RMA: an Agentic System for Research-Level Mathematical Problems
Quick Answer
This paper shows that The Research Math Agents (RMA) framework excels in solving research-level mathematical problems, outperforming models like GPT-5.2R and Aletheia on the First Proof benchmark by solving 8 out of 10 problems.
Quick Take
The Research Math Agents (RMA) framework excels in solving research-level mathematical problems, outperforming models like GPT-5.2R and Aletheia on the First Proof benchmark by solving 8 out of 10 problems. RMA's enhances proof generation and verification through structured reasoning and iterative feedback.
Key Points
- RMA framework focuses on long-horizon reasoning and iterative proof refinement.
- It consists of specialized modules for problem analysis, literature search, and proof verification.
- RMA outperformed strong baselines, solving 8 out of 10 research problems.
- Evaluation conducted on the First Proof benchmark with expert mathematicians.
- Public implementation of RMA will be available upon acceptance.
Paper Resources
Article Content
From source RSS / original summaryarXiv: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 research-level mathematical problems that require long-horizon reasoning, literature grounding, and iterative proof refinement.
RMA decomposes research-level proof solving into specialized modules for problem analysis, literature search and understanding, fair comparison, knowledge-bank construction, and proof verification, all coordinated by initializer, proposer, and verifier agents through a shared structured memory. Within this unified framework, these agents operate in a multi-role, multi-round workflow, collaboratively generating, refining, and verifying candidate proofs through iterative feedback.
We evaluate RMA on the First Proof benchmark, which consists of ten research-level problems contributed by expert mathematicians across diverse domains. Through comprehensive expert evaluation, RMA outperforms strong baselines on the First Proof benchmark, including GPT-5. 2R and Aletheia, solving eight out of ten research problems and producing more logically sound and readable proofs.
Our comprehensive ablation studies further show that performance gains arise from the interaction of structured reasoning modules, iterative refinement, and verifier-based feedback, rather than any single component. Our solutions and implementations will be made publicly available upon acceptance.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →Information Limits and Attractor Dynamics in Economies of Frontier LLM Agents: A Pre-Registered Test
A pre-registered experiment on Claude Opus 4.8 investigates wealth growth and population misalignment in economies, revealing that relative growth aligns with claimed information but fails to demonstrate expected noise-maintained dispersion. The experiment cost $138.76 and is fully reproducible from cached outputs.