arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.08373cs.AIcs.LG
收藏

基于可验证逻辑的生成规划器：一种可信具身AI的混合架构

Grounding Generative Planners in Verifiable Logic: A Hybrid Architecture for Trustworthy Embodied AI

School of Cyber Engineering, Xidian University（电子科技大学信息工程学院）

Feiyu Wu, Xu Zheng, Yue Qu, Zhuocheng Wang, Zicheng Feng, Hui Li

发表信息：
Proceedings of the International Conference on Learning Representations (ICLR), 2026
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出VIRF框架，通过逻辑导师与LLM的对话机制实现主动协作，提升具身AI的安全性与可靠性，实验显示其在家庭安全任务中表现优异。

摘要：

大型语言模型（LLMs）在具身AI中表现出潜力，但其随机性缺乏形式推理，无法提供严格的物理部署安全保证。当前方法常依赖不可靠的LLMs进行安全检查或拒绝不安全计划而不提供修复。我们引入可验证迭代精炼框架（VIRF），一种神经符号架构，将安全守护模式转变为主动协作模式。我们的核心贡献是一种导师-学徒对话机制，其中确定性的逻辑导师基于形式安全本体，为LLM规划器提供因果和教学反馈。这使规划器能够智能修复而非仅仅避免危险。我们还引入了一种可扩展的知识获取管道，从现实世界文档中合成安全知识库，纠正现有基准的盲点。在具有挑战性的家庭安全任务中，VIRF实现了0%的危险行动率（HAR）和77.3%的目标条件率（GCR），是所有基线中的最高值。它非常高效，平均仅需1.1次修正迭代。VIRF展示了构建根本可信和可验证安全具身代理的原理路径。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑