Edge devices host domain-specific small language models (SLMs) with limited resources, while private clouds offer larger LLMs. We propose G-Boost, an adaptive edge-cloud framework that improves a deployed SLM's task performance without parameter updates. It formulates reasoning as a tree search, choosing at each step between SLM-only inference and SLM-LLM logit fusion---which transfers domain knowledge from the SLM's adapted version to the cloud LLM without exposing private data. A process reward model guides Monte Carlo tree search to select beneficial collaboration steps dynamically. The edge runs the SLM and search controller; the cloud hosts the LLM and reward model, exchanging only current context. Evaluated on GSM8K and MATH-500 with Qwen2.5 and LLaMA2, G-Boost outperforms the SLM alone, static fusion, and fine-tuned baselines, gaining up to 8.6 and 10.7 percentage points over MCTS and Proxy-Tuning, respectively. Results confirm that step-level, reward-guided dynamic collaboration enhances reasoning and domain utilization for deployed edge SLMs.
CMAT: A Multi-Agent Collaboration Tuning Framework for Enhancing Small Language Models
East China Jiaotong University(华东交通大学);University of Minnesota - Twin Cities(明尼苏达大学双城分校);Guangdong University of Technology(广东工业大学);University of Electronic Science and Technology of China(电子科技大学);University of Toronto(多伦多大学);East China Normal University(华东师范大学)
A Knowledge-driven Adaptive Collaboration of LLMs for Enhancing Medical Decision-making
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)(莫扎德·本·扎耶德人工智能大学);University of Electronic Science and Technology of China(电子科学与技术大学);Swiss Federal Institute of Technology Lausanne (EPFL)(苏黎世联邦理工学院)
ColaCare: Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent Collaboration
Peking University(北京大学);ETH Zurich(苏黎世联邦理工学院);Peking University Third Hospital(北京大学第三医院);University of Edinburgh(爱丁堡大学);Beihang University(北京航空航天大学);Health Data Research UK(英国健康数据研究中心)
Federated Learning-Based Data Collaboration Method for Enhancing Edge Cloud AI System Security Using Large Language Models
College of Computing and Information Science(计算与信息科学学院);Siebel School of Computing and Data Science(计算与数据科学学院);Cornell University(康奈尔大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);New York, USA(美国纽约);Champaign, Illinois, USA(美国伊利诺伊州香槟)
PerspAct: Enhancing LLM Situated Collaboration Skills through Perspective Taking and Active Vision
University of Milan-Bicocca(米兰-比科卡大学);University of Naples Federico II(那不勒斯费德里科二世大学);Oversonic Robotics(Oversonic机器人公司);University of Essex(埃塞克斯大学);TUM School of Social Sciences and Technology(慕尼黑技术大学社会科学与技术学院)
From Automation to Collaboration: Human-in-the-Loop Methods for Safe and Trustworthy NLP
Department of Computer Science and Engineering, BRAC University(布拉克大学计算机科学与工程系);Department of Electrical and Electronic Engineering, Rajshahi University of Engineering and Technology(拉贾沙希工程与技术大学电子与电气工程系)
FirmCORe: A Benchmark for Structured Reasoning about Inter-Firm Collaboration Opportunities
Southwest University of Finance and Economics(西南财经大学);Nanyang Technological University(南洋理工大学);Beijing University of Post and Telecommunication(北京邮电大学)
Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration
The Chinese University of Hong Kong(香港中文大学);LLM Department, Tencent(腾讯语言模型部门);Mohamed bin Zayed University of Artificial Intelligence(马尔代夫人工智能大学);McGill University(麦吉尔大学);City University of Hong Kong(香港城市大学);The University of Edinburgh(爱丁堡大学)