Pandora's AI Model Routing Box通过低成本估计值优化查询分配，在多领域实验中表现优异，值得关注。
Pandora's AI Model Routing Box提出了一种高效的路由策略，通过低成本估计值来优化异构AI系统的查询分配。该策略在三个领域进行了实验，包括多LLM基准、检索增强专家和可变推理时间的LLM，结果显示其路由质量与全面估计相当，但查询昂贵估计器的频率更低。在去中心化设置中，当竞争估计准确时，信息价值推理提高了分配效率；然而，当竞争估计有噪声时，它可能会增加战略专家的效用，却以牺牲他人为代价。
Heterogeneous AI systems composed of multiple models, architectures, harnesses, or inference-time settings can improve quality and efficiency by routing queries to the specialist who can answer most effectively at the lowest cost. Routing requires estimating each specialist's expected return, but this value estimation has a cost. Cheap estimators (e.g., embedding-based predictors) are fast but noisy, while accurate estimators (e.g., fine-tuned models with access to retrieval results or partial reasoning traces) are expensive. We formalize this tradeoff as an instance of Pandora's Box, the classical problem of optimal search with costly inspection. Under a Gaussian signal model, the resulting policies have closed-form value-of-information expressions that determine, for each specialist and input, whether refining the value estimate is worth its cost. We call the centralized policy Pandora's Router. We extend this to a decentralized setting, Pandora's Bidder, where specialists independently decide whether to invest in self-assessment before accepting an offered price to claim a query. Experiments across three domains---a standard multi-LLM benchmark, retrieval-augmented specialists, and LLMs with variable inference-time reasoning---show that Pandora's Router matches the routing quality of exhaustive estimation, while querying the expensive estimator far less often. In the decentralized setting, value-of-information reasoning improves allocative efficiency when competing estimates are accurate; when competing estimates are noisy, however, it can increase the strategic specialist's utility at the expense of others.