Skip to content
AI Atlas
PaperActive

Measuring Progress in Reasoning Toward Mathematical Discovery with Automatic Verification

arxiv.org/abs/2603.15617

quality89

Updated 6 h ago · first seen 11 Sept 2026

paper_01M294FS2H341MDA8M89G2NBX8

Published
11 Sept 2026
T1 · 6 h ago
arXiv
2603.15617
T1 · 6 h ago
Category
cs.LG
T1 · 6 h ago

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history

9 claims · 9 properties

Official pageofficial_url1

Claim history for Official page
ValueValid from → toStatusSourceConfidenceExtractor
https://arxiv.org/abs/2603.15617currentcurrentarXiv (Atom API + RSS)T1highdeterministic

Abstractabstract1

Claim history for Abstract
ValueValid from → toStatusSourceConfidenceExtractor
Can AI make progress on important, unsolved mathematical problems? Large language models are now capable of sophisticated mathematical and scientific reasoning, but whether they can perform novel research is still widely debated and underexplored. We introduce HorizonMath, a benchmark of 113 predominantly unsolved problems spanning eight domains in mathematics and the mathematical sciences, paired with an open-source evaluation framework for automated verification. Our benchmark targets the generator-verifier gap: problems where discovery is hard and requires meaningful mathematical insight, but verification is computationally straightforward. This contrasts with most existing research-level benchmarks, which instead rely on formal proof verification or manual review, both of which are expensive to scale. Because these solutions are unknown, HorizonMath is resistant to data contamination, and most state-of-the-art models score under 10%. Using this framework, we identify six novel solutions to research problems that either resolve previously open questions or improve on the best-known published results, with GPT-5.4 Pro and GPT-5.6 Sol each discovering three of these solutions. Across seven frontier model families, reasoning efficiency and behavior also vary substantially. We release HorizonMath as an open challenge and a growing community resource, where each verified solution is a candidate contribution to the mathematical literature.currentcurrentarXiv (Atom API + RSS)T1highdeterministic

Arxiv announce typearxiv_announce_type1

Claim history for Arxiv announce type
ValueValid from → toStatusSourceConfidenceExtractor
replacecurrentcurrentarXiv (Atom API + RSS)T1highdeterministic

arXiv idarxiv_id1

Claim history for arXiv id
ValueValid from → toStatusSourceConfidenceExtractor
2603.15617currentcurrentarXiv (Atom API + RSS)T1highdeterministic

Authorsauthors1

Claim history for Authors
ValueValid from → toStatusSourceConfidenceExtractor
Erik Y. Wang, Sumeet R. Motwani, James V. Roggeveen, Eliot Hodges, Dulhan Jayalath, Charles London, Kalyan Ramakrishnan, Jakob Foerster, Cheng Zhang, Flaviu Cipcigan, Philip Torr, Alessandro AbatecurrentcurrentarXiv (Atom API + RSS)T1highdeterministic

Categoriescategories1

Claim history for Categories
ValueValid from → toStatusSourceConfidenceExtractor
cs.LGcurrentcurrentarXiv (Atom API + RSS)T1highdeterministic

PDFpdf_url1

Claim history for PDF
ValueValid from → toStatusSourceConfidenceExtractor
https://arxiv.org/pdf/2603.15617currentcurrentarXiv (Atom API + RSS)T1highdeterministic

Primary categoryprimary_category1

Claim history for Primary category
ValueValid from → toStatusSourceConfidenceExtractor
cs.LGcurrentcurrentarXiv (Atom API + RSS)T1highdeterministic

Publishedpublished_at1

Claim history for Published
ValueValid from → toStatusSourceConfidenceExtractor
11 Sept 2026currentcurrentarXiv (Atom API + RSS)T1highdeterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →