Steering vectors offer a training-free mechanism for controlling reasoning behaviors in large language models, but constructing effective vectors requires identifying genuine behavioral signals in the model's hidden states. For behaviors that can be toggled via prompts, this is straightforward. However, many reasoning behaviors -- such as self-reflection -- emerge spontaneously and resist prompt-level control. Current methods detect these behaviors through keyword matching in chain-of-thought traces, implicitly assuming that every detected boundary encodes a genuine behavioral signal. We show that this assumption is overwhelmingly wrong: across 541 keyword-detected boundaries, 93.3\% are behaviorally unstable, failing to reproduce the detected behavior under re-generation from the same prefix. We develop a probabilistic model that formalizes intrinsic reasoning behaviors as stochastic events with context-dependent trigger probabilities, and show that unstable boundaries dilute the steering signal. Guided by this analysis, we propose stability filtering, which retains only boundaries where the model consistently reproduces the target behavior. Combined with a content-subspace projection that removes residual question-specific noise, our method achieves 0.784 accuracy on MATH-500 (+5.0 over the strongest baseline). The resulting steering vectors transfer across models in the same architecture family without re-extraction, improving Nemotron-Research-Reasoning-1.5B (+5.0) and DeepScaleR-1.5B-Preview (+6.0). Code is available at https://github.com/zhmzm/stability-steering.
SEEK: Steering LLM Reasoning for RAG via Internal Reasoning Sketches
School of Computer Science and Engineering, Northeastern University, China(东北大学计算机科学与工程学院);Department of Computer Science and Technology, Institute for AI, Tsinghua University, China(清华大学计算机科学与技术系,人工智能研究院);School of Intelligent Science and Technology, Nanjing University, China(南京大学智能科学与技术学院)
School of Computing and Augmented Intelligence, Arizona State University(亚利桑那州立大学计算与增强智能学院);Department of Computer Science, University of California, Davis(加利福尼亚大学戴维斯分校计算机科学系)
VIS Lab, University of Amsterdam(阿姆斯特丹大学VIS实验室);FunAI Lab, University of Technology Nuremberg(纽伦堡技术大学FunAI实验室);CSAIL, Massachusetts Institute of Technology(麻省理工学院计算机科学与人工智能实验室)
Reflection Steering: Disentangling Reflection from Reasoning in Activation Space for Token-Efficient Inference
School of Computing and Data Science, The University of Hong Kong(香港大学计算与数据科学学院);Department of Computing, The Hong Kong Polytechnic University(香港理工大学计算学院);School of Data Science, Lingnan University(岭南大学数据科学学院);Centre for Learning, Teaching and Technology, The Education University of Hong Kong(香港教育大学学习、教学与技术中心)
Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs
Network Analysis and Social Influence Modelling (NASIM) Lab(网络分析与社会影响建模实验室);School of Physics Maths and Computing, The University of Western Australia(西澳大学物理数学与计算学院);School of Psychological Science, The University of Western Australia(西澳大学心理学科学学院);School of Computing, Macquarie University(麦考瑞大学计算机学院)
Improving LLM Reasoning through Interpretable Role-Playing Steering
Center for Information and Language Processing, LMU Munich(信息与语言处理中心,慕尼黑大学);Northwestern University(西北大学);Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心(MCML));New Jersey Institute of Technology(新泽西理工学院)
SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models
Northeastern University(东北大学);CAS Key Laboratory of Behavioral Science(中国科学院行为科学重点实验室);Independent Researcher(独立研究员);Kunming University of Science and Technology(昆明理工大学)
On the Limitations of Steering in Language Model Alignment
Birla Institute of Technology and Science Pilani(比拉理工科学与 Pilani 学院);National University of Singapore(新加坡国立大学);Institute for Data Science, National University of Singapore(新加坡国立大学数据科学研究院)
CoSToM:Causal-oriented Steering for Intrinsic Theory-of-Mind Alignment in Large Language Models
National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, Huazhong University of Science and Technology(华中科技大学国家大数据技术与系统工程技术研究中心、服务计算技术与系统实验室、集群与网格计算实验室);Singapore Management University(新加坡管理大学)