RMA: an Agentic System for Research-Level Mathematical Problems
Summary
Research Math Agents (RMA) is an agentic framework for automated reasoning on research-level mathematical problems, achieving state-of-the-art results on the First Proof benchmark by solving 8 out of 10 problems, outperforming strong baselines like GPT-5.2R and Aletheia.
View Cached Full Text
Cached at: 05/25/26, 08:54 AM
# RMA: an Agentic System for Research-Level Mathematical Problems
Source: [https://arxiv.org/abs/2605.22875](https://arxiv.org/abs/2605.22875)
[View PDF](https://arxiv.org/pdf/2605.22875)
> 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\.
## Submission history
From: Zelin Zhao \[[view email](https://arxiv.org/show-email/b0f3eb6c/2605.22875)\] **\[v1\]**Wed, 20 May 2026 04:54:22 UTC \(136 KB\)Similar Articles
AI Co-Mathematician: Accelerating Mathematicians with Agentic AI
This paper introduces the AI Co-Mathematician, a workbench that uses agentic AI to support mathematicians in open-ended research tasks like ideation and theorem proving. Early tests show the system achieving state-of-the-art results on hard problem-solving benchmarks, including a 48% score on FrontierMath Tier 4.
Recursive Multi-Agent Systems
This paper introduces RecursiveMAS, a framework that extends recursive scaling principles to multi-agent systems for improved collaborative reasoning efficiency and accuracy. It demonstrates significant speedups and token reduction across various benchmarks compared to standard baselines.
TMAS: Scaling Test-Time Compute via Multi-Agent Synergy
TMAS introduces a multi-agent framework that enhances large language model reasoning by scaling test-time compute through structured collaboration and hierarchical memory systems. The approach uses specialized agents, cross-trajectory information flow, and hybrid reward reinforcement learning to improve iterative scaling and stability on challenging reasoning benchmarks.
Building Agentic GraphRAG Systems: From knowledge graphs and ontologies to a unified memory as an MCP server for your AI agent.
The author argues that GraphRAG is fundamentally a data modeling problem rather than just a retrieval algorithm, proposing a five-component architecture using ontologies, knowledge graphs, and an MCP server for unified agent memory.
@GoogleResearch: Introducing our new agentic RAG framework. A collab with Google Cloud, our multi-agent workflow goes beyond standard RA…
Google Research introduces an agentic RAG framework hosted on the Gemini Enterprise Agent Platform that uses multi-agent workflows to break down complex enterprise queries and iteratively search for sufficient context, achieving up to 34% increased accuracy over standard RAG.