determinantal-point-processes

FlexRouter 提出一种显式建模模型互补性的 LLM 路由框架，将路由建模为基于覆盖的子集选择问题，并用 Determinantal Point Processes 对模型能力与冗余进行联合建模，同时通过边缘化失败集合的目标函数直接优化答案覆盖率。在 RouterEval 基准上，该方法在域内与域外任务上以更低冗余实现了更高的覆盖率，且推理成本灵活可控。

FlexRouter proposes a coverage-oriented LLM routing framework that uses Determinantal Point Processes to model complementarity among models, maximizing the probability that at least one selected model answers correctly while avoiding redundant selections and fixed budgets.