A Framework for Benchmarking and Aligning Task-Planning Safety in LLM-Based Embodied Agents
This addresses safety risks in embodied AI agents for real-world applications, representing a novel but incremental advancement in safety benchmarking and alignment.
The study tackled the problem of systemic safety in LLM-based embodied agents by introducing Safe-BeAl, a framework that benchmarks safety with 2,027 tasks across 8 hazard categories and aligns agents to improve safety by 8.55-15.22% while maintaining task performance.
Large Language Models (LLMs) exhibit substantial promise in enhancing task-planning capabilities within embodied agents due to their advanced reasoning and comprehension. However, the systemic safety of these agents remains an underexplored frontier. In this study, we present Safe-BeAl, an integrated framework for the measurement (SafePlan-Bench) and alignment (Safe-Align) of LLM-based embodied agents' behaviors. SafePlan-Bench establishes a comprehensive benchmark for evaluating task-planning safety, encompassing 2,027 daily tasks and corresponding environments distributed across 8 distinct hazard categories (e.g., Fire Hazard). Our empirical analysis reveals that even in the absence of adversarial inputs or malicious intent, LLM-based agents can exhibit unsafe behaviors. To mitigate these hazards, we propose Safe-Align, a method designed to integrate physical-world safety knowledge into LLM-based embodied agents while maintaining task-specific performance. Experiments across a variety of settings demonstrate that Safe-BeAl provides comprehensive safety validation, improving safety by 8.55 - 15.22%, compared to embodied agents based on GPT-4, while ensuring successful task completion.