Human-guided Collaborative Problem Solving: A Natural Language based Framework
University of Texas at Dallas(德克萨斯大学达拉斯分校);Microsoft Research India(微软印度研究院);Washington State University(华盛顿州立大学);University of Colorado Boulder(科罗拉多大学博尔德分校);University of Pennsylvania(宾夕法尼亚大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
Harsha Kokel, Mayukh Das, Rakibul Islam, Julia Bonn, Jon Cai, Soham Dan, Anjali Narayan-Chen, Prashant Jayannavar, Janardhan Rao Doppa, Julia Hockenmaier, Srira… 展开作者
Harsha Kokel, Mayukh Das, Rakibul Islam, Julia Bonn, Jon Cai, Soham Dan, Anjali Narayan-Chen, Prashant Jayannavar, Janardhan Rao Doppa, Julia Hockenmaier, Sriraam Natarajan, Martha Palmer, Dan Roth
We consider the problem of human-machine collaborative problem solving as a planning task coupled with natural language communication. Our framework consists of three components -- a natural language engine that parses the language utterances to a formal representation and vice-versa, a concept learner that induces generalized concepts for plans based on limited interactions with the user, and an HTN planner that solves the task based on human interaction. We illustrate the ability of this framework to address the key challenges of collaborative problem solving by demonstrating it on a collaborative building task in a Minecraft-based blocksworld domain. The accompanied demo video is available at https://youtu.be/q1pWe4aahF0.
Exploring Communication Strategies for Collaborative LLM Agents in Mathematical Problem-Solving
Institute for Intelligent Systems, University of Memphis, Memphis, TN, USA(智能系统研究所,密苏里大学);Department of Electrical and Computer Engineering, University of Memphis, Memphis, TN, USA(电气与计算机工程系,密苏里大学);AI4STEM Education Center, University of Georgia, Athens, GA, USA(AI4STEM教育中心,佐治亚大学);National GENIUS Center, Athens, GA, USA(国家GENIUS中心);Department of Mathematics, Science, and Social Studies Education, University of Georgia, Athens, GA, USA(数学、科学与社会科学教育系,佐治亚大学);Faculty of Education, The University of Hong Kong, Hong Kong, PR China(教育学院,香港大学);Educational Testing Service, Princeton, NJ, USA(教育测评服务);Department of Applied Social Sciences, Hong Kong Polytechnic University, Hong Kong, PR China(应用社会科学系,香港理工大学);Department of Psychology, University of Memphis, Memphis, TN, USA(心理学系,密苏里大学)
该研究使用 GPT-4o 在 MATH 数据集上比较双智能体数学解题的四种沟通模式,发现同伴协作准确率最高,并表明有效对话行为是提升 AI 教育协作解题的关键。
Between Sense and Sensibility: Declarative narrativisation of mental models as a basis and benchmark for visuo-spatial cognition and computation focussed collaborative cognitive systems
University of Bremen(不来梅大学)
“\emph{sensing}”和“\emph{sensibility}”之间有什么区别?换句话说,什么样的认知过程介导了感知能力和可感知印象的形成-例如,抽象,类比,假设和理论的形成,信念和他们的修正,论点的形成-在特定领域的问题解决中,还是在日常生活,工作和简单地在环境中走动的常规活动中?如何才能知识和推理的能力,表现出人类在特定的问题背景下,被用来作为一个模型和基准的发展与人类的援助,保证和授权的协作认知(互动)系统?我们提出这些问题的背景下,一系列的辅助技术与\emph{visuo-spatial perception and cognition}任务,包括方面,如常识,创造力,专业领域的知识和解决问题的思维过程的应用。正在考虑的辅助技术包括:(a)人类活动解释;(b)高级认知旋转;(c)建筑和数字媒体创作等领域以人为本的创造性设计;(d)地理信息系统的定性分析。计算叙事不仅提供了丰富的认知基础,但他们也作为一个基准的功能性能在我们的发展计算认知辅助系统。我们认为,有关空间,行动和变化的计算叙事提供了一个有用的模型\emph{visual}和\emph{spatio-temporal thinking}在广泛的解决问题的任务和应用领域,协作认知系统可以提供一个辅助和授权功能。