Multimodal clinical reasoning in the field of gastrointestinal (GI) oncology necessitates the integrated interpretation of endoscopic imagery, radiological data, and biochemical markers. Despite the evident potential exhibited by Multimodal Large Language Models (MLLMs), they frequently encounter challenges such as context dilution and hallucination when confronted with intricate, heterogeneous medical histories. In order to address these limitations, a hierarchical Multi-Agent Framework is proposed, which emulates the collaborative workflow of a human Multidisciplinary Team (MDT). The system attained a composite expert evaluation score of 4.60/5.00, thereby demonstrating a substantial improvement over the monolithic baseline. It is noteworthy that the agent-based architecture yielded the most substantial enhancements in reasoning logic and medical accuracy. The findings indicate that mimetic, agent-based collaboration provides a scalable, interpretable, and clinically robust paradigm for automated decision support in oncology.
@article{arxiv.2512.08674,
title = {Multi-Agent Intelligence for Multidisciplinary Decision-Making in Gastrointestinal Oncology},
author = {Rongzhao Zhang and Junqiao Wang and Shuyun Yang and Mouxiao Bian and Chihao Zhang and Dongyang Wang and Qiujuan Yan and Yun Zhong and Yuwei Bai and Guanxu Zhu and Kangkun Mao and Miao Wang and Chao Ding and Renjie Lu and Lei Wang and Lei Zheng and Tao Zheng and Xi Wang and Zhuo Fan and Bing Han and Meiling Liu and Luyi Jiang and Dongming Shan and Wenzhong Jin and Jiwei Yu and Zheng Wang and Jie Xu and Meng Luo},
journal= {arXiv preprint arXiv:2512.08674},
year = {2025}
}