Metraipolis › archive › dc_e810afe5950c

Safin-1.5: Safety-Native Architecture and Verifiable Reasoning for Recursive Safety Improvement — arXiv:2610.40751

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40751
License (as archived)
CC0-1.0
Archived
2026-11-02T04:44:25.603Z
SHA-256 of the archived text
1d0c237e31b3ceff7427ba4751b1898eac637c835a1af305c207cdf5f61d9037
Stable URL of this page
https://metraipolis.com/documento/dc_e810afe5950c

How to cite

Safin-1.5: Safety-Native Architecture and Verifiable Reasoning for Recursive Safety Improvement — arXiv:2610.40751 — arXiv (en), https://arxiv.org/abs/2610.40751 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e810afe5950c (Metraipolis archive dc_e810afe5950c, sha256 1d0c237e31b3ceff7427ba4751b1898eac637c835a1af305c207cdf5f61d9037)
BibTeX
@misc{dce810afe5950c,
  title = {Safin-1.5: Safety-Native Architecture and Verifiable Reasoning for Recursive Safety Improvement — arXiv:2610.40751},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40751},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e810afe5950c; sha256 1d0c237e31b3ceff7427ba4751b1898eac637c835a1af305c207cdf5f61d9037},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40751. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recursive self-improvement (RSI) enables large language models to advance their capabilities through successive updates, but these updates can also introduce new risks and weaken existing safeguards. In line with the AI-45° Law, we pursue Safety RSI, in which safety develops as an intrinsic capability alongside general model capabilities through continual risk discovery and repair, while preserving utility and limiting over-refusal. We introduce Safin-1.5, a model built on a safety architecture and trained through recursive safety improvement, with an inference-time harness that extends its capabilities to formal reasoning. Our approach comprises three components: i) The safety architecture combines persistent safety states with hazardous-knowledge disentanglement. The former retains and selectively invokes safety knowledge, while the latter relocates targeted hazardous knowledge into removable experts, enabling its removal with minimal impact on general capabilities. ii) Recursive safety improvement establishes a discovery-evaluation-repair loop. The loop identifies new vulnerabilities and uses experimental feedback to develop repair strategies. It accepts updates only when they improve safety while preserving general capabilities and limiting over-refusal. iii) The formal reasoning harness combines the model's language understanding with symbolic inference and verification. Proof-obligation-guided semantic bridging recovers missing relations in formal representations, enabling symbolic solvers to construct checkable proofs under formalized premises and accepted semantic bridges. Experimental results demonstrate that Safin-1.5 achieves safety and reasoning performance, outperforming frontier models.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.40751 — 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 2026-11-02T04:42:12.427Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).