Exercise Recommendation Based on the Collaborative Multi-Agents Paths
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
To address the one-sidedness limitation of singleagent recommendation systems, this paper proposes an exercise recommendation framework based on multi-agents collaboration. A dedicated management agent is designed to undertake task decomposition and global scheduling, while multiple functional agents are constructed to realize the collaborative execution of core recommendation tasks. Each agent assumes a distinct role, performing its designated functions and engaging in efficient synergy with others. Experimental results demonstrate that the multi-agents system, characterized by functional decoupling and closed-loop linkage, exhibits significant advantages in recommendation accuracy, user adaptability, and learning efficiency, ultimately achieving an overall upgrade of the exercise recommendation process.
Fields of Study & Subjects
Recommender Systems and Techniques
Innovation in Digital Healthcare Systems
Multi-Agent Systems and Negotiation
Publication details
- Journal / source
- International Conference on Electrical Automation and Artificial Intelligence (ICEAAI)
- Pages
- 866–872
- Publication date
- 16 January 2026
- Language
- EN