Customize Consent Preferences

We use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below.

The cookies that are categorized as "Necessary" are stored on your browser as they are essential for enabling the basic functionalities of the site. ... 

Always Active

Necessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.

No cookies to display.

Functional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.

No cookies to display.

Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.

No cookies to display.

Performance cookies are used to understand and analyze the key performance indexes of the website which helps in delivering a better user experience for the visitors.

No cookies to display.

Advertisement cookies are used to provide visitors with customized advertisements based on the pages you visited previously and to analyze the effectiveness of the ad campaigns.

No cookies to display.

0

上海,2025年3月18日 – 还记得那款让你和朋友“友尽”的《分手厨房》(Overcooked)吗?这款以实时协作烹饪为主题的游戏,凭借其高压的节奏和对团队默契的极致考验,成为了无数玩家的“爱情/友情检测器”。如今,上海交通大学SJTU-MARL实验室与AGI-Eval评测社区联合团队带来了一项创新研究,或许能让你在游戏中告别手忙脚乱,不再“糊锅”。

该团队由上海交通大学博士生张劭(导师:温颖副教授)和王锡淮(导师:张伟楠教授)领衔,通讯作者为上海交通大学人工智能学院副教授温颖。他们聚焦于大模型在实时同步交互协作中的应用,并针对《Overcooked》这款经典游戏,开发了DPT-Agent框架Overcooked Challenge实时同步协作评估环境

在春节期间DeepSeek大模型引发热潮后,人们对大模型的期望也日益高涨。然而,目前许多大模型的应用仍停留在静态的问答和推理层面,与现实世界中复杂的人机交互场景存在较大差距。尽管如Manus等项目试图探索LLM Agent与人的实时协作,但其交互模式更像是回合制,无法实现真正的实时响应和同步协作。

《Overcooked》作为一款强调实时性和强交互性的游戏,为研究人机实时同步协作提供了一个理想的测试平台。游戏中,玩家需要在有限的时间内,与队友分工合作,完成切菜、煎肉、组装汉堡等任务,并时刻注意灭火。这种高压环境对玩家的反应速度和协作能力提出了极高的要求。

上海交大的研究团队正是看到了这一点,他们对Overcooked-AI环境进行了升级,加入了更复杂的菜谱,并还原了游戏的实时协作机制,让大模型能够参与到这场协作游戏中,直面同步实时协作的挑战。

DPT-Agent框架的亮点包括:

  • 预判式协作: 在你切菜时,AI助手能迅速递上盘子;当牛排烧焦时,它会抢先一步灭火。
  • 动态分工: 根据订单的优先级,AI助手能够自动切换“主厨”和“帮工”的角色,有效安排时间。
  • 读心级配合: AI助手甚至能够通过你的动作历史,推测出你想要制作汉堡还是沙拉。

这项研究的核心在于利用大模型实现真正的人机实时同步协作,解决传统Agent在快速响应和推断用户意图方面的挑战。通过DPT-Agent框架,AI助手不再是被动地等待指令,而是能够主动地参与到协作过程中,与人类玩家形成默契的配合。

该研究成果已发表在论文《Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI Collaboration》中,并开源了DPT-Agent框架和Overcooked Challenge环境。感兴趣的读者可以在GitHub上找到相关资源,亲自体验大模型与你在《分手厨房》中并肩作战的乐趣。

参考文献:

  • Zhang, S., Wang, X., et al. (2025). Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI Collaboration. arXiv preprint arXiv:2502.11882.
  • DPT-Agent项目地址: https://github.com/sjtu-marl/DPT-Agent

(本文由机器之心根据上海交通大学SJTU-MARL实验室与AGI-Eval评测社区联合团队的研究成果撰写。)


>>> Read more <<<

Views: 0

0

发表回复

您的邮箱地址不会被公开。 必填项已用 * 标注