Abstract
Large Language Models (LLMs) show promise as planners for embodied AI, but their stochastic nature lacks formal reasoning, preventing strict safety guarantees for physical deployment. Current approaches often rely on unreliable LLMs for safety checks or simply reject unsafe plans without offering repairs. We introduce the Verifiable Iterative Refinement Framework (VIRF), a neuro-symbolic architecture that shifts the paradigm from passive safety gatekeeping to active collaboration. Our core contribution is a tutor-apprentice dialogue where a deterministic Logic Tutor, grounded in a formal safety ontology, provides causal and pedagogical feedback to an LLM planner. This enables intelligent plan repairs rather than mere avoidance. We also introduce a scalable knowledge acquisition pipeline that synthesizes safety knowledge bases from real-world documents, correcting blind spots in existing benchmarks. In challenging home safety tasks, VIRF achieves a perfect 0 percent Hazardous Action Rate (HAR) and a 77.3 percent Goal-Condition Rate (GCR), which is the highest among all baselines. It is highly efficient, requiring only 1.1 correction iterations on average. VIRF demonstrates a principled pathway toward building fundamentally trustworthy and verifiably safe embodied agents.
Abstract (translated)
大型语言模型（LLMs）在具身AI的规划方面显示出潜力，但它们随机性的特性缺乏形式化推理能力，这阻碍了其在物理部署中的严格安全保证。当前的方法通常依赖不可靠的LLM来进行安全性检查，或者干脆拒绝不安全的计划而不提供修复方案。我们提出了一个可验证的迭代细化框架（VIRF），这是一种神经符号架构，它将被动的安全守门模式转变为积极的合作模式。我们的核心贡献在于设计了一个导师-学徒对话机制，在这个机制中，确定性的逻辑导师根据形式化的安全性本体论提供因果关系和教学反馈给LLM规划器。这使得智能计划修复成为可能，而不仅仅是简单地避免问题。 我们还引入了一种可扩展的知识获取管道，该管道从现实世界的文档中综合出安全知识库，纠正现有基准中的盲点。在具有挑战性的家庭安全任务中，VIRF实现了完美的0%危险行动率（HAR）和77.3%的目标条件达成率（GCR），这两项指标都优于所有基线方法的表现。此外，VIRF的效率也很高，平均只需要1.1次修正迭代。 总的来说，VIRF展示了一种建立根本上值得信赖且可验证安全的具身代理的基本路径。
URL
https://arxiv.org/abs/2602.08373
