RMA: an Agentic System for Research-Level Mathematical Problems
Research Math Agents (RMA) is an automated reasoning framework for research-level mathematical problems. It solves 8 out of 10 problems on the First Proof benchmark, outperforming GPT-5.2R and Aletheia through multi-agent collaboration and iterative refinement.
Article intelligence
Key points
- RMA decomposes proof solving into specialized modules: problem analysis, literature search, fair comparison, knowledge bank construction, and proof verification.
- It uses initializer, proposer, and verifier agents operating in a multi-round workflow with shared structured memory.
- On the First Proof benchmark of ten research problems from expert mathematicians, RMA solved eight and produced more logically sound proofs.
- Ablation studies show performance gains come from the interaction of structured reasoning, iterative refinement, and verifier feedback.
Why it matters
This matters because RMA decomposes proof solving into specialized modules: problem analysis, literature search, fair comparison, knowledge bank construction, and proof verification.
Technical impact
May affect model selection, inference cost, product capability, and evaluation benchmarks.
[2605.22875] RMA: an Agentic System for Research-Level Mathematical Problems
[Submitted on 20 May 2026]
Title:RMA: an Agentic System for Research-Level Mathematical Problems
View a PDF of the paper titled RMA: an Agentic System for Research-Level Mathematical Problems, by Zelin Zhao and 3 other authors
View PDF
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.
Subjects:
Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as: arXiv:2605.22875 [cs.AI]
(or arXiv:2605.22875v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2605.22875
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Zelin Zhao [view email] [v1] Wed, 20 May 2026 04:54:22 UTC (136 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled RMA: an Agentic System for Research-Level Mathematical Problems, by Zelin Zhao and 3 other authors
View PDF
TeX Source
view license
Current browse context:
cs.AI
new | recent | 2026-05
Change to browse by:
cs cs.LG
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)