cognitive-behaviors

Tag

Cards List
#cognitive-behaviors

Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs

arXiv cs.AI · 2026-06-02 Cached

Introduces Latent Reward Steering (Lrs), an adaptive inference-time framework that uses sparse autoencoder latent states and a learned reward model to implicitly promote cognitive behaviors like verification and backtracking in reasoning LLMs, improving performance across multiple models and benchmarks.

0 favorites 0 likes
← Back to home

Submit Feedback