Medical question answering systems face deployment challenges including hallucinations, bias, computational demands, privacy concerns, and the need for specialized expertise across diverse domains. Here, we present SOLVE-Med, a multi-agent architecture combining domain-specialized small language models for complex medical queries. The system employs a Router Agent for dynamic specialist selection, ten specialized models (1B parameters each) fine-tuned on specific medical domains, and an Orchestrator Agent that synthesizes responses. Evaluated on Italian medical forum data across ten specialties, SOLVE-Med achieves superior performance with ROUGE-1 of 0.301 and BERTScore F1 of 0.697, outperforming standalone models up to 14B parameters while enabling local deployment. Our code is publicly available on GitHub: https://github.com/PRAISELab-PicusLab/SOLVE-Med.
@article{arxiv.2511.03542,
title = {SOLVE-Med: Specialized Orchestration for Leading Vertical Experts across Medical Specialties},
author = {Roberta Di Marino and Giovanni Dioguardi and Antonio Romano and Giuseppe Riccio and Mariano Barone and Marco Postiglione and Flora Amato and Vincenzo Moscato},
journal= {arXiv preprint arXiv:2511.03542},
year = {2025}
}