Learning to Interrupt in Language-based Multi-agent Communication

ArXi:2604.06452v1 Announce Type: new Multi-agent systems using large language models (LLMs) have nstrated impressive capabilities across various domains. However, current agent communication suffers from verbose output that overload context and increase computational costs. Although existing approaches focus on compressing the message from the speaker side, they struggle to adapt to different listeners and identify relevant information. An effective way in human communication is to allow the listener to interrupt and express their opinion or ask for clarification.