Year: 2026
Type: conference-paper
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 parameterefficient 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 plugand-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 2-3× higher token efficiency and robust accuracy gains.Further analysis shows that RISER can autonomously combine multiple vectors into interpretable, precise control strategies, paving way for more controllable and efficient LLM reasoning.
Institutions: Tongji University, Tencent (China)
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Awards: G723731210, G7336938272
OpenAlex ID: W7166871280