cs.RONov 10, 2026

LEASH: Stay Safe in Agentic Robotics

Authors: Qinfeng Zhu, Weiguang Zhao, Ke Sun, Xihao Guo, Yunxi Jiang, Rui Zhang, Lei Fan, Kaizhu Huang

Organizations: Xi’an Jiaotong-Liverpool University · Duke Kunshan University · University of Liverpool · National University of Singapore · 

Abstract

Foundation models such as GPT and Claude have shown strong capabilities in spatial understanding and embodied intelligence. These advances make agentic robotics a promising path toward artificial general intelligence in robotics. However, we find that using foundation models to control robots poses serious safety risks, and comprehensive safety evaluation is still lacking. We introduce RoboRisk, a comprehensive benchmark for evaluating safety in agentic robotics. Its 92 simulated tasks and 13 physical-robot tasks fall into five categories: Task-level Refusal (T), Plan Repair (P), Execution-time Hazard (E), Injection (I), and Sequential Memory (S). Prior benchmarks cover at most two of these categories, and several evaluate only text outputs. In contrast, RoboRisk covers all five and executes every task in closed loop. We evaluate six state-of-the-art foundation models on RoboRisk: GPT-6 Astra, GPT-6.1 Sol, GPT-6 Luna, Claude Opus 5.5, Gemini 4 Argon, and Grok 4.7. These models generally show high harm rates. We also evaluate two robot-specific APIs: the Dream API and PokeBot's RoboAPI. We further propose the Lease-Enforced Agentic Safety Harness (LEASH), which offers essential safety infrastructure for agentic robotics and can be integrated into nearly any agentic architecture. LEASH leverages a decision model (Jev or OpenAI's Decisions API) to implement task, action, and commit gates, which review the task, each action, and each irreversible operation in their visual context. The planner and all three gates share a common safety policy. Experiments on RoboRisk in simulation and on physical robots show that LEASH effectively reduces harm across all six foundation models. It largely preserves their task completion performance and adds little time and token overhead.

Figures & tables

Explore similar work

CardsList
  1. Risky-Bench: Evaluating Agentic Safety Risks in Real-World Life-Assist Deployments

    Feb 3, 2026Jingnan Zheng, Yanzhen Luo, Jingjun Xu +8Language Model Safety EvaluationLLM Agent Safety

  2. ResponsibleRobotBench: Benchmarking Risk-Aware Task-Level Decision Making for Robotic Manipulation with Large Multimodal Models

    Dec 3, 2025Lei Zhang, Ju Dong, Kaixin Bai +5Safe Robot ManipulationRobot Manipulation Benchmarks

  3. Inspect Robots: Evaluating the Capabilities and Safety of Embodied AI

    Oct 5, 2026Christopher Leet, Achu Menon, Sravanthi Machcha +12Robot SafetyAI Agent Evaluation