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

Large language models can be steered at inference time through prompting or activation interventions, but activation steering methods often underperform compared to prompt-based approaches. We propose a framework that formulates prompt steering as a form of activation steering and investigates whether distilling successful prompt steering behavior into simpler, interpretable models can close this gap. Our analysis reveals that popular activation steering methods are not faithful to the mechanics of prompt steering, which applies strong interventions on some tokens while barely affecting others. Based on these insights, we introduce Prompt Steering Replacement (PSR) models that estimate token-specific steering coefficients from the activations themselves and are trained to imitate prompt-based interventions. Experiments on three steering benchmarks across multiple language models show that PSR models outperform existing activation steering methods, especially when controlling for high-coherence completions, and also compare favorably to prompting on AxBench and persona steering.

Activation steering edits the behaviour of a frozen language model by adding a learned vector to its residual stream, and current practice fixes the injection layers globally per task. We argue that the best layers are an instance-level decision, and we make per-instance, multi-layer selection both well understood and deployable. On two open-weight 8B models and six binary persona traits, a per-instance oracle over layer subsets shows that the best layers vary from one input to the next: on most trait-model pairs, no fixed global layer set recovers the per-instance benefit. A greedy rule that ranks layers by single-layer marginal effect recovers nearly all of the oracle's benefit, but both must score candidate layers against the gold answer, so neither can run at deployment; the rule instead becomes the target a prompt-only predictor is trained to reproduce. Our deployable recipe needs no label at inference: a per-instance layer ranker read off the prompt embedding, a classifier that infers the steering direction, and an adaptive gate that scores short steered passes against that inferred direction and steers no more layers than necessary. The recipe recovers most of the oracle's lift (the bulk on the stronger model, a clear majority on the harder one), never drives any trait-model pair below its unsteered alignment baseline on average, and largely avoids the fluency collapse that strong global selection incurs at higher layer counts. A mechanistic account, "direction over magnitude", explains the behavioural flip under a mis-directed global set, the output collapse from steering too many layers, and the ceiling of unsteerable inputs.

Task knowledge is commonly stored either as text in the prompt or as an update to model weights. Text is modular but must be interpreted on every use, while weight adaptation makes the resulting capability difficult to load, remove, or share independently. We introduce KV-Skill, a design space of external factorized operators that a frozen language model reads through a lightweight interface. KV-Skill supports two complementary paths. Registration converts an authored text skill into a text-derived operator and trains a shared per-backbone interface. Reward learning develops a compact latent operator directly from task outcomes, with or without an authored skill. Neither path adds positions to the prompt. Across ten benchmarks and four backbones from three model families, converting text to a KV-Skill consistently makes the same procedural knowledge more effective. On Qwen3.5-4B LiveMath, registration reaches 77.2 accuracy, compared with 23.4 for the source text skill, 52.0 for SkillOpt, and 64.5 for SoftSkill. Under matched reward training and parameter budgets, KV-Skill gives the best result in seven of eight matched settings against soft prefixes, prefix tuning, and LoRA. A post-hoc rank analysis further shows that text-derived operators retain nearly all of their benefit with one task-aligned direction per injection layer, while matched random directions fail. Finally, one shared interface retains three independently loadable KV-Skills without measurable forgetting. These results show that task knowledge can be acquired from text or experience, compressed into an external operator, and deployed separately from the backbone. Code is available at: https://github.com/shawnzhg/KV-Skill