Wenzhe Fan, Tommaso Tognoli, Henry Peng Zou, Chunyu Miao, Yibo Wang, Xinhua Zhang
TodyComm is a dynamic communication algorithm for multi-agent systems that adapts to changing conditions, improving task effectiveness and efficiency.
In multi-agent systems where tasks are completed over multiple rounds, effective communication is crucial. Traditional methods use a fixed communication setup, which can be limiting when conditions change, like when roles shift or communication resources vary. TodyComm addresses this by adapting the communication structure dynamically based on the task and situation, optimizing performance. This approach has been shown to improve task outcomes while maintaining efficiency in communication and scalability.
