参照游戏为神经代理提供了一个接地的学习环境,这说明语言在功能上是用来交流的。然而,他们没有考虑到第二个被认为是人类语言形成的基本限制:它必须是新的语言学习者可以学习的。Cogswell et al.(2019)通过不断变化的代理人群在参考游戏中引入文化传播,以限制新兴语言的可学习性。然而,由此产生的语言仍然固有地受到代理的底层能力的影响。在这项工作中,我们引入语言传输引擎来模拟人口的代理人的文化和建筑的演变。作为我们的核心贡献,我们的经验表明,最佳的情况是考虑到语言学习者的学习偏见,从而让语言和代理共同发展。当我们允许智能体群体通过架构进化来进化时,我们在所有考虑的指标上都实现了全面的改进,并超过了文化传播所带来的收益。这些结果强调了研究潜在的代理架构的重要性,并铺平了道路,以调查语言和代理的共同进化的语言出现研究。
英文摘要:
Referential games offer a grounded learning environment for neural agents which accounts for the fact that language is functionally used to communicate. However, they do not take into account a second constraint considered to be fundamental for the shape of human language: that it must be learnable by new language learners.
Cogswell et al. (2019) introduced cultural transmission within referential games through a changing population of agents to constrain the emerging language to be learnable. However, the resulting languages remain inherently biased by the agents' underlying capabilities.
In this work, we introduce Language Transmission Engine to model both cultural and architectural evolution in a population of agents. As our core contribution, we empirically show that the optimal situation is to take into account also the learning biases of the language learners and thus let language and agents co-evolve. When we allow the agent population to evolve through architectural evolution, we achieve across the board improvements on all considered metrics and surpass the gains made with cultural transmission. These results stress the importance of studying the underlying agent architecture and pave the way to investigate the co-evolution of language and agent in language emergence studies.
LVLMs are Bad at Overhearing Human Referential Communication
Department of Linguistics(语言学系);Institute for Advanced Computational Science(先进计算科学研究所);Department of Psychology(心理学系);Department of Computer Science, Stony Brook University(石溪大学计算机科学系)
University of Amsterdam(阿姆斯特丹大学);Institute of Cognitive Science(认知科学研究所);University of Osnabruek(奥斯纳布吕克大学);Institute for Logic, Language and Computation(逻辑、语言与计算研究所)
GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?
The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Shenzhen Loop Area Institute(深圳河套学院);Hunyuan Team, Tencent(腾讯混元团队);USTB(北京科技大学);DualverseAI;SJTU(上海交通大学);NUS(新加坡国立大学)
How agents see things: On visual representations in an emergent language game
Facebook AI Research(脸书人工智能研究院)
人们越来越感兴趣的语言开发的代理人在紧急通信环境中进行交互。早期的研究集中在代理的符号使用,而不是他们的视觉输入表示。在本文中,我们考虑了Lazaridou et al.(2017)的参考游戏,并研究了代理在其不断发展的交互过程中发展的表示。我们发现,代理建立成功的沟通,诱导视觉表示,几乎完美地相互对齐,但令人惊讶的是,不捕捉输入图像中所描绘的对象的概念属性。我们的结论是,如果我们有兴趣在开发类似语言的通信系统,我们必须更加关注的视觉语义代理相关联的符号,他们使用。
LVLMs and Humans Ground Differently in Referential Communication
Department of Computer Science(计算机科学系);Department of Psychology(心理学系);Department of Linguistics(语言学系);Institute for Advanced Computational Science(先进计算科学研究院)
A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarios
The University of Hong Kong(香港大学);National University of Singapore(新加坡国立大学);Institute for Infocomm Research (I2R), A*STAR(新加坡科技研究局信息通信研究院);Peking University(北京大学);Harbin Institute of Technology(哈尔滨工业大学)
GameXpert-Bench: How Far Are Coding Agents from Expert Game Development?
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Tsinghua University(清华大学);The Hong Kong University of Science and Technology(香港科技大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Lightspeed Studios, Tencent(腾讯光速工作室)