Metraipolis › archive › dc_e1011d8bc712

Dense Neuro-Symbolic Reasoning in a Unified Geometry State — arXiv:2610.04280

Source
arXiv
Original
https://arxiv.org/abs/2610.04280
License (as archived)
CC0-1.0
Archived
2026-10-06T05:24:25.850Z
SHA-256 of the archived text
404aaf04f53308a5bfc84a095474c4170af67ebf266c00e6f63d3660a4e1a92e
Stable URL of this page
https://metraipolis.com/documento/dc_e1011d8bc712

How to cite

Dense Neuro-Symbolic Reasoning in a Unified Geometry State — arXiv:2610.04280 — arXiv, https://arxiv.org/abs/2610.04280 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e1011d8bc712 (Metraipolis archive dc_e1011d8bc712, sha256 404aaf04f53308a5bfc84a095474c4170af67ebf266c00e6f63d3660a4e1a92e)
BibTeX
@misc{dce1011d8bc712,
  title = {Dense Neuro-Symbolic Reasoning in a Unified Geometry State — arXiv:2610.04280},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04280},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e1011d8bc712; sha256 404aaf04f53308a5bfc84a095474c4170af67ebf266c00e6f63d3660a4e1a92e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04280. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Geometry reasoning is naturally stateful: solving a problem repeatedly alternates between structural proposals and exact deductions. We formulate this process as dense neural-symbolic coupling, in which neural guidance and symbolic execution share a typed state and communicate through executable actions at every search step. Neural proposals contribute theorem instances, constructions, and algebraic bridges; the symbolic runtime applies registered rules, propagates exact constraints, and records provenance. A nested controller allocates computation first between neural and symbolic proposal sources and then among admitted actions. We instantiate the framework in OmniGeo, a single solver for plane, analytic, and solid geometry. With Claude Sonnet 4.6, OmniGeo reaches 94.2%, 88.5%, and 89.8% on FormalGeo7K, Conic10K, and SolidFGeo, respectively (90.8% macro average), and solves 21/30 IMO-AG-30 problems.

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/2610.04280 — 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 2026-10-06T05:24:05.448Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).