稳定报道时间 2026-10-02 12:00
Sapien:一种用于自主人工智能代理的状态ful策略引擎
Sapien 是一个新的策略引擎,用于对 AI 代理实施有状态的上下文策略,从而在多步骤任务中实现更加动态和灵活的安全防御。
Sapien 是一个新的策略引擎,用于对 AI 代理实施有状态的上下文策略,从而在多步骤任务中实现更加动态和灵活的安全防御。
> Abstract: Contextual security defenses prevent AI agents from taking rogue actions by synthesizing a task-specific policy and enforcing it on the agent's tool calls.
Abstract: Contextual security defenses prevent AI agents from taking rogue actions by synthesizing a task-specific policy and enforcing it on the agent's tool calls. In multi-step tasks, however, which actions are valid often depends on what the agent has already done and learned. We present Sapien, a policy engine for enforcing stateful contextual policies.