让多智能体通信既快又懂：用混合信号提升效率与可解释性
HyLaT: Efficient Multi-Agent Communication via Hybrid Latent-Text Protocol
- 用隐空间传复杂信息，自然语言传关键指令，兼顾效率与可读
- 实验显示通信开销大幅降低，任务表现仍保持领先
- 适合需要高效协作且重视沟通透明度的多智能体系统
大型语言模型驱动的多智能体系统中，通信协议设计是核心挑战。现有单通道方法面临通信三难困境：纯文本方法可读性强但冗长，隐空间方法高效却不可解释且仅支持单向流程。受多通道通信理论启发，我们提出 HyLaT——一种混合隐空间-文本通信协议，通过隐空间传输复杂认知信号以提高效率，同时用自然语言表达简洁关键信号以保持可解释性与精确性。我们设计了两阶段训练框架，结合单智能体混合生成学习与多智能体交互协同训练，使智能体能在多轮互动中生成并理解混合消息。实验表明，HyLaT 显著降低通信开销，同时在多种场景下保持优异的任务性能、强泛化能力与鲁棒性。
原文摘要 · Abstract (English)
Communication protocol design is a central challenge in large language model-based multi-agent systems. Existing single-channel approaches face an inherent communication trilemma: text-based methods are interpretable but verbose, while latent-space methods are efficient but opaque and limited to unidirectional workflows. Inspired by multi-channel communication theory, we propose HyLaT, a hybrid latent-text communication protocol that transmits elaborate cognitive signals through a latent channel for efficiency, while expressing concise critical signals in natural language to preserve interpretability and precision. We introduce a two-stage training framework combining single-agent hybrid generation learning and multi-agent interactive co-training, enabling agents to generate and interpret hybrid messages across multiple rounds of interaction. Experiments demonstrate that HyLaT reduces communication overhead significantly while maintaining competitive task performance, with strong generalization and robustness across diverse settings.
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。