When Coding Agents Get Arms: Safety Risks Across the Digital-Physical Boundary
cs.RO, cs.CR, cs.MM
Submitted: 2026-11-08
Updated: 2026-11-08
Code: https://github.com/huggingface/lerobot
Project page: https://ymsun2020.github.io/CodingAgentEmbodiedSafety
Terminology
Sources
- Scaling Online Exploration for Robot Agents
- VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models
- IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks
- Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning
- Jailbreaking LLM-Controlled Robots
- Has GPT-6-Astra Achieved Embodied Intelligence?
- Refuses in Chat, Complies with Arms: LLM Refusal Does Not Survive Robot Control
- World Action Models are Zero-shot Policies
- SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents
- BadRobot: Jailbreaking Embodied LLM Agents in the Physical World
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation