RAG Multiagente para Recuperação de Conhecimento Organizacional
Resumo
This paper proposes a multi-agent system based on Retrieval Augmented Generation (RAG) to support knowledge management in corporate environments. The solution combines semantic document retrieval with response generation using large language models (LLMs), enabling fast and contextualized access to organizational information. By employing domain specialized agents and an intelligent orchestration architecture, the system provides accurate responses tailored to different decision-making levels. This approach aims to overcome challenges posed by the fragmentation and volume of institutional documents, promoting scalability, modularity, and efficiency in internal knowledge retrieval.
Referências
Davenport, T. H. and Prusak, L. (2002). Conhecimento empresarial: como as organizações gerenciam o seu capital intelectual. Campus, Rio de Janeiro, 6 edition.
Hong, S., Zhuge, M., Chen, J., Zheng, X., Cheng, Y., Zhang, C., Wang, J., Wang, Z., Yau, S. K. S., Lin, Z., Zhou, L., Ran, C., Xiao, L., Wu, C., and Schmidhuber, J. (2024). Metagpt: Meta programming for a multi-agent collaborative framework.
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-t., Rocktäschel, T., et al. (2020). Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems, 33:9459–9474.
Li, H., Su, Y., Cai, D., Wang, Y., and Liu, L. (2022). A survey on retrieval-augmented text generation.
Qian, C., Liu, W., Liu, H., Chen, N., Dang, Y., Li, J., Yang, C., Chen, W., Su, Y., Cong, X., Xu, J., Li, D., Liu, Z., and Sun, M. (2024). ChatDev: Communicative agents for software development. In Ku, L.-W., Martins, A., and Srikumar, V., editors, Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15174–15186, Bangkok, Thailand. Association for Computational Linguistics.
Wooldridge, M. (2009). An Introduction to MultiAgent Systems. Wiley.
Yao, Y., Zeng, Y., Zhong, N., and Huang, X. (2007). Knowledge retrieval (kr). In IEEE/WIC/ACM International Conference on Web Intelligence (WI’07), pages 729–735. IEEE.
Hong, S., Zhuge, M., Chen, J., Zheng, X., Cheng, Y., Zhang, C., Wang, J., Wang, Z., Yau, S. K. S., Lin, Z., Zhou, L., Ran, C., Xiao, L., Wu, C., and Schmidhuber, J. (2024). Metagpt: Meta programming for a multi-agent collaborative framework.
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-t., Rocktäschel, T., et al. (2020). Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems, 33:9459–9474.
Li, H., Su, Y., Cai, D., Wang, Y., and Liu, L. (2022). A survey on retrieval-augmented text generation.
Qian, C., Liu, W., Liu, H., Chen, N., Dang, Y., Li, J., Yang, C., Chen, W., Su, Y., Cong, X., Xu, J., Li, D., Liu, Z., and Sun, M. (2024). ChatDev: Communicative agents for software development. In Ku, L.-W., Martins, A., and Srikumar, V., editors, Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15174–15186, Bangkok, Thailand. Association for Computational Linguistics.
Wooldridge, M. (2009). An Introduction to MultiAgent Systems. Wiley.
Yao, Y., Zeng, Y., Zhong, N., and Huang, X. (2007). Knowledge retrieval (kr). In IEEE/WIC/ACM International Conference on Web Intelligence (WI’07), pages 729–735. IEEE.
Publicado
29/09/2025
Como Citar
MORETTI, Guilherme L.; SOUSA, Kalmax dos S.; MENDES, Matheus dos S.; OLIVEIRA, Marcos A. de.
RAG Multiagente para Recuperação de Conhecimento Organizacional. 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. 87-92.
ISSN 2326-5434.
DOI: https://doi.org/10.5753/wesaac.2025.37548.
