從咕噥到語法：合作覓食中湧現的語言

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

早期穴居人依賴手勢、發聲和簡單信號來協調、規劃、躲避捕食者並共享資源。如今，人類則運用複雜的語言進行合作，以達成非凡的成就。是什麼推動了這種交流方式的演變？語言是如何產生、適應並成為團隊合作不可或缺的要素的？理解語言的起源仍是一大挑戰。語言學和人類學中的一個主流假設認為，語言是為滿足早期人類合作的生態與社會需求而演化的。語言的出現並非孤立事件，而是源於共同的生存目標。受此觀點啟發，我們在多智能體覓食遊戲中探討語言的湧現。這些環境設計旨在反映被認為影響了交流演化的認知與生態約束。智能體在一個共享的網格世界中運作，僅對其他智能體和環境擁有部分知識，必須協調完成諸如拾取高價值目標或執行時間順序行動等遊戲任務。通過端到端的深度強化學習，智能體從零開始學習行動與交流策略。我們發現，智能體發展出的交流協議具有自然語言的標誌性特徵：任意性、互換性、位移性、文化傳播性和組合性。我們量化了每一特性，並分析了不同因素（如群體規模和時間依賴性）如何塑造湧現語言的特定方面。我們的框架為研究語言如何在具身多智能體環境中從部分可觀測性、時間推理和合作目標中演化提供了一個平臺。我們將公開所有數據、代碼和模型。

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.