Metraipolis › archive › dc_646d505ee70c
Learning to Discover Interesting Mathematics — arXiv:2609.28603
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.28603
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T04:27:02.267Z
- SHA-256 of the archived text
722770aff6916fe56a33233835e54a5bde5efd0dc02e976bd342c8878c07edc1- Stable URL of this page
https://metraipolis.com/documento/dc_646d505ee70c
How to cite
Learning to Discover Interesting Mathematics — arXiv:2609.28603 — arXiv (en), https://arxiv.org/abs/2609.28603 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_646d505ee70c (Metraipolis archive dc_646d505ee70c, sha256 722770aff6916fe56a33233835e54a5bde5efd0dc02e976bd342c8878c07edc1)
BibTeX
@misc{dc646d505ee70c,
title = {Learning to Discover Interesting Mathematics — arXiv:2609.28603},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.28603},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_646d505ee70c; sha256 722770aff6916fe56a33233835e54a5bde5efd0dc02e976bd342c8878c07edc1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28603. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recently, Large Language Models (LLMs) have been increasingly able to solve advanced mathematical problems, including many that have been open for decades. This opens the door to expansion of mathematical knowledge at unprecedented scale. Yet, while LLMs may be able to conjecture and prove more and more theorems, it remains open whether this new mathematical knowledge is interesting or useful. We define intrinsic interestingness of a theorem as the ratio between the length of its proof and the length of its statement. We show that this correlates strongly with an extrinsic measure of the downstream utility of a theorem. We identify the difficulty of a proof conditioned on a set of premises as a useful primitive for computing these metrics, and train a 27B model that predicts proof difficulty more accurately than frontier general-purpose models. Optimizing for our metric creates a model capable of producing more interesting theorems, while also reducing substantial or full overlap with Mathlib from 91.9% to 30.6%, showcasing the creation of more out-of-distribution math. We show that our system can generate candidate theorems, select the most interesting among them, and iteratively build on a self-expanding mathematical library. These metrics provide a practical and quantifiable signal for ranking conjectures and guiding proof search within formal mathematical libraries. Our framework provides a path towards self-expanding, machine-verified mathematical libraries that can choose worthwhile statements without relying on human-supplied targets. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.28603 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T03:50:57.936Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).