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

The authors introduce Latent Reward Steering, an inference-time framework designed to improve reasoning in large language models by dynamically adjusting cognitive behaviors.

Firefly links to the original publisher. The summary above is AI-generated for orientation and may differ from the source. The “current rank score” decays over time so newer significant stories surface first.