Emergent Communication (EmCom) investigates how agents develop symbolic communication through interaction without predefined language. Recent frameworks, such as the Metropolis--Hastings Naming Game (MHNG), formulate EmCom as the learning of shared external representations negotiated through interaction under joint attention, without explicit success or reward feedback. However, MHNG relies on sampling-based updates that suffer from high rejection rates in high-dimensional perceptual spaces, making the learning process sample-inefficient for complex visual datasets. In this work, we propose the SimSiam Naming Game (SSNG), a feedback-free EmCom framework that replaces sampling-based updates with a symmetric, self-supervised representation alignment objective between autonomous agents. Building on a variational inference--based probabilistic interpretation of self-supervised learning, SSNG formulates symbol emergence as an alignment process between agents' latent representations mediated by message exchange. To enable end-to-end gradient-based optimization, discrete symbolic messages are learned via a Gumbel--Softmax relaxation, preserving the discrete nature of communication while maintaining differentiability. Experiments on CIFAR-10 and ImageNet-100 show that the emergent messages learned by SSNG achieve substantially higher linear-probe classification accuracy than those produced by referential games, reconstruction games, and MHNG. These results indicate that self-supervised representation alignment provides an effective mechanism for feedback-free EmCom in multi-agent systems.

翻译：涌现通信（EmCom）研究智能体如何在没有预定义语言的情况下，通过交互发展出符号化通信方式。近期框架如Metropolis-Hastings命名博弈（MHNG）将EmCom形式化为在联合注意力下通过交互协商共享外部表征的学习过程，且无需显式的成功或奖励反馈。然而，MHNG依赖基于采样的更新机制，在高层感知空间中存在高拒绝率问题，导致其在复杂视觉数据集上的学习过程样本效率低下。本文提出SimSiam命名博弈（SSNG）——一种无反馈EmCom框架，利用自主智能体间的对称自监督表征对齐目标替代基于采样的更新。基于自监督学习的变分推断概率解释，SSNG将符号涌现建模为通过消息交换中介的智能体潜在表征对齐过程。为实现端到端梯度优化，离散符号消息通过Gumbel-Softmax松弛学习，既保留通信的离散本质又维持可微性。在CIFAR-10和ImageNet-100上的实验表明，SSNG所习得的涌现消息在线性探测分类准确率上显著优于指涉博弈、重构博弈及MHNG生成的消息。这些结果表明，自监督表征对齐为多智能体系统中的无反馈EmCom提供了有效机制。