K-alibra Agent: A Strategy for K-Client Selection in Autonomous Federated Learning

• Rafael O. Jarczewski UNICAMP https://orcid.org/0000-0002-2062-8976
• Eduardo Cerqueira UFPA https://orcid.org/0000-0001-8944-7922
• Antonio A. F. Loureiro UFMG https://orcid.org/0000-0002-5250-1785
• Leandro A. Villas UNICAMP https://orcid.org/0000-0002-3372-3366
• Allan M. de Souza UNICAMP https://orcid.org/0000-0002-5518-8392

DOI: https://doi.org/10.5753/sbrc.2026.19789

Abstract

Federated Learning (FL) has established itself as a robust approach for distributed model training while preserving data privacy. However, FL still suffers from scalability and network overhead issues. One mitigation strategy could be through dynamic client selection; however, most work focuses qualitatively on which clients to select and does not consider the number of clients selected. This rigidity prevents the system from adequately adapting to the temporal dynamics of the distributed system, resulting in high client numbers or inefficiently low client numbers. This flaw is caused by the difficulty of static algorithms in dynamically adapting to the system’s needs. To mitigate this rigidity, we present K-Agent, a Language Models (LM)-based orchestrator that dynamically adjusts the number of clients via a cycle of perception, reasoning, and action. Experiments demonstrate that the agent balances costs and stability, reducing data traffic by 44.4% to 59% compared to the literature, validating the effectiveness of agents in hyperparameter optimization in FL.

References

Acharya, D. B., Kuppan, K., and Divya, B. (2025). Agentic ai: Autonomous intelligence for complex goals—a comprehensive survey. IEEE Access, 13:18912–18936.

Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020). Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.

de Souza, A. M., Maciel, F., da Costa, J. B., Bittencourt, L. F., Cerqueira, E., Loureiro, A. A., and Villas, L. A. (2024). Adaptive client selection with personalization for communication efficient federated learning. Ad Hoc Networks, 157:103462.

Fu, L., Zhang, H., Gao, G., Zhang, M., and Liu, X. (2023). Client selection in federated learning: Principles, challenges, and opportunities. IEEE Internet of Things Journal, 10(24):21811–21819.

Jarczewski, R., Cerqueira, E., Bittencourt, L. F., A. F. Loureiro, A., A. Villas, L., and De Souza, A. M. (2026). Participation is power: Effective approach to dynamic federated learning. In Proceedings of the 18th IEEE/ACM International Conference on Utility and Cloud Computing, UCC ’25, New York, NY, USA. Association for Computing Machinery.

Jarczewski, R. O., Cerqueira, E., Bittencourt, L. F., Loureiro, A. A. F., Villas, L. A., and de Souza, A. M. (2024). Let’s federate - effective communication strategy for dynamic client participation. In 2024 International Conference on Machine Learning and Applications (ICMLA), pages 361–368.

Jee Cho, Y., Wang, J., and Joshi, G. (2022). Towards understanding biased client selection in federated learning. In Camps-Valls, G., Ruiz, F. J. R., and Valera, I., editors, Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, volume 151 of Proceedings of Machine Learning Research, pages 10351–10375. PMLR.

Kairouz, P., McMahan, H. B., Avent, B., Bellet, A., Bennis, M., Bhagoji, A. N., Bonawitz, K., Charles, Z., Cormode, G., Cummings, R., et al. (2021). Advances and open problems in federated learning. Foundations and trends® in machine learning, 14(1–2):1–210.

Lai, F., Zhu, X., Madhyastha, H. V., and Chowdhury, M. (2021). Oort: Efficient federated learning via guided participant selection. In 15th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 21), pages 19–35.

Maciel, F., de Souza, A. M., Bittencourt, L. F., Villas, L. A., and Braun, T. (2024). Federated learning energy saving through client selection. Pervasive and Mobile Computing, 103:101948.

McMahan, B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B. A. (2017). Communication-efficient learning of deep networks from decentralized data. In Artificial intelligence and statistics, pages 1273–1282. PMLR.

Nguyen, D. T., Johnson, T. T., and Leach, K. (2024). Fisc: Federated domain generalization via interpolative style transfer and contrastive learning. CoRR, abs/2410.22622.

Nishio, T. and Yonetani, R. (2019). Client selection for federated learning with heterogeneous resources in mobile edge. In ICC 2019-2019 IEEE international conference on communications (ICC), pages 1–7. IEEE.

Piao, H., Wu, Y., Wu, D., and Wei, Y. (2024). Federated continual learning via prompt-based dual knowledge transfer. In Proceedings of the 41st International Conference on Machine Learning, ICML’24. JMLR.org.

Shah, S. M. and Lau, V. K. N. (2023). Model compression for communication efficient federated learning. IEEE Transactions on Neural Networks and Learning Systems, 34(9):5937–5951.

Souza, A., Bittencourt, L., Cerqueira, E., Loureiro, A., and Villas, L. (2023). Dispositivos, eu escolho vocês: Seleção de clientes adaptativa para comunicação eficiente em aprendizado federado. In Anais do XLI Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, pages 1–14, Porto Alegre, RS, Brasil. SBC.

Talasso, G., de Souza, A., Guidoni, D., Cerqueira, E., and Villas, L. (2025). Fine-tuning eficiente de modelos de linguagem para detectar anomalias em logs privados usando aprendizado federado. In Anais do XLIII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, pages 126–139, Porto Alegre, RS, Brasil. SBC.

Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., Zhao, W. X., Wei, Z., and Wen, J. (2024). A survey on large language model based autonomous agents. Frontiers of Computer Science, 18(6):186345.

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.

Xu, J. and Wang, H. (2021). Client selection and bandwidth allocation in wireless federated learning networks: A long-term perspective. IEEE Transactions on Wireless Communications, 20(2):1188–1200.

Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K. R., and Cao, Y. (2022). React: Synergizing reasoning and acting in language models. In The eleventh international conference on learning representations.