Multi-Agent Generative AI: Coordinated Synthesis for Complex Problem-Solving
DOI:
https://doi.org/10.32628/CSEIT24113371Keywords:
Multi-agent systems, generative AI, distributed reasoning, consensus mechanisms, orchestration protocols, cross-domain synthesisAbstract
Single generative models struggle to handle tasks requiring diverse reasoning and multi-domain knowledge. This study presents a multi-agent generative AI architecture where specialized models collaborate via a negotiation and task allocation protocol. Agents can generate partial outputs, critique peers, and synthesize final results using consensus-based scoring. The paper introduces a generative agent orchestration framework using LangGraph and Apache Kafka, enabling distributed reasoning across domains such as legal analysis, software engineering, and biomedical research. Experiments demonstrate improved factual consistency, reduced hallucinations, and enhanced output diversity compared to monolithic models. The framework achieves a 34% reduction in factual errors and 42% improvement in task completion rates across complex multi-domain problems. The research presents three novel contributions: a novel orchestration protocol for multi-agent generative collaboration, consensus-driven synthesis mechanisms to reduce factual errors, and real-time distributed generation pipelines across heterogeneous model types. Comprehensive evaluation across diverse problem domains validates the effectiveness of coordinated multi-agent approaches for complex reasoning tasks requiring specialized domain expertise and cross-disciplinary integration.
📊 Article Downloads
References
Bernstein, A., & Klein, M. "Coordination in Multi-Agent Systems: A Survey." ACM Computing Surveys, vol. 45, no. 3, pp. 1-45, 2023.
Chen, L., Wang, K., & Liu, H. "Large Language Models in Multi-Agent Scenarios: Coordination and Collaboration." Proceedings of the International Conference on Machine Learning, pp. 2341-2358, 2024.
Davis, R., & Smith, R. G. "Negotiation as a Metaphor for Distributed Problem Solving." Artificial Intelligence, vol. 20, no. 1, pp. 63-109, 2023. DOI: https://doi.org/10.1016/0004-3702(83)90015-2
Foster, J. A., & Martinez, S. "Consensus Mechanisms in Distributed AI Systems." IEEE Transactions on Systems, Man, and Cybernetics, vol. 53, no. 8, pp. 4892-4906, 2023.
Garcia, M., Thompson, D., & Lee, Y. "Orchestration Frameworks for Complex AI Workflows." Journal of Artificial Intelligence Research, vol. 76, pp. 123-156, 2024.
Harrison, P., & Anderson, K. "Multi-Agent Reinforcement Learning for Collaborative Problem Solving." Neural Information Processing Systems, vol. 36, pp. 12456-12470, 2023.
Johnson, B., Rodriguez, C., & Kim, J. "Distributed Generation and Synthesis in Large Language Model Networks." Nature Machine Intelligence, vol. 6, no. 4, pp. 234-248, 2024.
Pendyala. S, “Cloud-Driven Data Engineering: Multi-Layered Architecture for Semantic Interoperability in Healthcare” Journal of Business Intelligence and Data Analytics., 2023, vol. 1, no. 1, pp. 1–14. doi: https://10.55124/jbid.v1i1.244
Chandra Sekhar Oleti. (2022). Serverless Intelligence: Securing J2ee-Based Federated Learning Pipelines on AWS. International Journal of Computer Engineering and Technology (IJCET), 13(3), 163-180. DOI: https://doi.org/10.34218/IJCET_13_03_017
Praveen Kumar Reddy Gujjala. (2022). Enhancing Healthcare Interoperability Through Artificial Intelligence and Machine Learning: A Predictive Analytics Framework for Unified Patient Care. International Journal of Computer Engineering and Technology (IJCET), 13(3), 181-192. https://iaeme.com/Home/issue/IJCET?Volume=13&Issue=3 DOI: https://doi.org/10.34218/IJCET_13_03_018
Sandeep Kamadi. (2022). AI-Powered Rate Engines: Modernizing Financial Forecasting Using Microservices and Predictive Analytics. International Journal of Computer Engineering and Technology (IJCET), 13(2), 220-233. DOI: https://doi.org/10.34218/IJCET_13_02_024
Sandeep Kamadi. (2022). Proactive Cybersecurity for Enterprise Apis: Leveraging AI-Driven Intrusion Detection Systems in Distributed Java Environments. International Journal of Research in Computer Applications and Information Technology (IJRCAIT), 5(1), 34-52. DOI: https://doi.org/10.34218/IJRCAIT_05_01_004
Sushil Prabhu Prabhakaran, Satyanarayana Murthy Polisetty, Santhosh Kumar Pendyala. Building a Unified and Scalable Data Ecosystem: AI-Driven Solution Architecture for Cloud Data Analytics. International Journal of Computer Engineering and Technology (IJCET), 13(3), 2022, pp. 137-153. DOI: https://doi.org/10.34218/IJCET_13_03_015
Santhosh Kumar Pendyala, Satyanarayana Murthy Polisetty, Sushil Prabhu Prabhakaran. Advancing Healthcare Interoperability Through Cloud-Based Data Analytics: Implementing FHIR Solutions on AWS. International Journal of Research in Computer Applications and Information Technology (IJRCAIT), 5(1),2022, pp. 13-20. DOI: https://doi.org/10.34218/IJRCAIT_05_01_002
Chandra Sekhar Oleti. (2023). Enterprise AI at Scale: Architecting Secure Microservices with Spring Boot and AWS. International Journal of Research in Computer Applications and Information Technology (IJRCAIT), 6(1), 133–154. DOI: https://doi.org/10.34218/IJRCAIT_06_01_011
Chandra Sekhar Oleti. (2024). AI-Driven Security Intelligence: Transforming Java Enterprise Observability into Proactive Cyber Threat Detection. International Journal of Computer Engineering and Technology (IJCET), 15(1), 144- 162. DOI: https://doi.org/10.34218/IJCET_15_01_015
Chen, S., Liu, Y., Han, W., Zhang, W., & Liu, T. (2023). A Survey on Multi-Generative Agent System: Recent Advances and New Frontiers. arXiv preprint arXiv:2412.17481.
Shinn, E., et al. (2023). Generative Agents: Interactive Simulacra of Human Behavior. arXiv preprint arXiv:2304.03442.
Xu, J., et al. (2023). Multi-Agent Reinforcement Learning for Multi-Generative Agent Systems. Proceedings of AAAI 2023.
Park, S., et al. (2023). Memory-augmented Generative Agents for Long Trajectory Decision-making. NeurIPS 2023.
Yao, S., et al. (2023). Planning with Generative Agents: A Multi-Agent AI Approach. ICML 2023.
Liu, Z., et al. (2022). Multi-Agent Collaboration for Complex Document Generation. ACL 2022.
Guo, Q., et al. (2022). Coordination Mechanisms in Multi-Agent Systems for Complex Reasoning. IEEE Transactions on Neural Networks and Learning Systems, 33(12). DOI: https://doi.org/10.1109/TNNLS.2022.3227739
Li, X., et al. (2021). Integrating Specialized Agents with Cooperative Protocols for Complex AI Tasks. AAAI 2021.
Zhang, M., & Wang, J. (2020). Distributed Multi-Agent Reasoning Using Consensus-driven Synthesis. Journal of Artificial Intelligence Research, 69.
Huang, C., et al. (2020). Agent Orchestration in Multi-Agent AI Systems with Real-Time Coordination. IJCAI 2020.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 International Journal of Scientific Research in Computer Science, Engineering and Information Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
