RISER: Orchestrating Latent Reasoning Skills for Adaptive Activation Steering

• URL: http://arxiv.org/abs/2601.09269v2
• Date: Mon, 19 Jan 2026 13:00:42 GMT
• Title: RISER: Orchestrating Latent Reasoning Skills for Adaptive Activation Steering
• Authors: Wencheng Ye, Xiaoyang Yuan, Yi Bin, Pengpeng Zeng, Hengyu Jin, Liang Peng, Heng Tao Shen,
• Abstract summary: We propose a plug-and-play intervention framework that adaptively steers large language models (LLMs) reasoning in activation space.<n>RISER constructs a library of reusable reasoning vectors and employs a lightweight Router to dynamically compose them for each input.<n>The Router is optimized via reinforcement learning under task-level rewards, activating latent cognitive primitives in an emergent and compositional manner.
• Score: 62.63376387138257
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs [42.13334813565475]
  STEER2ADAPT is a framework that adapts large language models (LLMs) by composing steering vectors rather than learning new ones from scratch.<n> Experiments across 9 tasks and 3 models in both reasoning and safety domains demonstrate the effectiveness of STEER2ADAPT, achieving an average improvement of 8.2%.
  arXiv  Detail & Related papers  (2026-02-07T00:00:50Z)
• Internalizing LLM Reasoning via Discovery and Replay of Latent Actions [4.830503861275364]
  Internalization of chain-of-thought processes into hidden states has emerged as a highly efficient paradigm for scaling test-time compute.<n>We propose STIR (Self-Distilled Tools for Internal Reasoning), a framework that reformulates reasoning enhancement as a dynamic latent trajectory control problem.
  arXiv  Detail & Related papers  (2026-02-04T08:44:57Z)
• Structured Uncertainty guided Clarification for LLM Agents [126.26213027785813]
  LLM agents extend large language models with tool-calling capabilities, but ambiguous user instructions often lead to incorrect invocations and task failures.<n>We introduce a principled formulation of structured uncertainty over tool-call parameters, modeling joint tool-argument clarification as a POMDP with Expected Value of Perfect Information (EVPI) objective for optimal question selection and aspect-based cost modeling to prevent redundancy.<n>Our SAGE-Agent leverages this structured uncertainty to achieve superior efficiency: increasing coverage on ambiguous tasks by 7-39% while reducing clarification questions by 1.5-2.7$times$ compared to strong prompting and uncertainty-based baselines.
  arXiv  Detail & Related papers  (2025-11-11T21:50:44Z)
• SEQR: Secure and Efficient QR-based LoRA Routing [53.52716967527183]
  Low-Rank Adaptation (LoRA) has become a standard technique for parameter-efficient fine-tuning of large language models.<n> Efficiently selecting the correct LoRA adapter for a given input remains a challenge.<n>We introduce SEQR, an unsupervised LoRA routing algorithm designed to maximize efficiency while providing strict routing guarantees.
  arXiv  Detail & Related papers  (2025-09-22T17:59:38Z)
• RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory [57.449129198822476]
  RCR is a role-aware context routing framework for multi-agent large language model (LLM) systems.<n>It dynamically selects semantically relevant memory subsets for each agent based on its role and task stage.<n>A lightweight scoring policy guides memory selection, and agent outputs are integrated into a shared memory store.
  arXiv  Detail & Related papers  (2025-08-06T21:59:34Z)
• Agentic Reinforced Policy Optimization [66.96989268893932]
  Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-26T07:53:11Z)
• Direct Reasoning Optimization: LLMs Can Reward And Refine Their Own Reasoning for Open-Ended Tasks [6.881699020319577]
  We propose Direct Reasoning Optimization (DRO), a reinforcement learning framework for fine-tuning Large Language Models (LLMs)<n>DRO is guided by a new reward signal: the Reasoning Reflection Reward (R3)<n>DRO consistently outperforms strong baselines while remaining broadly applicable across both open-ended and structured domains.
  arXiv  Detail & Related papers  (2025-06-16T10:43:38Z)
• Route-and-Reason: Scaling Large Language Model Reasoning with Reinforced Model Router [9.580226379350737]
  Multi-step reasoning has proven essential for enhancing the problem-solving capabilities of Large Language Models.<n>Yet, many reasoning steps are relatively simple and can be handled by more efficient smaller-scale language models.<n>We propose R2-Reasoner, a novel framework that enables collaborative reasoning across heterogeneous LLMs.
  arXiv  Detail & Related papers  (2025-06-06T09:18:56Z)
• ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding [71.654781631463]
  ReAgent-V is a novel agentic video understanding framework.<n>It integrates efficient frame selection with real-time reward generation during inference.<n>Extensive experiments on 12 datasets demonstrate significant gains in generalization and reasoning.
  arXiv  Detail & Related papers  (2025-06-02T04:23:21Z)
• Patterns and Mechanisms of Contrastive Activation Engineering [0.374490703387131]
  CAE has the potential to introduce a new paradigm of flexible, task-specific behavior tuning.<n>We analyze the performance of CAE in in in-distribution, out-of-distribution settings, evaluate drawbacks, and begin to develop comprehensive guidelines for its effective deployment.
  arXiv  Detail & Related papers  (2025-05-06T05:15:12Z)
• C-LoRA: Continual Low-Rank Adaptation for Pre-trained Models [26.560293264523903]
  Low-Rank Adaptation (LoRA) is an efficient fine-tuning method that has been extensively applied in areas such as natural language processing and computer vision.<n>We propose Continual Low-Rank Adaptation (C-LoRA), a novel extension of LoRA for continual learning.<n>C-LoRA uses a learnable routing matrix to dynamically manage parameter updates across tasks.
  arXiv  Detail & Related papers  (2025-02-25T07:35:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.