Authors Daibo Liu, Jiahe Geng, Zhengyang Huang, Shuchen Zhu, Hengrui Zhang, Boao Kong, Pingwen Zhang, Yutong He, Daibo Li, Guohong Li, Can Ren, Zekun Zhang, Yifan Liu, Ming Sun, Shu Li, Chenyi Li, Jiang Hu, Kun Yuan, Zaiwen Wen
Publication date 15 July 2026
Tldr This paper presents ReasFlow, an end-to-end system that assists reasoning-centric scientific discovery in applied mathematics by augmenting human experts with autonomous agents capable of rigorous derivations and knowledge synthesis. Its key contribution is the implementation of a collaborative paradigm where humans act as Principal Investigators and AI agents execute derivations like graduate students.
This page was built for publication: ReasFlow: Assisting Reasoning-Centric Scientific Discovery in Applied Mathematics via a Knowledge-Based Multi-Agent System
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7284206)
