Learning to Decide, Not to Reason: Parameter-Efficient Decision Operators via Low-Rank Activation Steering
arXiv:2610.06950v1 Announce Type: new Abstract: Injecting skills into a frozen language model currently costs a million parameters and a reinforcement-learning pipeline. We introduce \method{}, a System-1 decision operator trained by behavior cloning that lowers this cost by roughly two orders of m…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-07 04:00 · arXiv cs.LG
Learning to Decide, Not to Reason: Parameter-Efficient Decision Operators via Low-Rank Activation Steering