Metraipolis › archive › dc_faa4feb32b09

ProofEvolve: Neuro-Symbolic Evolution for Formal Automated Theorem Proving — arXiv:2608.26334

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.26334
License (as archived)
CC0-1.0
Archived
2026-10-17T14:22:35.876Z
SHA-256 of the archived text
154bc7d0d1d2de7f90ed2733f68b05f3e46aafb70516f77d2305d8fbc62b8dfe
Stable URL of this page
https://metraipolis.com/documento/dc_faa4feb32b09

How to cite

ProofEvolve: Neuro-Symbolic Evolution for Formal Automated Theorem Proving — arXiv:2608.26334 — arXiv (en), https://arxiv.org/abs/2608.26334 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_faa4feb32b09 (Metraipolis archive dc_faa4feb32b09, sha256 154bc7d0d1d2de7f90ed2733f68b05f3e46aafb70516f77d2305d8fbc62b8dfe)
BibTeX
@misc{dcfaa4feb32b09,
  title = {ProofEvolve: Neuro-Symbolic Evolution for Formal Automated Theorem Proving — arXiv:2608.26334},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26334},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_faa4feb32b09; sha256 154bc7d0d1d2de7f90ed2733f68b05f3e46aafb70516f77d2305d8fbc62b8dfe},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26334. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Automated theorem proving offers a natural foundation for recursive self-improvement in scientific discovery. However, existing neural provers do not fully preserve this recursive structure, where the learning process should be self-improving over time. Existing methods either embed proof experience into model parameters through expensive weight updates, or keep verified intermediate deductions only within the current problem. In addition, these methods also heavily rely on sparse whole-proof feedback, even when unsuccessful partial attempts contain useful discoveries. To close the gap, we propose ProofEvolve, a neuro-symbolic framework that evolves explicit, formally verified symbolic proof structures with neural models to decisively expand the knowledge boundary. In this framework, the neural model proposes variation operators, including decompositions, repairs, and schema recombinations. The symbolic Lean kernel verifies every proof transition. Over the evolution loops, ProofEvolve computes verified closure over the resulting proof directed acyclic graphs (DAGs). Within each problem, ProofEvolve evolves partial AND-OR proof DAGs in a behaviorally indexed archive. Across problems, kernel-checked schema extraction adds newly proved sub-DAGs to a persistent schema library. Proof DAGs inherit the solved results through typed schema recombination, with every residual premise exposed as a new subgoal. This evolutionary process preserves verified results from incomplete attempts and makes them available for later proofs without weakening formal soundness. Across three competition-level Lean benchmarks, ProofEvolve achieves the highest average solve rate among the evaluated proof systems.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.26334 — 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 2026-10-17T13:16:53.490Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).