Tag
Releasing a methodology for evaluating model routing with interactive benchmarks that achieve Pareto-dominance over leading benchmarks, offering higher quality at lower cost.
This paper proposes a prompt-based uncertainty decomposition method for LLM agents that separates action confidence from request uncertainty, enabling proactive clarification seeking in underspecified tasks. The method is evaluated on new clarification-augmented benchmarks across five LLM backbones, showing significant improvements.