Multi-Agent Decision Framework: A Systematic Approach to Agent Architecture Selection |
||
![]() |
![]() |
|
© 2025 by IJCTT Journal | ||
Volume-73 Issue-5 |
||
Year of Publication : 2025 | ||
Authors : Jay Prakash Thakur, Ananya Ghosh Chowdhury | ||
DOI : 10.14445/22312803/IJCTT-V73I5P105 |
How to Cite?
Jay Prakash Thakur, Ananya Ghosh Chowdhury, "Multi-Agent Decision Framework: A Systematic Approach to Agent Architecture Selection," International Journal of Computer Trends and Technology, vol. 73, no. 5, pp. 27-40, 2025. Crossref, https://doi.org/10.14445/22312803/IJCTT-V73I5P105
Abstract
Artificial intelligence system architects must choose between single-agent and multi-agent architectural patterns because this selection impacts performance, resource allocation, and operational efficiency. Despite the widespread adoption of agent-based systems across different domains, no standardized framework would help guide the essential architectural choice between single-agent and multi-agent systems. This paper presents a robust, quantitative decision framework that measures and organizes the evaluation between single-agent and multi-agent architectures. The research introduces noble evaluation tools and assessment procedures that examine task features, resource limitations, performance benchmarks and domain requirements. The proposed framework demonstrates its effectiveness through case studies in multiple application domains to guide optimal agent architecture selection. The research offers practitioners and researchers a systematic approach to choose the optimal architecture to enhance system performance for specific use cases while maximizing resource utilization.
Keywords
Multi-agent systems, Artificial intelligence, Decision framework, System architecture, Agent coordination, Task decomposition.
Reference
[1] Stuart Jonathan Russell, and Peter Norvig, Artificial Intelligence: A Modern Approach, Pearson, pp. 1-1091, 2014.
[Google Scholar] [Publisher Link]
[2] Michael Wooldridge, An Introduction to MultiAgent Systems, John Wiley & Sons, pp. 1-461, 2009.
[Google Scholar] [Publisher Link]
[3] Nicholas R. Jennings, Katia Sycara, and Michael Wooldridge, “A Roadmap of Agent Research and Development,” Autonomous Agents and Multi-Agent Systems, vol. 1, pp. 7-38, 1998.
[CrossRef] [Google Scholar] [Publisher Link]
[4] V.R. Lesser, “Cooperative Multiagent Systems: A Personal View of the State of the Art,” IEEE Transactions on Knowledge and Data Engineering, vol. 11, no. 1, pp. 133-142l, 1999.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Tim Finin et al., “KQML as an Agent Communication Language,” Proceedings of the Third International Conference on Information and Knowledge Management, Gaithersburg Maryland USA, pp. 456-463, 1994.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Onn Shehory, and Sarit Kraus, “Methods for Task Allocation via Agent Coalition Formation,” Artificial Intelligence, vol. 101, no. 1-2, pp. 165-200, 1998.
[CrossRef] [Google Scholar] [Publisher Link]
[7] D.R. Wilson, and T.R. Martinez, “Improved Heterogeneous Distance Functions,” Journal of Artificial Intelligence Research, vol. 6, pp. 1-34, 1997.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Peter Stone, and Manuela Veloso, “Multiagent Systems: A Survey from a Machine Learning Perspective,” Autonomous Robots, vol. 8, pp. 345-383, 2000.
[CrossRef] [Google Scholar] [Publisher Link]
[9] N. Schurr et al., The Defacto System: Coordinating Human-Agent Teams for the Future of Disaster Response, Multi-Agent Programming, pp. 197-215, 2005.
[CrossRef] [Google Scholar] [Publisher Link]
[10] M. Klusch, and A. Gerber, “Dynamic Coalition Formation among Rational Agents,” IEEE Intelligent Systems, vol. 17, no. 3, pp. 42-47, 2002.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Katia P. Sycara, “Multiagent Systems,” AI Magazine, vol. 19, no. 2, pp. 79-92, 1998. [CrossRef] [Google Scholar] [Publisher Link]
[12] Victor R. Lesser, “Evolution of the GPGP/TÆMS Domain-Independent Coordination Framework,” Autonomous Agents and Multi-Agent Systems, no. 1, pp. 1-2, 2002.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Lars Kotthoff, Algorithm Selection for Combinatorial Search Problems: A Survey, Data Mining and Constraint Programming, pp. 149-190, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Saleema Amershi et al., “Software Engineering for Machine Learning: A Case Study,” 2019 IEEE/ACM 41st International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP), Montreal, QC, Canada, pp. 291-300, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[15] D. Sculley et al., “Hidden Technical Debt in Machine Learning Systems,” Proceedings of the 29th International Conference on Neural Information Processing Systems, vol. 2, pp. 2503-2511, 2015.
[Google Scholar] [Publisher Link]
[16] José Hernández-Orallo, The Measure of All Minds: Evaluating Natural and Artificial Intelligence, Cambridge University Press, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Hiroaki Kitano et al., “RoboCup: The Robot World Cup Initiative,” Proceedings of the First International Conference on Autonomous Agents, pp. 340-347, 1997.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Michael P. Wellman, Introduction. In: Trading Agents, Synthesis Lectures on Artificial Intelligence and Machine Learning, pp. 1-7, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Edmund H. Durfee, and Victor R. Lesser “Negotiating Task Decomposition and Allocation using Partial Global Planning,” Distributed Artificial Intelligence, pp. 229-243, 1989.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Michael Wooldridge, and Nicholas R. Jennings, “Intelligent Agents: Theory and Practice,” The Knowledge Engineering Review, vol. 10, no. 2, pp. 115-152, 1995.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Katia Sycara, K. Decker, and M. Williamson, “Middle-Agents for the Internet,” Proceedings of the 15th International Joint Conference on Artificial Intelligence pp. 578-583, 1997.
[Google Scholar] [Publisher Link]
[22] Weiming Shen, Douglas H. Norrie, and J-P. Barthes, Multi-Agent Systems for Concurrent Intelligent Design and Manufacturing, CRC Press, pp. 1-416, 2019.
[Google Scholar] [Publisher Link]
[23] Shaikh Shoaib, and R.C. Mahajan, “Authenticating using Secret Key in Digital Video Watermarking using 3-Level DWT,” 2015 International Conference on Communication, Information & Computing Technology (ICCICT), Mumbai, India, pp. 1-5, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Liang Tong, Yong Li, and Wei Gao, “A Hierarchical Edge Cloud Architecture for Mobile Computing,” IEEE INFOCOM 2016 - The 35th Annual IEEE International Conference on Computer Communications, San Francisco, CA, USA, pp. 1-9, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Yoav Shoham, and Kevin Leyton-Brown, Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations, Cambridge University Press, pp. 1-483, 2009.
[Google Scholar] [Publisher Link]
[26] Sarit Kraus, and Jonathan Wilkenfeld, “Strategic Negotiation in Multiagent Environments, Psychology Press, pp. 1-32, 2001.
[Google Scholar] [Publisher Link]