SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of Foundation Model-based Embodied Agents

SENTINEL is the first framework to provide multi-level safety evaluation of foundation model-based embodied agents — across semantic interpretation, plan generation, and physical execution — within a unified formal framework. Instead of heuristic rules or subjective FM judgments, it grounds practical safety requirements in temporal logic semantics that precisely specify state invariants, temporal dependencies, and timing constraints, and applies the pipeline to agents in VirtualHome and AI2-THOR against diverse safety requirements.

Authors: Simon Sinong Zhan, Yao Liu, Philip Wang, Zinan Wang, Qineng Wang, Yiyan Peng, Zhian Ruan, Xiangyu Shi, Xinyu Cao, Frank Yang, Kangrui Wang, Huajie Shao, Manling Li, Qi Zhu

@article{zhan2025sentinel, title={SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of Foundation Model-based Embodied Agents}, author={Zhan, Simon Sinong and Liu, Yao and Wang, Philip and Wang, Zinan and Wang, Qineng and Peng, Yiyan and Ruan, Zhian and Shi, Xiangyu and Cao, Xinyu and Yang, Frank and Wang, Kangrui and Shao, Huajie and Li, Manling and Zhu, Qi}, journal={arXiv preprint arXiv:2510.12985}, year={2025} }