PlanGuard: A Guardrail for Multi-Step Plan Safety in Embodied Agents

arXiv:2609.32801 · cs.AI, cs.CR, cs.CV, cs.RO · Submitted 2026-09-26 · Read on arXiv

cs.AI, cs.CR, cs.CV, cs.RO

Submitted: 2026-09-26

Updated: 2026-09-26

Code: https://github.com/meta-llama/PurpleLlama

Terminology

• Distillation — 17× in this paper · explained in 2 episodes
• On-Policy Distillation — 9× in this paper · explained in 3 episodes
• Task Planning — 8× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Benchmark — 4× in this paper · explained in 2 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Generalization — 4× in this paper · explained in 13 episodes
• Benchmarking — 3× in this paper · explained in 3 episodes
• Verification — 3× in this paper · explained in 2 episodes
• F1 Score — 2× in this paper · explained in 3 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Embodied AI — 1× in this paper · explained in 2 episodes
• Two-Stage Optimization — 1× in this paper · explained in 2 episodes
• Two-stage training — 1× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes

Sources

• Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution
• Igniting VLMs toward the Embodied Space
• EARBench: Towards Evaluating Physical Risk Awareness for Task Planning of Foundation Model-based Embodied AI Agents
• SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents
• EMBGuard: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied Agents
• Qwen3-VL Technical Report
• DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
• Generating Robot Constitutions & Benchmarks for Semantic Safety
• Can AI Perceive Physical Danger and Intervene?
• A Framework for Benchmarking and Aligning Task-Planning Safety in LLM-Based Embodied Agents
• SafeMind: Benchmarking and Mitigating Safety Risks in Embodied LLM Agents
• Qwen3Guard Technical Report
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection