# Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulation

arXiv: https://arxiv.org/abs/2606.05660 · HTML: https://mlsanity.com/paper/2606.05660/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 87 of its 310 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Builds on (most cited first, 30 of 87)

- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [Safe Exploration in Continuous Action Spaces](https://mlsanity.com/paper/1801.08757/) (2018)
- [Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations](https://mlsanity.com/paper/2411.10414/) (2024)
- [SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents](https://mlsanity.com/paper/2412.13178/) (2024)
- [GRAPE: Generalizing Robot Policy via Preference Alignment](https://mlsanity.com/paper/2411.19309/) (2024)
- [Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis](https://mlsanity.com/paper/2312.08782/) (2023)
- [Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and Progress](https://mlsanity.com/paper/2410.04640/) (2024)
- [MEM: Multi-Scale Embodied Memory for Vision Language Action Models](https://mlsanity.com/paper/2603.03596/) (2026)
- [Errors are Useful Prompts: Instruction Guided Task Programming with Verifier-Assisted Iterative Prompting](https://mlsanity.com/paper/2303.14100/) (2023)
- [Guidance on the Assurance of Machine Learning in Autonomous Systems (AMLAS)](https://mlsanity.com/paper/2102.01564/) (2021)
- [SARM: Stage-Aware Reward Modeling for Long Horizon Robot Manipulation](https://mlsanity.com/paper/2509.25358/) (2025)
- [RePLan: Robotic Replanning with Perception and Language Models](https://mlsanity.com/paper/2401.04157/) (2024)
- [RoboFAC: A Comprehensive Framework for Robotic Failure Analysis and Correction](https://mlsanity.com/paper/2505.12224/) (2025)
- [Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback](https://mlsanity.com/paper/2412.15838/) (2024)
- [AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions](https://mlsanity.com/paper/2506.14697/) (2025)
- [FailSafe: Reasoning and Recovery from Failures in Vision-Language-Action Models](https://mlsanity.com/paper/2510.01642/) (2025)
- [ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Context](https://mlsanity.com/paper/2510.04246/) (2025)
- [VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer](https://mlsanity.com/paper/2512.11891/) (2025)
- [HallE-Control: Controlling Object Hallucination in Large Multimodal Models](https://mlsanity.com/paper/2310.01779/) (2023)
- [RoboEval: Where Robotic Manipulation Meets Structured and Scalable Evaluation](https://mlsanity.com/paper/2507.00435/) (2025)
- [BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation](https://mlsanity.com/paper/2602.09849/) (2026)
- [EARBench: Towards Evaluating Physical Risk Awareness for Task Planning of Foundation Model-based Embodied AI Agents](https://mlsanity.com/paper/2408.04449/) (2024)
- [Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification](https://mlsanity.com/paper/2510.16281/) (2025)
- [ForceVLA2: Unleashing Hybrid Force-Position Control with Force Awareness for Contact-Rich Manipulation](https://mlsanity.com/paper/2603.15169/) (2026)
- [RoboHorizon: An LLM-Assisted Multi-View World Model for Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2501.06605/) (2025)
- [Tactile-VLA: Unlocking Vision-Language-Action Model's Physical Knowledge for Tactile Generalization](https://mlsanity.com/paper/2507.09160/) (2025)
- [DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models](https://mlsanity.com/paper/2511.15669/) (2025)
- [LoHoRavens: A Long-Horizon Language-Conditioned Benchmark for Robotic Tabletop Manipulation](https://mlsanity.com/paper/2310.12020/) (2023)

## Built on by (most cited first, 1 of 1)

- [Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levels](https://mlsanity.com/paper/2607.26121/) (2026)

## Abstract (arXiv)

Embodied AI systems are increasingly expected to reason and act over extended horizons in physical environments. This growing capability brings safety to the foreground, because failures in the physical world can harm people, damage objects, and disrupt workplaces. Although safe embodied AI has attracted substantial attention, the literature remains fragmented across planning, policy design, and runtime execution. Long-horizon robotic manipulation is a particularly revealing anchor domain for this problem because semantic misgrounding, subtask-level error propagation, execution drift, and contact-rich physical risk can accumulate within the same closed-loop system. This survey therefore provides a structured review of safety in long-horizon robotic manipulation from an embodied AI perspective. We organize the literature by intervention locus, covering planning-time, policy-time, and execution-time safety, and we analyze the strength of the evidence that each line of work provides, distinguishing formal guarantees, statistical support, and empirical safety heuristics. This framework clarifies the distinct roles of backbone capability papers, direct safety mechanisms, and benchmark or evaluation studies, while exposing where current safety claims are well supported and where they remain indirect. We identify persistent gaps, including limited evidence for policy-time safety, weak formal support for contact-rich long-horizon manipulation, immature uncertainty-triggered intervention, and a shortage of manipulation-specific safety benchmarks. We conclude by outlining research directions for cross-layer assurance, evaluation design, and safer deployment of long-horizon robotic agents in real-world settings.