LLM routers across 21 methods on 5 benchmarks converge to similar accuracy below oracle due to learning global performance trends rather than fine-grained query signals.
Generalized Correctness Mod- els: Learning Calibrated and Model-Agnostic Correctness Predictors from Historical Patterns.arXiv preprint arXiv:2509.24988, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Routing Plateau: Understanding and Breaking the Accuracy Limits of LLM Routers
LLM routers across 21 methods on 5 benchmarks converge to similar accuracy below oracle due to learning global performance trends rather than fine-grained query signals.