English

RISER: Orchestrating Latent Reasoning Skills for Adaptive Activation Steering

Artificial Intelligence 2026-01-21 v2

Abstract

Recent work on domain-specific reasoning with large language models (LLMs) often relies on training-intensive approaches that require parameter updates. While activation steering has emerged as a parameter efficient alternative, existing methods apply static, manual interventions that fail to adapt to the dynamic nature of complex reasoning. To address this limitation, we propose RISER (Router-based Intervention for Steerable Enhancement of Reasoning), a plug-and-play intervention framework that adaptively steers LLM reasoning in activation space. RISER constructs a library of reusable reasoning vectors and employs a lightweight Router to dynamically compose them for each input. The Router is optimized via reinforcement learning under task-level rewards, activating latent cognitive primitives in an emergent and compositional manner. Across seven diverse benchmarks, RISER yields 3.4-6.5% average zero-shot accuracy improvements over the base model while surpassing CoT-style reasoning with 2-3x higher token efficiency and robust accuracy gains. Further analysis shows that RISER autonomously combines multiple vectors into interpretable, precise control strategies, pointing toward more controllable and efficient LLM reasoning.

Keywords

Cite

@article{arxiv.2601.09269,
  title  = {RISER: Orchestrating Latent Reasoning Skills for Adaptive Activation Steering},
  author = {Wencheng Ye and Xiaoyang Yuan and Yi Bin and Pengpeng Zeng and Hengyu Jin and Liang Peng and Heng Tao Shen},
  journal= {arXiv preprint arXiv:2601.09269},
  year   = {2026}
}