Skip to content

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

Oct 2026 · 1 citation · 64 references
Computer Science

TL;DR

This work introduces 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, and demonstrates that Safin-1.5 achieves safety and reasoning performance, outperforming frontier models.

Abstract

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{\deg} 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.

View source

Similar papers

#artificial intelligence Preprint Oct 2026

ReSI: Recursive Safety Improvement toward Resistant and Resilient AI

Recursive self-improvement, the participation of AI systems in improving their own capabilities, is beginning to move from theoretical prospect to practice, posing both challenges and opportunities for safety alignment. Models evolve through frequent updates, and their safety alignment requires continual adaptation to...

Jing-Nan Zheng, Dong-Cheng Zhang, Yi Zhang et al. · 2 citations
Preprint Oct 2026

Safety Mid-Training: Internalizing LLM Safety as a Foundational Capability

It is suggested that learning safety and general reasoning within a shared mid-training stage can reduce the safety-utility trade-off and make safety more robust to subsequent training.

Zheng-Yue Zhao, Li-Wei Jiang, Ye-Jin Choi et al. · 1 citation
Book Open access Oct 2026

When Safety Claims Fail Silently: A Modelling Approach to AI Assurance

Problem. The rapid deployment of large language models (LLMs) into safety-critical roles, including mental health support, education, and professional guidance, has created a gap between the safety claims AI developers publish and the behaviors their systems exhibit in practice. Current documentation practices, primari...

Kalvin Thuan-phong Khuu · 0 citations
Review Open access Oct 2026

Runtime assurance of language-model-based systems: from safety monitors to certification-ready evidence

Language models are entering systems whose failures matter: vehicles, industrial toolchains, and autonomous agents acting on real infrastructure. At the same time, emerging regulation and safety standards demand not merely safe behavior but evidence of it that a third party can re-check. This survey traces a single arc...

Kamal Essam · 0 citations
Preprint Oct 2026

V$^3$AST-Bench: Verifiable, Valid, and Versatile Safety Evaluation for Coding Agents

Across model-harness combinations, agents with comparable competence exhibit markedly different safety outcomes, showing that task capability alone does not guarantee safe execution, and highlighting the need to move beyond risk recognition toward enforcing safety throughout execution.

Wei-Tao Feng, Heng-Heng Xiong, Zi-Hao Zeng et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Runtime Authorization of Self-Generated Subgoals in Long-Horizon Tool-Using AI Agents

Long-horizon tool-using AI agents create subgoals, replan, delegate work, and compose sibling results. Per-tool permission checks cannot establish that a changing goal graph remains within the principal-approved task. We address this authorization gap in a finite structured domain with one principal and one authorizati...

Gen-Liang Zhu, Chu Wang · 1 citation

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.