Grounding Generative Planners in Verifiable Logic: A Hybrid Architecture for Trustworthy Embodied AI
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
机构 * School of Cyber Engineering, Xidian University(电子科技大学信息工程学院)
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。
Comments Accepted to ICLR 2026. Project page. https://openreview.net/forum?id=wb05ver1k8¬eId=v1Ax8CwI71
Journal ref Proceedings of the International Conference on Learning Representations (ICLR), 2026