search in Google Scholar Back to article
S. Han, Q. Zhang, Y. Yao, W. Jin, Z. Xu, C. He. LLM Multi-Agent Systems: Challenges and Open Problems, preprint, arXiv:2402.03578, 2024. https://doi.org/10.48550/arXiv.2402.03578
Search in Google Scholar Back to article
B. Yan, X. Zhang, L. Zhang, L. Zhang, Z. Zhou, D. Miao, C. Li, Beyond Self‑Talk: A Communication‑Centric Survey of LLM‑Based Multi‑Agent Systems, preprint, arXiv:2502.14321, 2025. https://doi.org/10.48550/arXiv.2502.14321
Search in Google Scholar Back to article
S. Mu, S. Lin, A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications, preprint, arXiv:2503.07137, 2025. https://doi.org/10.48550/arXiv.2503.0713
Search in Google Scholar Back to article
L. Ma, R. Zhang, Y. Han, S. Yu, Z. Wang, Z. Ning, J. Zhang, P. Xu, P. Li, W. Ju, C. Chen, D. Wang, K. Liu, P. Wang, P. Wang, Y. Fu, C. Liu, Y. Zhou, C.-T. Lu. A Comprehensive Survey on Vector Database: Storage and Retrieval Technique, Challenge, preprint, arXiv:2310.11703, 2021.
Search in Google Scholar Back to article
J. Pan, J. Wang, G. Li, Survey of Vector Database Management Systems, VLDB J., 33, pp. 1591-1615, 2023. https://doi.org/10.48550/arXiv.2310.14021
Search in Google Scholar Back to article
D. M. Wegner, Transactive memory: A contemporary analysis of the group mind, Theories of group behavior, pp. 185–205, Springer-Verlag, New York, 1986.
Search in Google Scholar Back to article
M. Catasta, A. Tonon, D. E. Difallah, G. Demartini, K. Aberer, P. Cudré‑Mauroux, TransactiveDB: Tapping into Collective Human Memories, Proc. VLDB Endow., 7 (14), pp. 1977-1980, 2014. https://www.vldb.org/pvldb/vol7/p1977-catasta.pdf
Search in Google Scholar Back to article
H. Y. Shang, X. Liu, Z. Liang, J. Zhang, H. Hu, S. Guo, United Minds or Isolated Agents? Exploring Coordination of LLMs under Cognitive Load Theory, preprint, arXiv:2506.06843v1, 2025. https://doi.org/10.48550/arXiv.2506.06843
Search in Google Scholar Back to article
R.M. Aratchige and W. M. K. S. Ilmini, LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM‑Based Multi Agent Systems, preprint, arXiv:2504.01963, 2025. https://doi.org/10.48550/arXiv.2504.01963
Search in Google Scholar Back to article
H. Sun, Y. Zhuang, L. Kong, B. Dai, C. Zhang, AdaPlanner: Adaptive Planning from Feedback with Language Models, preprint, arXiv:2305.16653, 2023. https://doi.org/10.48550/arXiv.2305.16653
Search in Google Scholar Back to article
S. Yao, J. Zhao, D. Yu, N. Du, I. Shafran, K. Narasimhan, and Y. Cao, ReAct: Synergizing Reasoning and Acting in Language Models, preprint, arXiv:2210.03629, 2022. https://doi.org/10.48550/arXiv.2210.03629
Search in Google Scholar Back to article
S. Yao, D. Yu, J. Zhao, I. Shafran, T. L. Griffiths, Y. Cao, K. Narasimhan, Tree of Thoughts: Deliberate Problem Solving with Large Language Models, preprint, arXiv:2305.10601, 2023. https://doi.org/10.48550/arXiv.2305.10601
Search in Google Scholar Back to article
L. Becchetti, A. Clementi, E. Natale, Consensus Dynamics: An Overview, ACM SIGACT News, 51 (1), pp.57, 2020. https://doi.org/10.1145/3388392.3388402
Search in Google Scholar Back to article
R. Zhang, S. Eger, Llm-based multi-agent poetry generation in non-cooperative environments, preprint, arXiv:2409.03659, 2024. https://doi.org/10.48550/arXiv.2409.03659
Search in Google Scholar Back to article
Q. Wang, T. Wang, Z. Tang, Q. Li, N. Chen, J. Liang, B. He, MegaAgent: A Large‑Scale Autonomous LLM‑Based Multi‑Agent System Without Predefined SOPs, preprint, arXiv:2408.09955, 2024. https://doi.org/10.48550/arXiv.2408.09955
Search in Google Scholar Back to article
W. Chen, Y. Su, J. Zuo, C. Yang, AgentVerse: Facilitating Multi‑Agent Collaboration and Exploring Emergent Behaviors in Agents, preprint, arXiv:2308.10848, 2023. https://doi.org/10.48550/arXiv.2308.10848
Search in Google Scholar Back to article
Z. Wang, S. Moriyama, W.-Y. Wang, B. Gangopadhyay, S. Takamatsu, Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi‑Agent Systems, preprint, arXiv:2502.11098v1, 2025. https://doi.org/10.48550/arXiv.2502.11098
Search in Google Scholar Back to article
J. Cai, J. Li, M. Zhang, M. Li, C.-S. Wang, K. Tei, Language Evolution for Evading Social Media Regulation via LLM-based Multi-agent Simulation, IEEE Congress on Evolutionary Computation (CEC), 1–10, 2024..
Search in Google Scholar Back to article

Emergent Strategies in Multi-Agent Systems

Abstract

Paradigm

My account