Pinned Loading

1. cost-aware-hybrid-router cost-aware-hybrid-router Public

   Cost-aware hybrid router for multi-agent LLM systems: keyword → embedding → LLM cascade. Matches LLM-only accuracy (82.6% vs 82.9%, McNemar p>0.3) with 74% fewer LLM calls on CLINC150.

   Python 2

2. tau-bench-decomposition tau-bench-decomposition Public

   Cheap Decomposition, Expensive Execution: cost-aware task decomposition for LLM agents on τ-bench

   Python 1

3. tinyrouter tinyrouter Public

   Fine-tuning a small encoder for cost-aware LLM routing on CLINC150: sample efficiency, calibration, and LLM fallback.

   Python