RoboRisk 基准与 LEASH 安全框架：给机器人智能体加上安全闸门
LEASH: Stay Safe in Agentic Robotics
让 GPT-6、Claude Opus 5.5 这些模型去真控制机器人，危害率都不低。这篇论文给了一套能直接套在现有架构上的三层闸门方案，任务照做、危险操作被拦，做具身智能和机器人方向的开发者值得看测试细节。
研究者发布 RoboRisk 基准，包含 92 个仿真任务和 13 个物理机器人任务，覆盖任务拒绝、计划修复、执行期危险、注入攻击、顺序记忆五类风险场景，此前同类基准最多只覆盖两类。
论文评测了 GPT-6 Astra、GPT-6.1 Sol、GPT-6 Luna、Claude Opus 5.5、Gemini 4 Argon、Grok 4.7 六个基础模型，以及 Dream API 和 PokeBot 的 RoboAPI 两个机器人专用 API，结果显示这些模型普遍存在较高危害率。
作者随后提出 LEASH 安全框架，用决策模型（Jev 或 OpenAI 的 Decisions API）在任务、动作、不可逆操作三个层级设置审查闸门，规划器与闸门共享同一套安全策略。实验表明 LEASH 能降低全部六个模型的危害率，同时基本保留任务完成度，时间与 token 开销很小，且可接入几乎任意智能体架构。
LEASH: Stay Safe in Agentic Robotics
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.
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include LEASH, RoboRisk, Claude, GPT-6.
Primary source verification: published directly by arXiv: OpenAI with first-party authority. Cross-source corroboration: 11 independent sources have covered this development (including TestingCatalog, kimmonismus, 宝玉), confirming industry-wide signal strength.