Multi Agent
Multi-agent systems research focuses on designing and analyzing systems composed of multiple interacting agents, aiming to achieve complex goals through collaboration or competition. Current research emphasizes leveraging large language models (LLMs) to enhance agent capabilities, particularly in reasoning, planning, and communication, often employing architectures like multi-agent reinforcement learning (MARL) and novel communication pipelines to improve efficiency and robustness. This field is significant for advancing AI capabilities in diverse applications, including robotics, autonomous driving, and scientific discovery, by enabling more sophisticated and adaptable intelligent systems.
Papers
MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate
Alfonso Amayuelas, Xianjun Yang, Antonis Antoniades, Wenyue Hua, Liangming Pan, William Wang
GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models
Shilong Li, Yancheng He, Hangyu Guo, Xingyuan Bu, Ge Bai, Jie Liu, Jiaheng Liu, Xingwei Qu, Yangguang Li, Wanli Ouyang, Wenbo Su, Bo Zheng
EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms
Siyu Yuan, Kaitao Song, Jiangjie Chen, Xu Tan, Dongsheng Li, Deqing Yang
Robust Cooperative Multi-Agent Reinforcement Learning:A Mean-Field Type Game Perspective
Muhammad Aneeq uz Zaman, Mathieu Laurière, Alec Koppel, Tamer Başar