Centralized Orchestration for High-Frequency Agent-to-Agent Negotiations: The Puppeteer Pattern
DOI:
https://doi.org/10.5281/zenodo.20763208Keywords:
Agentic AI, Multi-Agent Systems, Centralized Control, High-Frequency Negotiation, CybersecurityAbstract
As AI agents become more common in complex systems, coordinating how they negotiate with each other in fast-moving environments has become a real challenge. The older, decentralized approaches — where each agent largely fends for itself — tend to fall apart at scale. They're slow, they often produce outcomes that are good for one agent but bad for the overall system, and they can't keep up when conditions are changing rapidly and every millisecond counts. This paper presents the Puppeteer Pattern, a new architecture that puts a central coordinator in charge of guiding negotiation strategies across a mix of different AI agents. That central controller uses machine learning to update strategies on the fly, manage shared resources, and keep the system secure all in real time. The results from testing are encouraging. The system achieved a negotiation success rate of 92.3%, delivered nearly 29% better outcomes for the group as a whole compared to fully decentralized setups, and responded in an average of 150 milliseconds compared to 920 milliseconds without central coordination. That's roughly six times faster. The paper does not only talk about the good results. It also honestly explains what you actually need to make this system work in the real world, things like the right technology setup, how to keep it safe from threats, whether it works with different kinds of AI agents, and what its weaknesses are so that developers can be prepared.
References
Adabara, I., Sadiq, B. O., Shuaibu, A. N., Danjuma, Y. I., & Maninti, V. (2025). Trustworthy agentic AI systems: A cross-layer review. F1000Research, 14, 905.
An, B. (2022). Automated negotiation for complex multi-agent resource allocation (Doctoral dissertation, University of Massachusetts Amherst).
Bagga, P., Paoletti, N., & Stathis, K. (2020). Learnable strategies for bilateral agent negotiation over multiple issues. arXiv Preprint. https://arxiv.org/abs/2009.08302
Bastos, J., Azevedo, A., Ávila, P., Mota, A., Costa, L., & Castro, H. (2023). Collaborative planning in non-hierarchical networks. Applied Sciences, 13(14), 8347. https://doi.org/10.3390/app13148347
Day, D., et al. (2017). Improving throughput and latency of D-Bus. In Proceedings of the International Conference on Accelerator and Large Experimental Physics Control Systems (ICALEPCS) (pp. 809–812).
Faratin, P., Sierra, C., & Jennings, N. R. (1998). Negotiation decision functions for autonomous agents. Robotics and Autonomous Systems, 24(3–4), 159–182. https://doi.org/10.1016/S0921-8890(98)00029-3
Fatima, S., Kraus, S., & Wooldridge, M. (2014). Principles of automated negotiation (1st ed.). Cambridge University Press.
Hasan, M., Saifullah, M. K., Kamal, M. A. S., & Yamada, K. (2024). Distributed broadcast control of multi-agent systems using hierarchical coordination. Biomimetics, 9(7), 407. https://doi.org/10.3390/biomimetics9070407
Huang, Z., et al. (2025). Adaptive orchestration for high-frequency multi-agent negotiations. Autonomous Agents and Multi-Agent Systems, 39(1), 112–138.
Jelasity, M., Montresor, A., & Babaoglu, O. (2005). Gossip-based aggregation in large dynamic networks. ACM Transactions on Computer Systems, 23(3), 219–252. https://doi.org/10.1145/1082469.1082470
Jennings, N. R., Parsons, S., Noriega, P., & Sierra, C. (2001). Automated negotiation: Prospects, methods and challenges. Group Decision and Negotiation, 10(2), 199–215. https://doi.org/10.1023/A:1008746126376
Khan, K., Ahmed, S., Rahman, T., Ali, M., & Hussain, F. (2025). A multiagent framework coordinating one-to-many concurrent composite negotiations. IEEE Open Journal of Industry Applications, 6, 717–727.
Krawczyk, H., Bellare, M., & Canetti, R. (1997). HMAC: Keyed-hashing for message authentication (RFC 2104). Internet Engineering Task Force. https://doi.org/10.17487/RFC2104
Liu, F. T., Ting, K. M., & Zhou, Z.-H. (2008). Isolation forest. In Proceedings of the IEEE International Conference on Data Mining (ICDM) (pp. 413–422). https://doi.org/10.1109/ICDM.2008.17
Liu, T., Wang, J., & Cheng, D. (2019). Game theoretic control of multiagent systems. SIAM Journal on Control and Optimization, 57(3), 1691–1709. https://doi.org/10.1137/17M1137931
Moore, D. (2025). A taxonomy of hierarchical multi-agent systems. arXiv Preprint. https://arxiv.org/abs/2508.12683
Nisan, N., Roughgarden, T., Tardos, É., & Vazirani, V. V. (Eds.). (2007). Algorithmic game theory. Cambridge University Press.
Ongaro, D., & Ousterhout, J. (2014). In search of an understandable consensus algorithm. In Proceedings of the USENIX Annual Technical Conference (USENIX ATC) (pp. 305–319).
Pinto, T., Fotouhi Ghazvini, M. A., Soares, J., Faia, R., Corchado, J. M., Castro, R., & Vale, Z. (2018). Decision support for negotiations among microgrids. Energies, 11(10), 2526. https://doi.org/10.3390/en11102526
Ravindrakumar. (2023). AI-driven threat detection in distributed cloud systems. ShodhKosh Journal, 4(2). https://shodhkosh.com/
Renting, B. M., Hoos, H. H., & Jonker, C. M. (2020). Automated configuration of negotiation strategies. In Proceedings of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS) (pp. 1116–1124).
Rose, S., Borchert, O., Mitchell, S., & Connelly, S. (2020). Zero trust architecture (NIST Special Publication 800-207). National Institute of Standards and Technology. https://doi.org/10.6028/NIST.SP.800-207
Rubinstein, A. (1982). Perfect equilibrium in a bargaining model. Econometrica, 50(1), 97–109. https://doi.org/10.2307/1912531
Rustogi, S. K. (1999). Empirical studies of coordination in decentralized multiagent systems (Doctoral dissertation, University of Massachusetts Amherst).
Salama, R., & Al-Turjman, F. (2025). Addressing cybersecurity vulnerabilities with cloud security. NEU Journal for Artificial Intelligence and Internet of Things, 4, 86–95.
Sim, K. M. (2004). Negotiation agents that make prudent compromises. Computational Intelligence, 20(4), 643–662. https://doi.org/10.1111/j.0824-7935.2004.00265.x
Sim, K. M., Guo, H., Shi, B., & Sun, L. (2008). Negotiation and scheduling mechanisms for multi-agent systems. Multiagent and Grid Systems, 4(1), 1–3.
Stephen, S. (2026). Federated learning architectures for distributed multi-agent systems. arXiv Preprint. https://arxiv.org/
Suggu, S. K. (2025). Agentic AI workflows in cybersecurity. Journal of Information Systems Engineering and Management, 10(52s), 612–624.
Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction (2nd ed.). MIT Press.
Tupsamudre, H., Kumar, A., Agarwal, V., Gupta, N., & Mondal, S. (2022). AI-assisted controls change management for cloud cybersecurity. In Proceedings of the AAAI Conference on Artificial Intelligence (pp. 12629–12635). https://doi.org/10.1609/aaai.v36i11.21510
Tykhonov, D. (2010). Designing generic and efficient negotiation strategies. Data Archiving and Networked Services (DANS).
Wooldridge, M. (2009). An introduction to multiagent systems (2nd ed.). Wiley.
Xu, X., & Zhao, Q. (2020). Distributed no-regret learning in multiagent systems. IEEE Signal Processing Magazine, 37(3), 84–91. https://doi.org/10.1109/MSP.2020.2970358
Xu, Y., Wang, L., Chen, X., & Zhao, Q. (2017). Cost-efficient negotiation over multiple resources with reinforcement learning. In Proceedings of IEEE International Workshop on Quality of Service (IWQoS). https://doi.org/10.1109/IWQoS.2017.7969152
Yamanaka, H., et al. (2022). Design and implementation of an edge computing testbed. IEICE Transactions on Information and Systems, E105.D(9), 1516–1528. https://doi.org/10.1587/transinf.2021EDP7208
Yang, J., Li, H., Zhang, W., Chen, Y., & Zhao, P. (2025). Ablation analysis of centralized AI-driven negotiation systems. IEEE Transactions on Autonomous Systems, 12(3), 204–219.
Ygge, F., & Akkermans, H. (1999). Decentralized markets versus central control: A comparative study. Journal of Artificial Intelligence Research, 11, 301–333. https://doi.org/10.1613/jair.630
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Research on Multidisciplinary Studies
This work is licensed under a Creative Commons Attribution 4.0 International License.
