Junjie Liao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Junjie Liao has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Jiandian Zeng
Institute of Artificial Intelligence and Future Networks, Beijing Normal University, Zhuhai, China
2 shared publications - Binbin Song
Faculty of Computing Harbin Institute of Technology Harbin China
1 shared publication - Changfu Xu
Jiangxi University of Finance and Economics
1 shared publication - Guangxue Zhang
Institute of Artificial Intelligence and Future Networks, Beijing Normal University
1 shared publication - Huaijin Liu
School of Artificial Intelligence Guangzhou Maritime University China and College of Mechanical Engineering and Automation Huaqiao University Xiamen China
1 shared publication - Mengting Zhou
State Key Laboratory of Internet of Things for Smart City and the Department of Computer and Information Science, University of Macau, Macao, China
1 shared publication
Latest Publications
- 1 March 2026
- Published by Elsevier in Pattern Recognition
- Vol. 178
Unlocking explainable and effective multimodal affective reasoning via large language models
- 1 March 2026
- Published by Elsevier in Pattern Recognition
- Vol. 178
Unlocking explainable and effective multimodal affective reasoning via large language models
- 14 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. 40 (3) , 34-41
Multi-Agent Collaborative Reasoning via Cloud-Edge Framework
Large Language Model (LLM)-based agents have significantly advanced the reasoning and problem-solving capabilities of intelligent systems. As tasks grow more complex, there is an increasing need to shift from single-agent framework to Multi-Agent Systems (MAS) for enhanced collaborative performance. Achieving better performance typically requires deploying large-scale LLMs, however, it poses significant challenges on resource-constrained edge devices. In addition, most MAS adopt a fully connected communication topology and require multiple rounds of interaction, resulting in considerable communication redundancy and increased computational overhead. To address the issues, in this paper, we propose a Directed Acyclic Graph-based Multi-Agent System (DAG-MAS) via cloud-edge framework for collaborative reasoning. Specifically, considering the limited resources on the edge, we utilize a 72B-LLM in the cloud finetunes a lightweight Small Language Model (SLM) for edge deployment. To generate a one round interaction graph, the SLM is further employed to analyze task requirements and determine optimal communication topology, minimizing overhead while enabling effective information exchange. Extensive experiments and analyses on four reasoning datasets demonstrate the superiority of our approach compared to several benchmark methods, validating the effectiveness in achieving higher reasoning performance with lower communication costs.
- 14 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. 40 (3) , 34-41
Multi-Agent Collaborative Reasoning via Cloud-Edge Framework
Large Language Model (LLM)-based agents have significantly advanced the reasoning and problem-solving capabilities of intelligent systems. As tasks grow more complex, there is an increasing need to shift from single-agent framework to Multi-Agent Systems (MAS) for enhanced collaborative performance. Achieving better performance typically requires deploying large-scale LLMs, however, it poses significant challenges on resource-constrained edge devices. In addition, most MAS adopt a fully connected communication topology and require multiple rounds of interaction, resulting in considerable communication redundancy and increased computational overhead. To address the issues, in this paper, we propose a Directed Acyclic Graph-based Multi-Agent System (DAG-MAS) via cloud-edge framework for collaborative reasoning. Specifically, considering the limited resources on the edge, we utilize a 72B-LLM in the cloud finetunes a lightweight Small Language Model (SLM) for edge deployment. To generate a one round interaction graph, the SLM is further employed to analyze task requirements and determine optimal communication topology, minimizing overhead while enabling effective information exchange. Extensive experiments and analyses on four reasoning datasets demonstrate the superiority of our approach compared to several benchmark methods, validating the effectiveness in achieving higher reasoning performance with lower communication costs.