Teacher-Guided Tool Learning for Small Language Models via Bidirectional KL Constraints
Nanjing University of Aeronautics and Astronautics(南京航空航天大学);Security Capability Center(360安全能力中心);Nanjing University(南京大学);Tongji University(同济大学);Shanghai Jiao Tong University(上海交通大学)
External tools can extend the capabilities of small language models (SLMs), enabling their deployment in resource constrained environments. However, their limited capabilities make it difficult for SLMs to discover effective tool use behaviors through reinforcement learning alone, while direct teacher supervision suffers from teacher student behavioral distribution mismatch and may propagate erroneous preferences. To address these challenges, we propose Selective Teacher guided Policy Optimization (SeTPO), which coordinates student exploration with selective teacher guidance and persistent demonstration supervision. Specifically, SeTPO incorporates reverse KL derived token level teacher feedback into policy advantages on low reward trajectories, while auxiliary forward KL supervision preserves teacher demonstrated behaviors throughout training. Under an idealized bidirectional KL objective, we theoretically establish that the optimal policy achieves expected reward no lower than the teacher's while retaining a guaranteed fraction of the teacher's probability mass. Extensive experiments on BFCL v4 and API Bank demonstrate that SeTPO achieves superior overall performance over supervised fine tuning, reinforcement learning, and distillation baselines across all three student scales.
Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence
School of Computer Science and Engineering, Northeastern University, China(东北大学计算机科学与工程学院);Tsinghua University(清华大学);Meituan(美团);Meta AI;NiuTrans Research, Shenyang, China(新译研究院,沈阳,中国)
Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation
The University of Hong Kong(香港大学);Simon Fraser University(西蒙菲莎大学);University of California, Los Angeles(加州大学洛杉矶分校);Dartmouth College(达特茅斯学院);University of Maryland, Baltimore County(马里兰大学巴尔的摩县分校);Tencent(腾讯)
Learning from Stochastic Teacher Representations Using Student-Guided Knowledge Distillation
LIVIA, Dept. of Systems Engineering, ETS Montreal(LIVIA,系统工程系,蒙特利尔工程学院);CentraleSupélec, Universite Paris Saclay(中央理工巴黎高等学院);Aiim Lab, Queen’s University(人工智能实验室,皇后大学)
Teacher-Student Gaps Are Not Enough: Outcome-Guided On-Policy Distillation for Multi-Turn Autonomous Agents
Qwen Large Model Application Team, Alibaba(阿里巴巴通义千问大模型应用团队);Peking University(北京大学);University of Chinese Academy of Sciences(中国科学院大学);Shanghai Jiao Tong University(上海交通大学)
A Physics Prior-Guided Dual-Stream Attention Network for Motion Prediction of Elastic Bragg Breakwaters
Shandong University of Science and Technology(山东科技大学);Shandong Provincial Key Laboratory of Reliability and Intelligent Protection for Marine Engineering Equipment(山东省海洋工程装备可靠性与智能防护重点实验室)
BG-YOLO: A Bidirectional-Guided Method for Underwater Object Detection
School of Tropical Agriculture and Forestry, Hainan University(海南大学热带农林学院);School of Information and Communication Engineering(信息与通信工程学院);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);School of Cybersecurity, Northwestern Polytechnical University(西北工业大学网络空间安全学院)
DeSyR: A decoupled symbolic recovery framework for PDEs with PINN-guided structure discovery and physics-based coefficient refinement
Chengdu University of Information Technology(成都信息工程大学);Sichuan University(四川大学);Hong Kong Polytechnic University(香港理工大学);Southwest Petroleum University(西南石油大学)
Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders
State Key Laboratory for Novel Software Technology, Nanjing University(南京大学新型软件技术国家重点实验室);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算机与数据科学学院)
University of Tübingen(图宾根大学);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);ELLIS Institute Tübingen(图宾根ELLIS研究所);Tübingen AI Center(图宾根人工智能中心)
Lightweight Intrusion Detection in IoT via SHAP-Guided Feature Pruning and Knowledge-Distilled Kronecker Networks
LSIA Laboratory, Moroccan School of Engineering Sciences (EMSI)(摩洛哥工程科学学校LSIA实验室);Laboratory of Research in Informatics (LaRI), Faculty of Sciences, Ibn Tofail University(伊本·泰菲勒大学信息研究实验室);College of Computing, University Mohammed VI Polytechnic(穆莱·伊沙克六世理工学院计算机学院)
From Atoms to Chains: Divergence-Guided Reasoning Curriculum for Unlabeled LLM Domain Adaptation
Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science and Technology, Beijing Institute of Technology(北京智能信息科技重点实验室,计算机科学与技术学院,北京理工大学);ByteDance China(字节跳动中国)
On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents
Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所基础模型研究中心);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Large Language Model Department, Tencent(腾讯大语言模型部);University of Science and Technology of China(中国科学技术大学);Zhejiang University(浙江大学);National University of Singapore(新加坡国立大学);Wuhan AI Research(武汉人工智能研究院)