LLM-Powered Conversational Multi-Agent Cognitive System for Collaborative Task Solving
Resumo
Multi-agent system architectures powered by Large Language Models (LLMs) present a promising solution for tackling complex problems through autonomous collaboration. However, key challenges persist, including the need for seamless communication and coordination among agents, computational efficiency, behavioral consistency, and effective memory management. This study proposes a novel multi-agent system architecture in which an orchestrator agent dynamically distributes tasks among specialized LLM-powered agents. Our approach enables efficient task execution and intelligent decision support. We present a case application via an early implementation of our solution to identify factors influencing system effectiveness in terms of the agents’ memory results.
Referências
Aeronautiques, C., Howe, A., Knoblock, C., McDermott, I. D., Ram, A., Veloso, M., Weld, D., Sri, D. W., Barrett, A., Christianson, D., et al. (1998). Pddl— the planning domain definition language. Technical Report, Tech. Rep.
Becker, J. (2024). Multi-Agent Large Language Models for Conversational Task-Solving. arXiv preprint arXiv:2410.22932, (arXiv:2410.22932).
Cardoso, R. C., Ferrando, A., and Papacchini, F. (2021). Automated Planning and BDI Agents: A Case Study. In Workshop-Escola de Sistemas de Agentes, Seus Ambientes e Aplicações (WESAAC), pages 131–142. SBC.
da Costa, F. J., Avila, C. V. S., Rolim, T. V., de Castro Andrade, R. M., and Vidal, V. M. P. (2022). Dikw4iot: Uma abordagem baseada na hierarquia dikw para a construção de grafos de conhecimento para integração de dados de iot. In Simpósio Brasileiro de Banco de Dados (SBBD), pages 190–202. SBC.
de Souza Soares, E. F., Souza, R., Thiago, R. M., Machado, M. d. O. C., and Azevedo, L. G. (2021). A recommender for choosing data systems based on application profiling and benchmarking. In Simpósio Brasileiro de Banco de Dados (SBBD), pages 265–270. SBC.
Ehrlinger, L. and Wöß, W. (2016). Towards a definition of knowledge graphs. SEMANTiCS (Posters, Demos, SuCCESS), 48(1-4):2.
Georgeff, M., Pell, B., Pollack, M., Tambe, M., and Wooldridge, M. (1999). The belief-desire-intention model of agency. In Intelligent Agents V: Agents Theories, Architectures, and Languages: 5th International Workshop, ATAL’98 Paris, France, July 4–7, 1998 Proceedings 5, pages 1–10. Springer.
Huang, X., Liu, W., Chen, X., Wang, X., Wang, H., Lian, D., Wang, Y., Tang, R., and Chen, E. (2024). Understanding the planning of LLM agents: A survey. arXiv preprint arXiv:2402.02716.
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-t., Rocktäschel, T., Riedel, S., and Kiela, D. (2021). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. arXiv preprint arXiv:2005.11401, (arXiv:2005.11401).
Pan, S., Luo, L., Wang, Y., Chen, C., Wang, J., and Wu, X. (2024). Unifying Large Language Models and Knowledge Graphs: A Roadmap. IEEE Transactions on Knowledge and Data Engineering, 36(7):3580–3599.
Qian, C., Liu, W., Liu, H., Chen, N., Dang, Y., Li, J., Yang, C., Chen, W., Su, Y., Cong, X., et al. (2024). Chatdev: Communicative agents for software development. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15174–15186.
Sumers, T., Yao, S., Narasimhan, K., and Griffiths, T. (2024). Cognitive architectures for language agents. Transactions on Machine Learning Research. Survey Certification.
Tavares, C. J. and Ralha, C. G. (2024). Multi-agent System Architectural Aspects for Continuous Replanning. In Workshop-Escola de Sistemas de Agentes, Seus Ambientes e Aplicações (WESAAC), pages 39–50. SBC.
Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., et al. (2024a). A survey on large language model based autonomous agents. Frontiers of Computer Science, 18(6):186345.
Wang, Y., Pan, Y., Zhao, Q., Deng, Y., Su, Z., Du, L., and Luan, T. H. (2024b). Large Model Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends. arXiv preprint arXiv:2409.14457.
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., Chi, E., Le, Q. V., Zhou, D., et al. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824–24837.
Yin, Z., Sun, Q., Chang, C., Guo, Q., Dai, J., Huang, X., and Qiu, X. (2023). Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 15135–15153, Singapore. Association for Computational Linguistics.
Zhang, H., Du, W., Shan, J., Zhou, Q., Du, Y., Tenenbaum, J. B., Shu, T., and Gan, C. (2023). Building cooperative embodied agents modularly with large language models. arXiv preprint arXiv:2307.02485.
Zhuo, T. Y., Vu, M. C., Chim, J., Hu, H., Yu, W., Widyasari, R., Yusuf, I. N. B., Zhan, H., He, J., Paul, I., et al. (2024). Bigcodebench: Benchmarking code generation with diverse function calls and complex instructions. arXiv preprint arXiv:2406.15877.
Becker, J. (2024). Multi-Agent Large Language Models for Conversational Task-Solving. arXiv preprint arXiv:2410.22932, (arXiv:2410.22932).
Cardoso, R. C., Ferrando, A., and Papacchini, F. (2021). Automated Planning and BDI Agents: A Case Study. In Workshop-Escola de Sistemas de Agentes, Seus Ambientes e Aplicações (WESAAC), pages 131–142. SBC.
da Costa, F. J., Avila, C. V. S., Rolim, T. V., de Castro Andrade, R. M., and Vidal, V. M. P. (2022). Dikw4iot: Uma abordagem baseada na hierarquia dikw para a construção de grafos de conhecimento para integração de dados de iot. In Simpósio Brasileiro de Banco de Dados (SBBD), pages 190–202. SBC.
de Souza Soares, E. F., Souza, R., Thiago, R. M., Machado, M. d. O. C., and Azevedo, L. G. (2021). A recommender for choosing data systems based on application profiling and benchmarking. In Simpósio Brasileiro de Banco de Dados (SBBD), pages 265–270. SBC.
Ehrlinger, L. and Wöß, W. (2016). Towards a definition of knowledge graphs. SEMANTiCS (Posters, Demos, SuCCESS), 48(1-4):2.
Georgeff, M., Pell, B., Pollack, M., Tambe, M., and Wooldridge, M. (1999). The belief-desire-intention model of agency. In Intelligent Agents V: Agents Theories, Architectures, and Languages: 5th International Workshop, ATAL’98 Paris, France, July 4–7, 1998 Proceedings 5, pages 1–10. Springer.
Huang, X., Liu, W., Chen, X., Wang, X., Wang, H., Lian, D., Wang, Y., Tang, R., and Chen, E. (2024). Understanding the planning of LLM agents: A survey. arXiv preprint arXiv:2402.02716.
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-t., Rocktäschel, T., Riedel, S., and Kiela, D. (2021). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. arXiv preprint arXiv:2005.11401, (arXiv:2005.11401).
Pan, S., Luo, L., Wang, Y., Chen, C., Wang, J., and Wu, X. (2024). Unifying Large Language Models and Knowledge Graphs: A Roadmap. IEEE Transactions on Knowledge and Data Engineering, 36(7):3580–3599.
Qian, C., Liu, W., Liu, H., Chen, N., Dang, Y., Li, J., Yang, C., Chen, W., Su, Y., Cong, X., et al. (2024). Chatdev: Communicative agents for software development. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15174–15186.
Sumers, T., Yao, S., Narasimhan, K., and Griffiths, T. (2024). Cognitive architectures for language agents. Transactions on Machine Learning Research. Survey Certification.
Tavares, C. J. and Ralha, C. G. (2024). Multi-agent System Architectural Aspects for Continuous Replanning. In Workshop-Escola de Sistemas de Agentes, Seus Ambientes e Aplicações (WESAAC), pages 39–50. SBC.
Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., et al. (2024a). A survey on large language model based autonomous agents. Frontiers of Computer Science, 18(6):186345.
Wang, Y., Pan, Y., Zhao, Q., Deng, Y., Su, Z., Du, L., and Luan, T. H. (2024b). Large Model Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends. arXiv preprint arXiv:2409.14457.
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., Chi, E., Le, Q. V., Zhou, D., et al. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824–24837.
Yin, Z., Sun, Q., Chang, C., Guo, Q., Dai, J., Huang, X., and Qiu, X. (2023). Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 15135–15153, Singapore. Association for Computational Linguistics.
Zhang, H., Du, W., Shan, J., Zhou, Q., Du, Y., Tenenbaum, J. B., Shu, T., and Gan, C. (2023). Building cooperative embodied agents modularly with large language models. arXiv preprint arXiv:2307.02485.
Zhuo, T. Y., Vu, M. C., Chim, J., Hu, H., Yu, W., Widyasari, R., Yusuf, I. N. B., Zhan, H., He, J., Paul, I., et al. (2024). Bigcodebench: Benchmarking code generation with diverse function calls and complex instructions. arXiv preprint arXiv:2406.15877.
Publicado
29/09/2025
Como Citar
SILVA, Eryck; SANTOS, Frances A.; THOMPSON, Pedro; REIS, Julio C. dos.
LLM-Powered Conversational Multi-Agent Cognitive System for Collaborative Task Solving. In: WORKSHOP-ESCOLA DE SISTEMAS DE AGENTES, SEUS AMBIENTES E APLICAÇÕES (WESAAC), 19. , 2025, Fortaleza/CE.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 59-70.
ISSN 2326-5434.
DOI: https://doi.org/10.5753/wesaac.2025.37528.
