Metraipolis › archive › dc_aafda058e995

When Does Structured Knowledge Help Neural Theorem Proving? — arXiv:2609.34460

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34460
License (as archived)
CC0-1.0
Archived
2026-10-07T20:57:48.729Z
SHA-256 of the archived text
a501b74dfb284970bfeba8ee486c48a6752044cc727a36b114ebfb876a02d2c7
Stable URL of this page
https://metraipolis.com/documento/dc_aafda058e995

How to cite

When Does Structured Knowledge Help Neural Theorem Proving? — arXiv:2609.34460 — arXiv (en), https://arxiv.org/abs/2609.34460 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aafda058e995 (Metraipolis archive dc_aafda058e995, sha256 a501b74dfb284970bfeba8ee486c48a6752044cc727a36b114ebfb876a02d2c7)
BibTeX
@misc{dcaafda058e995,
  title = {When Does Structured Knowledge Help Neural Theorem Proving? — arXiv:2609.34460},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34460},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aafda058e995; sha256 a501b74dfb284970bfeba8ee486c48a6752044cc727a36b114ebfb876a02d2c7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34460. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Does structured mathematical knowledge help LLMs prove theorems in Lean 4? If so, for which models, and does the answer vary by problem? Formal libraries such as Mathlib encode 285,000+ verified theorems with syntactic dependencies, but the semantic layer mathematicians rely on for discovery (analogies, generalizations, cross-domain bridges) remains implicit. We introduce MathAgent, which builds this layer as a knowledge graph, MathKG, and uses it to augment LLM theorem provers. MathKG connects 364 Mathlib theorems and definitions by 9,434 typed semantic edges inferred via LLM-based relation extraction anchored to verified Mathlib declarations. We run a controlled ablation across four augmentation modes (no context, knowledge-graph context, Mathlib retrieval, both) and five models: Qwen3-8B/32B, their Lean-specialized derivatives Goedel-Prover-V2-8B/32B, and Claude Sonnet 4.6, on miniF2F, plus PutnamBench and MathOlympiadBench for Sonnet. Three findings emerge. (i) Specialization dominates augmentation: Lean fine-tuning adds 33-38 percentage points of solve rate in every mode, and a specialized 8B model beats a $4\times$ larger general one by 29-35 points, while no augmentation mode improves solve rate by more than 3 points. (ii) Augmentation is capability-conditioned: knowledge-graph context helps small models but hurts large ones, with the specialized model gaining more relative to its general base at every scale. (iii) Yet the augmentation modes solve different problems: an oracle selecting the best mode per problem solves 6% to 58% more than the unaugmented prover, a complementarity effect that strengthens on harder problems (32% more on PutnamBench). These results motivate adaptive strategies that select augmentation by model capability and problem. Code, data, and artifacts are available at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Logic in Computer Science (cs.LO).
Pagina del lavoro: https://arxiv.org/abs/2609.34460 — 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 2026-10-07T20:29:01.562Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).