Large language models contain noisy general knowledge of the world, yet are hard to train or fine-tune. On the other hand cognitive architectures have excellent interpretability and are flexible to update but require a lot of manual work to instantiate. In this work, we combine the best of both worlds: bootstrapping a cognitive-based model with the noisy knowledge encoded in large language models. Through an embodied agent doing kitchen tasks, we show that our proposed framework yields better efficiency compared to an agent based entirely on large language models. Our experiments indicate that large language models are a good source of information for cognitive architectures, and the cognitive architecture in turn can verify and update the knowledge of large language models to a specific domain.
Web-CogReasoner: Towards Multimodal Knowledge-Induced Cognitive Reasoning for Web Agents
Southwestern University of Finance and Economics(西南财经大学);Shanghai Jiao Tong University(上海交通大学);Central South University(中南大学);Hithink Research(Hithink研究);Westlake University(西湖大学);Harbin Institute of Technology(哈尔滨工业大学);University of Manchester(曼彻斯特大学);University of California, Los Angeles(加州大学洛杉矶分校);University of Adelaide(阿德莱德大学);Fudan University(复旦大学);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);Chengdu Everimaging Science and Technology Co., Ltd(成都亿联科技有限公司)
BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling
Microsoft Research(微软研究院);The University of Manchester, UK(英国曼彻斯特大学);Nanjing University, China(南京大学);Imperial College London, Imperial Global Singapore, Singapore(伦敦帝国学院,新加坡帝国全球分校,新加坡);The University of Tokyo, Japan(日本东京大学)
Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents
Department of Computer Science, Princeton University(普林斯顿大学计算机科学系);Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology(麻省理工学院脑科学与认知科学系);Zuckerman Mind Brain Behavior Institute(祖克曼心智大脑行为研究所);Department of Psychiatry, Columbia University(哥伦比亚大学精神医学系);Neuroscience Institute(神经科学研究所);Department of Machine Learning, Carnegie Mellon University(卡内基梅隆大学机器学习系);Department of Psychology, Princeton University(普林斯顿大学心理学系)
Evaluating Cognitive Age Alignment in Interactive AI Agents
University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Shenzhen Children's Hospital(深圳儿童医院);Peking University(北京大学);Hong Kong Polytechnic University(香港理工大学)
NuHF Claw: A Risk Constrained Cognitive Agent Framework for Human Centered Procedure Support in Digital Nuclear Control Rooms
Institute of Nuclear and New Energy Technology, Tsinghua University(清华大学核能与新能源技术研究院);National Key Laboratory of Human Factors Engineering(人因工程国家重点实验室);Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所)
Socratic-Zero : Bootstrapping Reasoning via Data-Free Agent Co-evolution
Alibaba Group Holding Limited(阿里巴巴集团控股有限公司);EPIC Lab, Shanghai Jiao Tong University(上海交通大学EPIC实验室);Shanghai University of Finance and Economics(上海财经大学);Wuhan University(武汉大学);Zhejiang University(浙江大学)
Think Before You Comfort: Reflective Cognitive Alignment for Protocol-Grounded Elderly Stimulation Agents
The Chinese University of Hong Kong(香港中文大学);The University of Hong Kong(香港大学);Guangdong Provincial Laboratory of Artificial Intelligence and Digital Economy (Shenzhen)(广东省人工智能与数字经济实验室(深圳))
Bootstrapping Conversational Agents With Weak Supervision
IBM Watson(IBM沃森);IBM Research AI(IBM研究院人工智能部门)
当今市场上的许多会话代理遵循标准的机器人开发框架,该框架需要训练意图分类器来识别用户输入。创建一组合适的训练样本的需求通常是开发过程中的瓶颈。在许多情况下,代理开发人员可以访问历史聊天日志,这些日志可以提供大量的训练样本。然而,用数十到数百个意图标记它们的成本通常会阻止充分利用这些聊天日志。在本文中,我们提出了一个框架称为\textit{search, label, and propagate}(SLP)的引导意图从现有的聊天日志使用弱监督。该框架通过使用搜索引擎查找示例,将数小时到数天的标记工作减少到几分钟的工作,然后依靠数据编程方法自动扩展标签。我们报告的用户研究,显示积极的用户反馈,这种新的方法来建立对话代理,并证明了使用数据编程自动标记的有效性。虽然该系统是为训练会话代理而开发的,但该框架在显着减少训练文本分类器的标记工作方面具有更广泛的应用。
Measuring Cognitive Engagement in Collaborative Discourse with an Extended ICAP Framework: Comparing Human Annotation, In-Context Learning, and Reflective LLM Agents