AI实验发现，高效协作无需人类语言，挑战了思维需符号化假说。
The Efficiency Attenuation Phenomenon: A Computational Challenge to the Language of Thought Hypothesis
- 用多智能体强化学习模拟自发通信协议
- 自发协议效率比人类符号协议高50.5%
- 适合关注认知科学与AI哲学交叉的读者
本文通过计算实验检验思维是否需要类语言格式，即语言之思（LoT）假说。我们提出“AI私有语言”思想实验：若两个人工智能体通过多智能体强化学习（MARL）发展出高效且不可理解的通信协议，而强制使用人类可理解的语言会导致性能下降，则这种效率衰减现象（EAP）将挑战LoT。我们在部分可观测的协作导航任务中形式化该实验。结果表明，具备自生通信协议的智能体效率比使用预设人类符号协议的智能体高出50.5%，证实了EAP的存在。这表明在这些系统中，最优协同认知并非依赖符号结构，而是自然耦合于非符号计算。研究连接哲学、认知科学与人工智能，主张认知架构的多元主义，并揭示其对AI伦理的启示。
原文摘要 · Abstract (English)
This paper computationally investigates whether thought requires a language-like format, as posited by the Language of Thought (LoT) hypothesis. We introduce the ``AI Private Language'' thought experiment: if two artificial agents develop an efficient, inscrutable communication protocol via multi-agent reinforcement learning (MARL), and their performance declines when forced to use a human-comprehensible language, this Efficiency Attenuation Phenomenon (EAP) challenges the LoT. We formalize this in a cooperative navigation task under partial observability. Results show that agents with an emergent protocol achieve 50.5\% higher efficiency than those using a pre-defined, human-like symbolic protocol, confirming the EAP. This suggests optimal collaborative cognition in these systems is not mediated by symbolic structures but is naturally coupled with sub-symbolic computations. The work bridges philosophy, cognitive science, and AI, arguing for pluralism in cognitive architectures and highlighting implications for AI ethics.
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。