从咕哝到语法：合作觅食中涌现的语言

From Grunts to Grammar: Emergent Language from Cooperative Foraging

May 19, 2025

作者: Maytus Piriyajitakonkij, Rujikorn Charakorn, Weicheng Tao, Wei Pan, Mingfei Sun, Cheston Tan, Mengmi Zhang

cs.AI

摘要

远古穴居人依靠手势、发声及简单信号来协调行动、制定计划、躲避捕食者并共享资源。如今，人类借助复杂语言合作，取得了非凡成就。是什么推动了这种交流方式的演变？语言如何产生、适应并成为团队协作的关键？理解语言的起源仍是一项挑战。语言学与人类学中的一个主流假说认为，语言的发展是为了满足早期人类合作的生态与社会需求。语言并非孤立产生，而是源于共同的生存目标。受此观点启发，我们在多智能体觅食游戏中探究了语言的涌现。这些环境设计旨在反映被认为影响交流进化的认知与生态限制。智能体在一个共享的网格世界中运作，仅对其他智能体及环境拥有部分了解，必须协调一致以完成诸如收集高价值目标或执行时序性动作等游戏任务。通过端到端的深度强化学习，智能体从零开始学习行动与交流策略。我们发现，智能体发展出的交流协议具有自然语言的标志性特征：任意性、可互换性、位移性、文化传递性及组合性。我们量化了每一特性，并分析了不同因素（如群体规模与时间依赖性）如何塑造涌现语言的具体方面。我们的框架为研究语言如何从部分可观测性、时序推理及具身多智能体环境中的合作目标中演化提供了一个平台。我们将公开所有数据、代码及模型。

English

Early cavemen relied on gestures, vocalizations, and simple signals to coordinate, plan, avoid predators, and share resources. Today, humans collaborate using complex languages to achieve remarkable results. What drives this evolution in communication? How does language emerge, adapt, and become vital for teamwork? Understanding the origins of language remains a challenge. A leading hypothesis in linguistics and anthropology posits that language evolved to meet the ecological and social demands of early human cooperation. Language did not arise in isolation, but through shared survival goals. Inspired by this view, we investigate the emergence of language in multi-agent Foraging Games. These environments are designed to reflect the cognitive and ecological constraints believed to have influenced the evolution of communication. Agents operate in a shared grid world with only partial knowledge about other agents and the environment, and must coordinate to complete games like picking up high-value targets or executing temporally ordered actions. Using end-to-end deep reinforcement learning, agents learn both actions and communication strategies from scratch. We find that agents develop communication protocols with hallmark features of natural language: arbitrariness, interchangeability, displacement, cultural transmission, and compositionality. We quantify each property and analyze how different factors, such as population size and temporal dependencies, shape specific aspects of the emergent language. Our framework serves as a platform for studying how language can evolve from partial observability, temporal reasoning, and cooperative goals in embodied multi-agent settings. We will release all data, code, and models publicly.