# A Framework for Benchmarking and Aligning Task-Planning Safety in LLM-Based Embodied Agents

arXiv: https://arxiv.org/abs/2504.14650 · HTML: https://mlsanity.com/paper/2504.14650/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 20 Apr 2025.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 23 of 23)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [VirtualHome: Simulating Household Activities via Programs](https://mlsanity.com/paper/1806.07011/) (2018)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners](https://mlsanity.com/paper/2307.01928/) (2023)
- [A Survey on Vision-Language-Action Models for Embodied AI](https://mlsanity.com/paper/2405.14093/) (2024)
- [Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs](https://mlsanity.com/paper/2406.18629/) (2024)
- [Large Language Model Alignment: A Survey](https://mlsanity.com/paper/2309.15025/) (2023)
- [ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings](https://mlsanity.com/paper/2305.11554/) (2023)
- [Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI](https://mlsanity.com/paper/2407.06886/) (2024)
- [BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation](https://mlsanity.com/paper/2403.09227/) (2024)
- [Language Models Meet World Models: Embodied Experiences Enhance Language Models](https://mlsanity.com/paper/2305.10626/) (2023)
- [The Vulnerability of Language Model Benchmarks: Do They Accurately Reflect True LLM Performance?](https://mlsanity.com/paper/2412.03597/) (2024)
- [Hazards in Daily Life? Enabling Robots to Proactively Detect and Resolve Anomalies](https://mlsanity.com/paper/2411.00781/) (2024)
- [LLM-Personalize: Aligning LLM Planners with Human Preferences via Reinforced Self-Training for Housekeeping Robots](https://mlsanity.com/paper/2404.14285/) (2024)

## Built on by (most cited first, 30 of 30)

- [IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks](https://mlsanity.com/paper/2506.16402/) (2025)
- [AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions](https://mlsanity.com/paper/2506.14697/) (2025)
- [SafeMind: Benchmarking and Mitigating Safety Risks in Embodied LLM Agents](https://mlsanity.com/paper/2509.25885/) (2025)
- [Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses](https://mlsanity.com/paper/2605.02900/) (2026)
- [MADRA: Multi-Agent Debate for Risk-Aware Embodied Planning](https://mlsanity.com/paper/2511.21460/) (2025)
- [Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives](https://mlsanity.com/paper/2506.09656/) (2025)
- [HomeSafeBench: Benchmarking Embodied Vision-Language Models in Free-Exploration Home Safety Inspection](https://mlsanity.com/paper/2509.23690/) (2025)
- [HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task](https://mlsanity.com/paper/2603.14367/) (2026)
- [Using large language models for embodied planning introduces systematic safety risks](https://mlsanity.com/paper/2604.18463/) (2026)
- [ForesightSafety Bench: A Frontier Risk Evaluation and Governance Framework towards Safe AI](https://mlsanity.com/paper/2602.14135/) (2026)
- [LABSHIELD: A Multimodal Benchmark for Safety-Critical Reasoning and Planning in Scientific Laboratories](https://mlsanity.com/paper/2603.11987/) (2026)
- [EmbodiedGovBench: A Benchmark for Governance, Recovery, and Upgrade Safety in Embodied Agent Systems](https://mlsanity.com/paper/2604.11174/) (2026)
- [LabGuard: Grounding Natural-Language Laboratory Rules into Runtime Guards for Embodied Laboratory Agents](https://mlsanity.com/paper/2606.31045/) (2026)
- [SafeRelBench: A Spatial-Relation-Aware Benchmark for Process-Level Safety in VLM-Driven Embodied Agents](https://mlsanity.com/paper/2607.14543/) (2026)
- [Security of World-Model-Based Embodied AI: A Lifecycle of Threats, Defenses, and Evaluation](https://mlsanity.com/paper/2607.28226/) (2026)
- [S3LoRA: Safe Spectral Sharpness-Guided Pruning in Adaptation of Agent Planner](https://mlsanity.com/paper/2508.15068/) (2025)
- [HomeSafe-Bench: Evaluating Vision-Language Models on Unsafe Action Detection for Embodied Agents in Household Scenarios](https://mlsanity.com/paper/2603.11975/) (2026)
- [SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models](https://mlsanity.com/paper/2604.19638/) (2026)
- [EgoSafetyBench: A Diagnostic Egocentric Video Benchmark for Evaluating Embodied VLMs as Runtime Safety Guards](https://mlsanity.com/paper/2607.00218/) (2026)
- [Before We Trust Them: Decision-Making Failures in Navigation of Foundation Models](https://mlsanity.com/paper/2601.05529/) (2026)
- [TSHA: A Benchmark for Visual Language Models in Trustworthy Safety Hazard Assessment Scenarios](https://mlsanity.com/paper/2603.29759/) (2026)
- [NEXUS: Continual Learning of Symbolic Constraints for Safe and Robust Embodied Planning](https://mlsanity.com/paper/2605.09387/) (2026)
- [Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs](https://mlsanity.com/paper/2606.09038/) (2026)
- [When Words Are Safe But Actions Kill: Probing Physical Jailbreak Beyond Textual Jailbreak in Hidden-State Risk Space](https://mlsanity.com/paper/2607.15218/) (2026)
- [GuardianBench: A Same-Scene Instruction-Contrastive Benchmark for Latent Contextual Risk in Embodied AI](https://mlsanity.com/paper/2608.21928/) (2026)
- [Beyond What Meets the Eye: Unveiling Situational Illusions for Multimodal Large Language Models](https://mlsanity.com/paper/2608.22232/) (2026)
- [Safe Task Planning with Long-Term Graph Memory for Embodied Agents](https://mlsanity.com/paper/2609.08444/) (2026)
- [Security and Privacy in Large-Model-Driven Embodied Agents: Attacks, Defenses, and Future Directions](https://mlsanity.com/paper/2609.27847/) (2026)
- [PlanGuard: A Guardrail for Multi-Step Plan Safety in Embodied Agents](https://mlsanity.com/paper/2609.32801/) (2026)
- [RT-Safe: Benchmarking Agent Safety in Real-Time Embodied Environment](https://mlsanity.com/paper/2610.09294/) (2026)

## Abstract (arXiv)

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.