HM-ROUTER：面向智能体系统的联合模型与框架路由
HM-ROUTER: Joint Model and Harness Routing for Agentic Systems
浏览论文内容
中文总结 AI 辅助
提出HM-Router，联合选择模型与框架的路由方法，利用CP分解交互项处理未观测组合，在12个基准上平均路由准确率提升7.3个百分点，并具样本效率和泛化能力。
中文摘要 AI 辅助
智能体性能取决于底层模型以及管理其工具使用和执行的框架。选择合适的模型与框架组合需要考虑它们的兼容性，然而训练样本可能仅覆盖不断增长的组合空间的一个子集。我们提出HM-Router，一种为每个查询联合选择模型和框架的路由方法。它学习跨路由共享的独立模型和框架表示，并引入受典型多路（CP）张量分解启发的交互项，以捕捉兼容性如何随查询变化。这种共享机制使得来自已观测对的训练样本能够为未观测组合的预测提供信息。我们从12个公开智能体基准中整理了一个基准，涵盖293条路由、73个模型和25个框架。HM-Router在平均路由准确率上超过最强评估的已学习基线7.3个百分点，并在六个基准子集上的所有七个评估成本预算中均领先。当90%的路由的训练结果被扣留时，允许未观测组合比将同一路由器限制在已观测路由上，在归一化准确率上提升了15.8个百分点。HM-Router还展示了针对新路由和组件的训练样本效率，以及对未见基准的泛化能力。我们的代码和数据已在以下网址开源：此https URL。
英文摘要
Agent performance depends on both the underlying model and the harness that manages its tool use and execution. Selecting a suitable pair requires accounting for their compatibility, yet training samples may cover only a subset of the growing combination space. We introduce HM-Router, a routing method that jointly selects a model and harness for each query. It learns separate model and harness representations shared across routes, with an interaction term inspired by canonical polyadic (CP) tensor decomposition to capture how their compatibility varies with the query. This sharing allows training samples from observed pairs to inform predictions for unobserved combinations. We curate a benchmark from 12 public agent benchmarks, covering 293 routes, 73 models, and 25 harnesses. HM-Router exceeds the strongest evaluated learned baseline by 7.3 percentage points in mean routing accuracy and leads at all seven evaluated cost budgets on the six-benchmark subset. When 90% of routes have their training outcomes withheld, allowing unobserved combinations improves normalized accuracy by 15.8 points over restricting the same router to observed routes. HM-Router has also demonstrated training sample efficiency for new routes and components and generalization to unseen benchmarks. Our code and data are open-sourced at https://github.com/hmarkc/HM-Router.
