# RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic

arXiv: https://arxiv.org/abs/2512.21220 · HTML: https://mlsanity.com/paper/2512.21220/

## Key facts

- Cited by 14 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 32 of its 39 references that are in the map.
- First posted on arXiv 24 Dec 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, 30 of 32)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022)
- [LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models](https://mlsanity.com/paper/2212.04088/) (2022)
- [DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving](https://mlsanity.com/paper/2312.09245/) (2023)
- [AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents](https://mlsanity.com/paper/2503.18666/) (2025)
- [Dolphins: Multimodal Language Model for Driving](https://mlsanity.com/paper/2312.00438/) (2023)
- [Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model](https://mlsanity.com/paper/2305.11176/) (2023)
- [SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents](https://mlsanity.com/paper/2412.13178/) (2024)
- [Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt](https://mlsanity.com/paper/2406.04031/) (2024)
- [VLM-AD: End-to-End Autonomous Driving through Vision-Language Model Supervision](https://mlsanity.com/paper/2412.14446/) (2024)
- [Octopus: Embodied Vision-Language Programmer from Environmental Feedback](https://mlsanity.com/paper/2310.08588/) (2023)
- [SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models](https://mlsanity.com/paper/2410.18927/) (2024)
- [MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception](https://mlsanity.com/paper/2312.07472/) (2023)
- [Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection](https://mlsanity.com/paper/2412.04455/) (2024)
- [Manipulating Multimodal Agents via Cross-Modal Prompt Injection](https://mlsanity.com/paper/2504.14348/) (2025)
- [BadRobot: Jailbreaking Embodied LLM Agents in the Physical World](https://mlsanity.com/paper/2407.20242/) (2024)
- [Pre-trained Trojan Attacks for Visual Recognition](https://mlsanity.com/paper/2312.15172/) (2023)
- [RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints](https://mlsanity.com/paper/2503.16408/) (2025)
- [ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Prediction](https://mlsanity.com/paper/2508.00500/) (2025)
- [Easier Said Than Done: Unpacking Intent-Behavior Gap in Jailbreaking LLM-Based Robots](https://mlsanity.com/paper/2412.16633/) (2024)
- [Multi-Modal Grounded Planning and Efficient Replanning For Learning Embodied Agents with A Few Examples](https://mlsanity.com/paper/2412.17288/) (2024)

## Built on by (most cited first, 14 of 14)

- [From Question Answering to Task Completion: A Survey on Agent System and Harness Design](https://mlsanity.com/paper/2606.20683/) (2026)
- [Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses](https://mlsanity.com/paper/2605.02900/) (2026)
- [HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task](https://mlsanity.com/paper/2603.14367/) (2026)
- [Pre-VLA: Preemptive Runtime Verification for Reliable Vision-Language-Action and World-Model Rollouts](https://mlsanity.com/paper/2605.22446/) (2026)
- [Tex3D: Objects as Attack Surfaces via Adversarial 3D Textures for Vision-Language-Action Models](https://mlsanity.com/paper/2604.01618/) (2026)
- [LabGuard: Grounding Natural-Language Laboratory Rules into Runtime Guards for Embodied Laboratory Agents](https://mlsanity.com/paper/2606.31045/) (2026)
- [Position: A Three-Layer Probabilistic Assume-Guarantee Architecture Is Structurally Required for Safe LLM Agent Deployment](https://mlsanity.com/paper/2605.18672/) (2026)
- [Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulation](https://mlsanity.com/paper/2606.05660/) (2026)
- [Self-Evolving Just-In-Time Memory for Proactive Embodied Safety](https://mlsanity.com/paper/2607.16247/) (2026)
- [Device Context Protocol: A Compact, Safety-First Architecture for LLM-Driven Control of Constrained Devices](https://mlsanity.com/paper/2605.26159/) (2026)
- [Security of Foundation-Model-Powered Embodied Agents: Attack Surfaces, Attacks, Defenses, and Evaluation](https://mlsanity.com/paper/2608.16843/) (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)
- [Benchmarking Jailbreak Guardrails for Embodied Agents](https://mlsanity.com/paper/2610.06122/) (2026)

## Abstract (arXiv)

Embodied agents powered by vision-language models (VLMs) are increasingly capable of executing complex real-world tasks, yet they remain vulnerable to hazardous instructions that may trigger unsafe behaviors. Runtime safety guardrails, which intercept hazardous actions during task execution, offer a promising solution due to their flexibility. However, existing defenses often rely on static rule filters or prompt-level control, which struggle to address implicit risks arising in dynamic, temporally dependent, and context-rich environments. To address this, we propose RoboSafe, a hybrid reasoning runtime safeguard for embodied agents through executable predicate-based safety logic. RoboSafe integrates two complementary reasoning processes on a Hybrid Long-Short Safety Memory. We first propose a Backward Reflective Reasoning module that continuously revisits recent trajectories in short-term memory to infer temporal safety predicates and proactively triggers replanning when violations are detected. We then propose a Forward Predictive Reasoning module that anticipates upcoming risks by generating context-aware safety predicates from the long-term safety memory and the agent's multimodal observations. Together, these components form an adaptive, verifiable safety logic that is both interpretable and executable as code. Extensive experiments across multiple agents demonstrate that RoboSafe substantially reduces hazardous actions (-36.8% risk occurrence) compared with leading baselines, while maintaining near-original task performance. Real-world evaluations on physical robotic arms further confirm its practicality. Code will be released upon acceptance.