Research

Learning to Decide, Not to Reason: Parameter-Efficient Decision Operators via Low-Rank Activation Steering

Single source1 source7 Oct 2026

arXiv:2610.06950v2 Announce Type: replace-cross Abstract: Injecting skills into a frozen language model currently costs a million parameters and a reinforcement-learning pipeline.

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2610.06950

← Back to all developments · Signals are a development reported by more than one source. See the methodology.