Peer Agent
Peer agents represent a burgeoning field exploring the interaction and collaboration between artificial agents, encompassing diverse applications from federated learning to educational settings. Current research focuses on improving the robustness and privacy of peer-to-peer systems, developing effective algorithms for peer evaluation and consensus-building (e.g., using LLMs for peer review or automated model evaluation), and designing methods for efficient resource utilization in distributed training environments. This research is significant for advancing both theoretical understanding of multi-agent systems and practical applications in areas such as machine learning, education, and robotics, addressing challenges related to data privacy, efficiency, and the reliability of automated systems.
Papers
ItTakesTwo: Leveraging Peer Representations for Semi-supervised LiDAR Semantic Segmentation
Yuyuan Liu, Yuanhong Chen, Hu Wang, Vasileios Belagiannis, Ian Reid, Gustavo Carneiro
PEER: Expertizing Domain-Specific Tasks with a Multi-Agent Framework and Tuning Methods
Yiying Wang, Xiaojing Li, Binzhu Wang, Yueyang Zhou, Yingru Lin, Han Ji, Hong Chen, Jinshi Zhang, Fei Yu, Zewei Zhao, Song Jin, Renji Gong, Wanqing Xu