Deploying Large Language Models (LLMs) for discriminative workloads is often limited by inference latency, compute, and API costs at scale. Active distillation reduces these costs by querying an LLM oracle to train small discriminative students, but most pipelines distill only final labels, discarding intermediate reasoning signals and offering limited diagnostics of what reasoning is missing and where errors arise. We propose Graph of Concept Predictors (GCP), a reasoning-aware active distillation framework in which the teacher's reasoning is elicited as a directed acyclic graph of intermediate concepts and mirrored in the student. GCP enhances sample efficiency through a graph-aware acquisition strategy that weights per-concept uncertainty, gradient diversity, and coverage by node centrality. Additionally, it improves training stability and efficiency by performing targeted sub-module retraining, which attributes downstream loss to specific concept predictors and updates only the most influential modules. Experiments on eight NLP classification benchmarks demonstrate that GCP enhances performance under limited annotation budgets while yielding more interpretable and controllable training dynamics. Code is available at https://github.com/Ziyang-Yu/GCP.
Distilling Mathematical Reasoning Capabilities into Small Language Models
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）
Domain-Specialized Tree of Thought through Plug-and-Play Predictors
Xi'an Jiaotong University, China（西安交通大学）；Singapore Management University, Singapore（新加坡管理学院）；University of Massachusetts at Amherst, United States（马萨诸塞大学阿默斯特分校）
DART: Difficulty-Adaptive Reasoning Truncation for Efficient Large Language Models
School of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能学院）；CSE Department, The Chinese University of Hong Kong（香港中文大学计算机科学与工程系）；Research and Development Department, SIMMIR Tech（Simmir科技研发部）；School of Information Science and Technology, Xiamen University Tan Kah Kee College（厦门大学信息科学与技术学院）；The University of Hong Kong（香港大学）
Reasoning Compression with Mixed-Policy Distillation
Technical University of Munich（慕尼黑技术大学）；GESIS – Leibniz Institute for the Social Sciences（莱布尼茨社会科学研究所）；Northeastern University（东北大学）；LMU Munich（慕尼黑大学）；Siemens AG（西门子股份公司）；University of Cambridge（剑桥大学）；University of Oxford（牛津大学）；Mina AI
Structural Knowledge Distillation: Tractably Distilling Information for Structured Predictor
ShanghaiTech University（上海科技大学）；Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences（中国科学院上海微系统与信息技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）
Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model Enhancement
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, China（通用人工智能国家重点实验室，智能科学与技术学院，北京大学，中国）；Huawei Noah’s Ark Lab, China（华为诺亚方舟实验室，中国）
Reflect to Inform: Boosting Multimodal Reasoning via Information-Gain-Driven Verification
University of Science and Technology of China（中国科学技术大学）；Huawei Foundation Model Department（华为基础模型部）；The Chinese University of Hong Kong（香港中文大学）；Hong Kong University of Science and Technology（香港科技大学）
Key-Point-Driven Mathematical Reasoning Distillation of Large Language Model
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；School of Artificial Intelligence, Beijing Normal University（北京师范大学人工智能学院）
Large Language Models Explore by Latent Distilling
State Key Laboratory of General Artificial Intelligence, BIGAI, Beijing, China（人工智能通用基础理论国家重点实验室，BIGAI，北京，中国）；School of Information Science and Technology, ShanghaiTech University, Shanghai, China（信息科学与技术学院，上海交通大学，上海，中国）
ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model
Northeastern University（东北大学）；University of California San Diego（加州大学圣地亚哥分校）；University of Maryland（马里兰大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Washington（华盛顿大学）
LLMs-based Few-Shot Disease Predictions using EHR: A Novel Approach Combining Predictive Agent Reasoning and Critical Agent Instruction
Emory University（埃默里大学）；University of Washington（华盛顿大学）；UCSD（加利福尼亚大学圣迭戈分校）；Rollins School of Public Health, Emory University（埃默里大学罗林斯公共卫生学院）；School of Medicine, Emory University（埃默里大学医学院）
FAIR at Meta（Meta 的 FAIR 部门）；Inria（法国国家科学与技术研究院）；Sorbonne Université（索邦大学）；Institut universitaire de France（法国国家科学研究院）；CERMICS École des Ponts ParisTech（巴黎理工学院 CERMICS 实验室）；ENS, PSL Research University（巴黎高等师范学院与巴黎科学实验室）
ViLAM: Distilling Vision-Language Reasoning into Attention Maps for Social Robot Navigation
Dept. of Electrical and Computer Engineering, University of Maryland, College Park, MD, USA（电气与计算机工程系，马里兰大学，College Park, MD, USA）；Dept. of Computer Science, University of Maryland, College Park, MD, USA（计算机科学系，马里兰大学，College Park, MD, USA）；James Clark School of Engineering, University of Maryland, College Park, MD, USA（James Clark工程学院，马里兰大学，College Park, MD, USA）
