routebench-e32dd30e·1 events·first seen Aliases: ROUTEBENCH
Researchers introduce ROUTEBENCH, a diagnostic benchmark testing whether transformers can implicitly route between inductive-bias families (ridge-like, lasso-like, Huber-like, kNN-like) based on the latent data-generating regime, without changing prompt form. Dense decoder-only transformers trained from scratch at 44M–612M parameters show strong routing behavior, with a 306M model closing 80.9% of the oracle-routing gap and achieving route F1 of 84.1. Activation patching and probe controls confirm that route-relevant internal directions are decodable and functionally involved in output behavior. The results provide controlled mechanistic evidence for latent algorithm routing but explicitly do not generalize claims to pretrained LLMs or open-ended reasoning.