Human culture relies on collective innovation: our ability to continuously explore how existing elements in our environment can be combined to create new ones. Language is hypothesized to play a key role in human culture, driving individual cognitive capacities and shaping communication. Yet the majority of models of collective innovation assign no cognitive capacities or language abilities to agents. Here, we contribute a computational study of collective innovation where agents are Large Language Models (LLMs) that play Little Alchemy 2, a creative video game originally developed for humans that, as we argue, captures useful aspects of innovation landscapes not present in previous test-beds. We, first, study an LLM in isolation and discover that it exhibits both useful skills and crucial limitations. We, then, study groups of LLMs that share information related to their behaviour and focus on the effect of social connectivity on collective performance. In agreement with previous human and computational studies, we observe that groups with dynamic connectivity out-compete fully-connected groups. Our work reveals opportunities and challenges for future studies of collective innovation that are becoming increasingly relevant as Generative Artificial Intelligence algorithms and humans innovate alongside each other.
Discovering Adaptive Transmission Programs for Collective Innovation
Flowers AI & CogSci Lab(Flowers AI与认知科学实验室);Inria(法国国家信息与自动化研究所);IT University of Copenhagen(哥本哈根IT大学);Institute for Advanced Study in Toulouse(图卢兹高等研究院)
FernUni LLM Experimental Infrastructure (FLEXI) -- Enabling Experimentation and Innovation in Higher Education Through Access to Open Large Language Models
FernUniversität in Hagen(哈根远程大学);Institut für Bildungswissenschaft und Medienforschung(教育科学与媒体研究所)
Towards unearthing neglected climate innovations from scientific literature using Large Language Models
Grantham Institute for Climate Change and the Environment, Imperial College London(帝国理工学院格兰瑟姆气候变化与环境研究所);Dyson School of Engineering, Imperial College London(帝国理工学院戴森工程学院);Department of Earth Science and Engineering, Imperial College London(帝国理工学院地球科学与工程系)
Intelligent Computing Social Modeling and Methodological Innovations in Political Science in the Era of Large Language Models
Shanghai Academy of Social Sciences(上海社会科学院);Nanjing University(南京大学);Shanghai Jiao Tong University(上海交通大学);Shanghai Institutes for International Studies(上海国际问题研究院)
Can Large Language Models Reinvent Foundational Algorithms?
Xiongan AI Institute(雄安人工智能研究院);Institute for Interdisciplinary Information Sciences, Tsinghua University(清华大学交叉信息研究院);Shanghai Qi Zhi Institute(上海期智研究院);Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);Beijing University of Posts and Telecommunications(北京邮电大学)
Systematic Exploration of Dialogue Summarization Approaches for Reproducibility, Comparative Assessment, and Methodological Innovations for Advancing Natural Language Processing in Abstractive Summarization
SRM Institute of Science and Technology(SRM科学技术学院);SRM University, AP(SRM大学(安得拉邦))
Generative Emergent Communication: Large Language Model is a Collective World Model
Graduate School of Informatics, Kyoto University(京都大学信息科学研究生院);Graduate School of Engineering, The University of Tokyo(东京大学工学研究生院);Graduate School of Informatics and Engineering, The University of Electro-Communications(电通大学信息科学和工学研究生院);College of Information Science and Engineering, Ritsumeikan University(立命馆大学信息科学和工学学院)
CollectiveSFT: Scaling Large Language Models for Chinese Medical Benchmark with Collective Instructions in Healthcare
School of Software Engineering(软件工程学院);University of Science and Technology of China(中国科学技术大学);Shenzhen Institute of Advanced Technology(深圳先进技术研究院);Chinese Academy of Sciences(中国科学院);Xiangshui County Party School(响水县党校);School of Biomedical Engineering(生物医学工程学院);UNSW(新南威尔士大学)
Regulatory Science Innovation for Generative AI and Large Language Models in Health and Medicine: A Global Call for Action
Singapore General Hospital(新加坡中央医院);Duke-NUS Medical School(杜克-新加坡国立大学医学院);University of California, San Francisco(加州大学旧金山分校);Stanford University School of Medicine(斯坦福大学医学院);Byers Eye Institute(拜尔斯眼科研究所);Singapore Health Services(新加坡医疗服务机构);TUD Dresden University of Technology(德累斯顿工业大学);Mass General Brigham(麻省总医院布里格姆医疗系统);Harvard Medical School(哈佛医学院);Brigham and Women’s Hospital(布莱根妇女医院);Dana-Farber Cancer Institute(达纳-法伯癌症研究所);University of Birmingham(伯明翰大学);University Hospitals Birmingham NHS Foundation Trust(伯明翰大学医院NHS基金会信托);National University of Singapore(新加坡国立大学);NUS Artificial Intelligence Institute(新加坡国立大学人工智能研究院)
Probabilistic Aggregation and Targeted Embedding Optimization for Collective Moral Reasoning in Large Language Models
School of Computation, Information and Technology, Technical University of Munich(计算、信息与技术学院,慕尼黑技术大学);School of Social Sciences and Technology, Technical University of Munich(社会科学与技术学院,慕尼黑技术大学)
Balancing Innovation and Privacy: Data Security Strategies in Natural Language Processing Applications
University of Southern California(南加州大学);San Francisco State University(旧金山州立大学);Southwest Jiaotong University(西南交通大学);Columbia University(哥伦比亚大学);Carnegie Mellon University(卡内基梅隆大学)
Artificial Intelligence and Natural Language Processing and Understanding in Space: A Methodological Framework and Four ESA Case Studies
European Space Research and Technology Centre (ESA-ESTEC)(欧洲空间研究与技术中心);European Space Research Institute (ESA-ESRIN)(欧洲空间研究所);European Space Agency (ESA)(欧洲空间局);European Space Operations Center (ESA-ESOC)(欧洲空间运营中心)
Innovation: An Almost Characterization of Hallucination
School of Technology and Computer Science, Tata Institute of Fundamental Research, Mumbai, Maharashtra - 400 005, India(技术与计算机科学学院,塔塔基础研究机构,孟买,马哈拉施特拉邦 - 400 005, 印度)
Towards Optimal Circuit Generation: Multi-Agent Collaboration Meets Collective Intelligence
National Key Laboratory of Spintronics, Hangzhou International Innovation Institute(国家磁电子键实验室、杭州国际创新研究院;集成电路科学与工程学院,北京航空航天大学);School of Integrated Circuit Science and Engineering, Beihang University(机械电子工程学院,武汉理工大学);School of Mechanical and Electronic Engineering, Wuhan University of Technology(数学与物理科学学院,谢菲尔德大学);School of Mathematical and Physical Sciences, University of Sheffield
OpenClaw-Skill: Collective Skill Tree Search for Agentic Large Language Models
The Hong Kong Polytechnic University(香港理工大学);Nanyang Technological University(南洋理工大学);Tsinghua University(清华大学);Royal Melbourne Institute of Technology(皇家墨尔本理工大学);Beijing University of Aeronautics and Astronautics(北京航空航天大学)
Alignment as Iatrogenesis: Pastoral Power, Collective Pathology, and the Structural Limits of Monolingual Safety Evaluation
Research Institute of Criminal Psychiatry(刑事精神病研究所以);Sex Offender Medical Center(性犯罪医疗中心);Department of Neuropsychiatry, Graduate School of Medicine, Kyoto University(京都大学医学研究生院神经精神病学系)