← 研踪 PaperTrailarXiv:2611.11438 · v1
When Coding Agents Get Arms: Safety Risks Across the Digital-Physical Boundary
首次提交 2026-11-08 23:02
版本更新 2026-11-08 23:02
雷达观测 2026-11-10 12:16
摘要
Advances in spatial understanding have enabled frontier models to power coding agents that control a real robot arm zero-shot and end-to-end, without task-specific demonstrations or retraining. This brings two new safety challenges. First, the extensive knowledge of frontier models lets these agents perform tasks that earlier VLA and WAM paradigms could not, opening the door to new forms of capability misuse. Second, coding agents can access digital resources such as web pages and emails. Threats in these resources, such as indirect prompt injection, can carry over into the physical world when the agent controls a robot. We therefore introduce ArmedAgent, the first systematic benchmark to evaluate both risks for coding agents performing zero-shot robot control. It covers robustness, malicious use, and indirect injection across 36 tasks in 5 scenarios, evaluated in simulation and validated on a physical robot arm. A distinctive portion of the tasks target harmful behaviors that earlier VLA paradigms could not perform. Testing several frontier models, including GPT-6-Astra, under widely used agent frameworks, we find substantial safety risks in current systems.
作者备注：Technical report, work in progress
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-08 23:02 · 最新观测版本
When Coding Agents Get Arms: Safety Risks Across the Digital-Physical Boundary
Advances in spatial understanding have enabled frontier models to power coding agents that control a real robot arm zero-shot and end-to-end, without task-specific demonstrations or retraining. This brings two new safety challenges. First, the extensive knowledge of frontier models lets these agents perform tasks that earlier VLA and WAM paradigms could not, opening the door to new forms of capability misuse. Second, coding agents can access digital resources such as web pages and emails. Threats in these resources, such as indirect prompt injection, can carry over into the physical world when the agent controls a robot. We therefore introduce ArmedAgent, the first systematic benchmark to evaluate both risks for coding agents performing zero-shot robot control. It covers robustness, malicious use, and indirect injection across 36 tasks in 5 scenarios, evaluated in simulation and validated on a physical robot arm. A distinctive portion of the tasks target harmful behaviors that earlier VLA paradigms could not perform. Testing several frontier models, including GPT-6-Astra, under widely used agent frameworks, we find substantial safety risks in current systems.
查看此版本解读 →查看此版本原文 ↗