Large Language Models (LLMs) have achieved exceptional performance across diverse domains through training on massive datasets. However, scaling LLMs to support multiple downstream domain applications remains a significant challenge, especially under resource constraints. Existing approaches often struggle to balance performance across multiple domains with resource efficiency, limiting their broader applicability. To address this, we introduce the CCoE architecture, a modular framework that seamlessly integrates domain-specific experts into a unified LLM. By leveraging independently trained expert subnetworks on a shared backbone partition, CCoE achieves state-of-the-art performance while significantly reducing the resource requirements for multi-expert deployments. Furthermore, rule-based gating and expert planning in CCoE enable flexible task allocation, promoting expert collaboration to handle complex reasoning tasks. CCoE not only reduces inference costs but also provides a flexible and scalable solution for integrating domain expertise across diverse applications. Experiments on five domains demonstrate that CCoE achieves comparable performance to current domain-specific LLMs. Moreover, compared to existing multi-domain model ensemble methods, CCoE reduces memory usage by 61.3%, while improving inference efficiency by 0.76x over parameter-efficient multi-expert integration approaches.
RAM2C: A Liberal Arts Educational Chatbot based on Retrieval-augmented Multi-role Multi-expert Collaboration
Center for Brain Inspired Computing Research (CBICR), Tsinghua University(清华大学脑启发计算研究中心);Optical Memory National Engineering Research Center, Tsinghua University(清华大学光存储国家工程研究中心);Tsinghua University-China Electronics Technology HIK Group Co. Joint Research Center for Brain-inspired Computing(清华大学-中国电子 hik 集团联合脑启发计算研究中心);IDG/McGovern Institute for Brain Research, Tsinghua University(清华大学 IDG/麦戈文脑科学研究院);Tsinghua University(清华大学)
CoE-Ops: Collaboration of LLM-based Experts for AIOps Question-Answering
SKLCCSE, Institute of Artificial Intelligence, Beihang University(SKLCCSE,人工智能学院,北航);Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University(未来区块链与隐私计算先进创新中心,北航)
Expertise-aware Multi-LLM Recruitment and Collaboration for Medical Decision-Making
School of Automation, Hangzhou Dianzi University(杭州电子大学自动化学院);School of Control Science and Engineering, Shandong University(山东大学控制科学与工程学院);Department of Electronic Engineering, Chinese University of Hong Kong(香港中文大学电子工程系)
LLARS: Enabling Domain Expert & Developer Collaboration for LLM Prompting, Generation and Evaluation
Technische Hochschule Nürnberg Georg Simon Ohm(图恩-努尔堡技术大学乔治·西蒙·奥姆学院);Faculty of Computer Science, Centre for Artificial Intelligence (KIZ)(计算机科学学院,人工智能中心(KIZ));Faculty of Social Sciences, Institute for E-Counselling(社会科学学院,电子咨询研究所)
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)
Rank-and-Reason: Multi-Agent Collaboration Accelerates Zero-Shot Protein Mutation Prediction
Shanghai Jiao Tong University(上海交通大学);Shanghai Innovation Institute(上海创新研究院);Southern University of Science(南方大学(科学));East China University of Science and Technology(东中国科学与技术大学)
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)
A foundation model for human-AI collaboration in medical literature mining
University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);National Library of Medicine, National Institutes of Health(美国国立卫生研究院国家医学图书馆);National Institute of Diabetes and Digestive and Kidney Diseases, National Institutes of Health(美国国立卫生研究院国家糖尿病、消化和肾脏疾病研究所);Massachusetts General Hospital(麻省总医院);Harvard Medical School(哈佛医学院);National Eye Institute, National Institutes of Health(美国国立卫生研究院国家眼科研究所);Northwestern University Feinberg School of Medicine(西北大学费恩伯格医学院);Chungbuk National University Hospital(忠北国立大学医院);Chungbuk National University College of Medicine(忠北国立大学医学院);University of Pittsburgh Medical Center(匹兹堡大学医学中心);Weill Cornell Medicine(威尔康奈尔医学院);UT Southwestern Medical Center(德克萨斯大学西南医学中心);University of Washington(华盛顿大学);NYU Langone Health(纽约大学朗格尼健康中心);OSF HealthCare Illinois Neurological Institute(OSF医疗保健伊利诺伊神经研究所)
From Visual Perception to Deep Empathy: An Automated Assessment Framework for House-Tree-Person Drawings Using Multimodal LLMs and Multi-Agent Collaboration
Tsinghua University(清华大学);Shenzhen University(深圳大学);University of Oxford(牛津大学);Shenzhen Institute of Education Sciences(深圳市教育科学研究院);Guangzhou University of Chinese Medicine(广州中医药大学);Harbin Institute of Technology(哈尔滨工业大学)
STRICTA: Structured Reasoning in Critical Text Assessment for Peer Review and Beyond
UKP Lab, ATHENE National Research Center for Applied Cybersecurity, Technical University of Darmstadt(UKP实验室,ATHENE国家应用网络安全研究中心,德累斯顿技术大学);AIML Lab, Hessian Center for AI, Technical University of Darmstadt(AIML实验室,黑森人工智能中心,德累斯顿技术大学);Synthetic RNA Biology, Technical University of Darmstadt(合成RNA生物学,德累斯顿技术大学)
AIAP: A No-Code Workflow Builder for Non-Experts with Natural Language and Multi-Agent Collaboration
Department of Animation, \ University of Art \& Design Uiwang-si Gyeonggi-do Republic of Korea;Graduate School of Information, \ University Seoul Republic of Korea;Department of Animation, \ University of Art \& Design;Graduate School of Information, \ University