RESEARCH

RMA: an Agentic System for Research-Level Mathematical Problems

ArXiv cs.AI · Mon, 25 May 2026 04:00:00 GMT

arXiv:2605.22875v1 Announce Type: new Abstract: We present $\textbf{Research Math Agents (RMA)}$, an agentic framework for automated reasoning on research-level mathematical problems. Unlike prior studies centered on competition mathematics or formal theorem proving, RMA targets

Read original source Discuss with A.S.I.S