RouteGuard：当互补性不足时，对LLM多智能体系统中的路由增益进行认证

中文摘要 AI 辅助

多智能体LLM系统在由模型支持的顾问之间进行路由，但部署者在部署前很少知道路由是否真的有帮助。主流路由方法优化门控的AUC，并假设顾问的互补性足以保证路由有效。我们证明这两个假设都不能决定可部署的增益。我们引入了RouteGuard，一个部署认证框架。路由增益可分解为G = πΔ_E，可实现的增益由条件遗憾泛函Φ决定，而非AUC。有限样本认证区间带有匹配的Le Cam下界，在固定活动类上具有恒定尖锐度，且存在鲁棒性相变。在两个基准测试中，该框架起到了护栏作用：在RouterBench（11个跨系列模型）上，结果取决于采样单元：在提示级采样下，协议认证了优于GPT-4的增益，而在工作负载集群重采样下则拒绝认证，因为增益取决于86个工作负载单元中的3个；在OpenRCA（三个Gemini顾问）上，顾问在统计上是冗余的：在我们测试的所有池（221个RouterBench池和三个OpenRCA分布）中，实现的神谕性能等于或低于独立性基线，因此协议正确拒绝认证。一个预先注册的半合成对照验证了校准：当m≥m*时，协议认证真正的增益，而不会认证真实的空情况。代码和冻结的工件将在发布版本中发布。

英文摘要

Multi-agent LLM systems route among model-backed advisors, yet a deployer rarely knows before shipping whether routing will help at all. Prevailing routers optimize a gate's AUC and presume that advisor complementarity suffices. We show that neither determines the deployable gain. We introduce RouteGuard, a deployment-certification framework. Routing gain decomposes as $G = πΔ_E$, and the achievable gain is governed by a conditional-regret functional $Φ$, not by AUC. A finite-sample certification bracket comes with a matching Le Cam lower bound, constant-sharp over the fixed-activity class, and a robustness phase transition. On two benchmarks the framework acts as a guardrail. On RouterBench (11 cross-family models) the verdict depends on the sampling unit: the protocol certifies a gain over GPT-4 under prompt-level sampling and withholds it under workload-cluster resampling, because the gain rests on 3 of 86 workload cells. On OpenRCA (three Gemini advisors) the advisors are statistically redundant: the realized oracle sits at or below the independence baseline in all pools we tested (221 RouterBench pools and three OpenRCA distributions), so the protocol correctly refuses to certify. A pre-registered semi-synthetic control confirms calibration: the protocol certifies a genuine gain once $m \ge m^\star$ and does not certify a true null. Code and frozen artifacts will be released with the published version.

发表机构

• University of Miami（迈阿密大学）
• Google（谷歌公司）

机构由 AI 辅助整理，请以论文原文为准。