Metraipolis › archive › dc_a4c7b36beee3
Improving Analytic Constants via Interpretable AI-Guided Lean Proof Refinement — arXiv:2611.10961
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.10961
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:41:18.405Z
- SHA-256 of the archived text
c9ef1eaa594332938e586e95c7eedb498967f315ae4bfbce20f12787bdf38fc8- Stable URL of this page
https://metraipolis.com/documento/dc_a4c7b36beee3
How to cite
Improving Analytic Constants via Interpretable AI-Guided Lean Proof Refinement — arXiv:2611.10961 — arXiv (en), https://arxiv.org/abs/2611.10961 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a4c7b36beee3 (Metraipolis archive dc_a4c7b36beee3, sha256 c9ef1eaa594332938e586e95c7eedb498967f315ae4bfbce20f12787bdf38fc8)
BibTeX
@misc{dca4c7b36beee3,
title = {Improving Analytic Constants via Interpretable AI-Guided Lean Proof Refinement — arXiv:2611.10961},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.10961},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a4c7b36beee3; sha256 c9ef1eaa594332938e586e95c7eedb498967f315ae4bfbce20f12787bdf38fc8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10961. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
AI agents are increasingly capable of discovering new mathematical results, yet their reasoning and generated proofs can be difficult to understand and verify. We introduce an interpretable framework for AI-guided mathematical discovery, focused on improving quantitative bounds on analytic constants. Our key insight is that existing proofs often contain slack in intermediate lemmas, which can be tightened without reconstructing the entire argument. To exploit this structure, we represent proofs as partially-formalized Lean blueprints: human-interpretable dependency graphs of definitions, lemmas, and theorems. An AI agent then iteratively refines the Lean code while preserving the blueprint's dependency structure, allowing local improvements to automatically propagate to a verified final bound. This interpretable structure allows humans to inspect the agent's refinements and understand how local improvements propagate to the final theorem. For Grothendieck's constant ($\mathcal{K}_G$), we obtain $$ \mathcal{K}_G \leq \frac{\pi}{2\log(1+\sqrt{2})} - 10^{-17}, $$ an explicit numerical improvement over Krivine's 1977 bound. For Korenblum's constant ($\mathcal{K}_K$), we obtain $$ \mathcal{K}_K \geq 0.356565, $$ improving Wang's 2025 bound of $0.3554$. Our experiments demonstrate the potential of both partial formalization and iterative agentic refinement for interpretable mathematical discovery.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Numerical Analysis (math.NA).
Pagina del lavoro: https://arxiv.org/abs/2611.10961 — 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 2026-11-10T18:37:37.509Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).