Line of inquiry
Inquiring lines›How do architecture and constraint…›How do architectural decisions and…›this line of inquiry
What determines effective LLM routing across cost, quality, and governance?
A broader line of inquiry — a family of 18 specific questions the research asks around this. Follow one into its inquiring-line page, or move sideways to a related line below.
Questions in this line of inquiry 18
Specific inquiring lines the field asks around this — ordered from the most general framing down to the most specific angle.
- Which components of LLM routers actually drive performance differences?
- How much worse are convergent routing methods than theoretical oracle routing?
- Why do routers fail when only a few models have the right answer?
- How do pre-training and distillation enable minimal routing signals to work?
- Can clustering-based routing match neural network routers in cost and quality?
- What makes routing a governance mechanism rather than just a predictor?
- Why do commercial LLM routers fail to beat lightweight baselines?
- Can a router predict query complexity well but still fail as governance?
- How do KNN and prompted routers differ in the accuracy-stability tradeoff?
- How do routers decide when to escalate from small to large models?
- What learning signals best supervise router training across benchmark tasks?
- Does the improved model actually return to the routing pool and shape future decisions?
- What makes mixture-of-experts routing learn token-level specialization effectively?
- Why do KNN routers collapse when queries are paraphrased?
- Why does Branch-Train-Merge fail without learned routing between experts?
- Who serves as the teacher model in the routing-guided distillation process?
- Why does a second routing level sometimes break accuracy in disclosure hierarchies?
- How do miscalibrated confidence signals affect the success of SmartPause routing?