Artificial neural networks (ANNs) are increasingly used as research models, but questions remain about their generalizability and representational invariance. Biological neural networks under social constraints evolved to enable communicable representations, demonstrating generalization capabilities. This study proposes a communication protocol between cooperative agents to analyze the formation of individual and shared abstractions and their impact on task performance. This communication protocol aims to mimic language features by encoding high-dimensional information through low-dimensional representation. Using grid-world mazes and reinforcement learning, teacher ANNs pass a compressed message to a student ANN for better task completion. Through this, the student achieves a higher goal-finding rate and generalizes the goal location across task worlds. Further optimizing message content to maximize student reward improves information encoding, suggesting that an accurate representation in the space of messages requires bi-directional input. This highlights the role of language as a common representation between agents and its implications on generalization capabilities.

翻译：人工神经网络（ANNs）日益被用作研究模型，但其泛化能力和表征不变性仍存疑问。在社会约束下演化的生物神经网络能够形成可交流的表征，展现出泛化能力。本研究提出一种合作智能体间的通信协议，用以分析个体抽象与共享抽象的形成过程及其对任务性能的影响。该通信协议通过低维表征编码高维信息，旨在模拟语言特征。利用网格世界迷宫和强化学习，教师ANN向学生ANN传递压缩信息以提升任务完成效果。通过这一机制，学生ANN实现了更高的目标发现率，并能在不同任务世界中泛化目标位置。进一步优化信息内容以最大化学生奖励，可改善信息编码效率，表明在信息空间中形成精确表征需要双向输入。这揭示了语言作为智能体间共同表征的作用及其对泛化能力的影响。