让语言模型学会在对话中适时打断，提升多智能体沟通效率。
Learning to Interrupt in Language-based Multi-agent Communication
- 听众可主动中断说话者生成过程，改变传统单向压缩通信方式。
- 引入HANDRAISER方法，使中断时机更合理，通信成本降低32.2%。
- 适用于多智能体协作任务，行为具备跨任务和智能体的泛化能力。
当同事解释你已了解的内容时，你会选择打断。这一人类交流中的自然行为，在当前冗长的语言模型多智能体系统中仍缺失。现有方法仅从发言方优化通信效率，通过压缩消息实现；我们则转换视角：不强迫发言者更简洁，而是赋予倾听者决定何时停止接收信息的能力。提出一种新通信范式，允许听众在发言者生成过程中主动中断。实验发现，单纯赋予模型中断能力会导致其过早打断，因过度自信而获取不足信息。为此提出HANDRAISER学习方法，基于未来收益与沟通成本预测最优中断时机。在三类多智能体任务（双智能体文字猜图、三智能体会议协调、三智能体辩论）上验证，相比不可中断基线，通信成本降低32.2%，任务表现相当或更优，且中断行为具有跨智能体和任务的泛化性。
原文摘要 · Abstract (English)
When a colleague starts explaining something you already understand, you interrupt them. This simple act, a listener taking control of the conversation, is natural in human communication but absent in current verbose LLM multi-agent systems. Current approaches address communication efficiency only from the speaker side, compressing messages before they are sent. We flip the perspective: rather than making speakers more concise, we let listeners decide when they have heard enough. We propose a new communication paradigm in which the listener can interrupt the speaker mid-generation. We find that LLMs, given this ability, are overconfident and interrupt too early before receiving sufficient information. This finding motivates HANDRAISER, a learning method that predicts the right moment to interrupt based on estimated future reward and communication cost. We evaluate our framework on three multi-agent tasks: 2-agent text pictionary, 3-agent meeting scheduling, and 3-agent debate. HANDRAISER reduces communication cost by 32.2% over the non-interruptible baseline while achieving comparable or superior task performance, with interruption behavior that generalizes across different agents and tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。