Metraipolis › archive › dc_2e2dc38fcf75
IneqAgent: Agentic Inequality Proving in Lean with Symbolic Computation — arXiv:2610.20681
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.20681
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T08:59:25.345Z
- SHA-256 of the archived text
5cd044eb63256e21786b85e85bf26482b837ff92eaaa0f7fa9d9a0e9c7a2b979- Stable URL of this page
https://metraipolis.com/documento/dc_2e2dc38fcf75
How to cite
IneqAgent: Agentic Inequality Proving in Lean with Symbolic Computation — arXiv:2610.20681 — arXiv (en), https://arxiv.org/abs/2610.20681 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2e2dc38fcf75 (Metraipolis archive dc_2e2dc38fcf75, sha256 5cd044eb63256e21786b85e85bf26482b837ff92eaaa0f7fa9d9a0e9c7a2b979)
BibTeX
@misc{dc2e2dc38fcf75,
title = {IneqAgent: Agentic Inequality Proving in Lean with Symbolic Computation — arXiv:2610.20681},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.20681},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2e2dc38fcf75; sha256 5cd044eb63256e21786b85e85bf26482b837ff92eaaa0f7fa9d9a0e9c7a2b979},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20681. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Formal inequality proving requires mathematical reasoning and exact computation, often connected through intermediate lemmas and goal reformulations. We introduce IneqAgent, an agentic framework combining LLM reasoning with symbolic computation for inequality proving in Lean4. Lemma-level Monte Carlo Tree Search coordinates lemma construction, goal reformulation, and symbolic backend selection. Complementary sum-of-squares, Bernstein, and successive difference-substitution backends produce exact certificates for local Lean proof generation. The agent integrates these proofs with LLM-generated steps and uses Lean feedback to construct complete proofs checked against the original theorem statements. On four benchmarks, IneqAgent with DeepSeek-V4-Flash solves 175 of 186 problems (94.09%), achieving the highest overall success rate among the evaluated methods. Across four backbones, it achieves higher success rates at low LLM inference cost thresholds than Direct Agent using the same backbone, with lower mean inference costs over each method's successful runs. We also obtain Lean-verified strengthenings of Dittert's conjecture in dimensions four and five, and certify the Holens--Djokovic $(4,4)$ inequality, implying Merris's conjecture in dimension four. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.20681 — 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 2026-10-16T08:44:17.648Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).