Large language models improve final-answer accuracy through extended chain-of-thought reasoning, but often spend tokens inefficiently and offer little inference-time control. Existing efficient reasoning methods control thinking length by shortening, early-stopping, or compressing traces, leaving how the model thinks implicit. In this paper, we propose Agentic Chain-of-Thought Steering (ACTS), which formulates reasoning steering as a Markov decision process where a controller agent adaptively steers a frozen reasoner during inference. At each step, the controller observes the reasoning trace and remaining thinking budget, then issues a steering action consisting of a reasoning strategy and a steering phrase that initiates the next reasoner step. This enables budget-aware strategy control for efficient reasoning while preserving the reasoner's generation continuity. We initialize the controller agent from our constructed synthetic steering trajectories with multi-budget augmentation, and further optimize it via reinforcement learning with budget-conditioned reward shaping. Experiments across multiple benchmarks show that ACTS achieves competitive accuracy with substantial token savings, and enables controllable accuracy-token trade-offs across different reasoners and tasks. The code is available at https://github.com/Andree-9/ACTS.
MetaSteer: Context-Conditioned, nonlinear Steering via Attention-Projection Adaptation
School of Computer Science and Engineering, UNSW Sydney（悉尼新南威尔士大学计算机科学与工程学院）；ARC Centre of Excellence for Automated Decision-Making and Society (ADM+S)（澳大利亚研究理事会自动化决策与社会卓越中心）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
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）
Compositional Steering of Large Language Models with Steering Tokens
NEC Laboratories Europe（NEC欧洲实验室）；University of Edinburgh（爱丁堡大学）；Center for Artificial Intelligence and Data Science（人工智能与数据科学中心）；University of Würzburg（乌尔姆大学）；CAIR, Ss. Cyril and Methodius University of Skopje（CAIR，斯·西里尔和方法ius大学）
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Arrive Bio（Arrive Bio（阿里夫生物））
Prior work on controllable text generation has focused on learning how to control language models through trainable decoding, smart-prompt design, or fine-tuning based on a desired objective. We hypothesize that the information needed to steer the model to generate a target sentence is already encoded within the model. Accordingly, we explore a different approach altogether: extracting latent vectors directly from pretrained language model decoders without fine-tuning. Experiments show that there exist steering vectors, which, when added to the hidden states of the language model, generate a t…
From Rational Answers to Emotional Resonance: The Role of Controllable Emotion Generation in Language Models
State Key Laboratory on Technologies for Chinese Medicine Pharmaceutical Process Control and Intelligent Manufacture（中药制药过程控制与智能制造技术国家重点实验室）；Zhejiang Lab（浙江实验室）
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）
Building a Foundational Guardrail for General Agentic Systems via Synthetic Data
University of Notre Dame（诺特大学）；MIT-IBM Watson AI Lab（MIT-IBM Watson AI实验室）；University of Washington（华盛顿大学）；Ca’ Foscari University of Venice（威尼斯卡福尔学院）；IBM Research（IBM研究院）
Are Emotion and Rhetoric Neurons in LLM? Neuron Recognition and Adaptive Masking for Emotion-Rhetoric Prediction Steering
Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University（航空信息安全与可信计算 key laboratory，教育部，武汉大学计算机科学与工程学院）
SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions
University of North Dakota（北达科他大学）；Youngstown State University（青年州大学）；University of Toledo（托莱多大学）；University of Missouri（密苏里大学）；Tribhuvan University（特里布文大学）
Unveiling the Potential of Diffusion Large Language Model in Controllable Generation
University of Southern California（南加州大学）；University of Queensland（昆士兰大学）；University of California, San Diego（加州大学圣地亚哥分校）；University of California, Merced（加州大学默塞德分校）
Self-Improvements in Modern Agentic Systems: A Survey
School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）；King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学）；University of Alberta（阿尔伯塔大学）；The Swiss AI Lab IDSIA/USI/SUPSI（瑞士人工智能实验室IDSIA/USI/SUPSI）
