收录解读
工具调用前的运行时门控能否提供安全保证,取决于策略状态的可表达性、裁判可见信息以及阻断是否改变后续行为。
论文分别刻画固定oracle下的可执行策略、外生分布下的误阻断-漏检前沿与共形证书,以及内生闭环下的occupancy规划,并给出不可判定性与PSPACE边界。
在AgentDojo 949回合闭环重跑中,强门控把攻击成功从45/949降至4/949(p=2.2×10^-9),同时揭示78%阻断率的安全-效用代价。
形式理论与闭环实证共同重构了运行时安全保证的边界,但结论依赖明确模型假设且部署代价较高,因此定为disruptive而非paradigm。
原始摘要
Runtime guardrails act before irreversible tool calls, but their guarantees depend on what policy state is representable, what a judge observes, and whether intervention changes future behavior. We separate three questions. First, relative to fixed oracle predicates, a deterministic gate enforces exactly the nonempty safety policies whose good prefixes its register model recognizes; policy nontriviality is undecidable with two decrementable counters but in PSPACE for a separable monotone fragment. Second, under a fixed exogenous law, Neyman-Pearson gives the exact false-block/miss frontier and conformal calibration gives a finite-sample marginal certificate, possibly via block-all. Third, once blocking changes future proposals, static scores and ungated trajectories need not identify the closed-loop frontier; a specified finite controlled model instead yields an occupancy program. Bounded representation attacks add a robustness margin, so benign calibration alone does not transfer. Experiments target these distinctions through static diagnostics, controlled-model enumeration, representation rewrites, and paired closed-loop reruns.