The discovery of scientific formulae that parsimoniously explain natural phenomena and align with existing background theory is a key goal in science. Historically, scientists have derived natural laws by manipulating equations based on existing knowledge, forming new equations, and verifying them experimentally. In recent years, data-driven scientific discovery has emerged as a viable competitor in settings with large amounts of experimental data. Unfortunately, data-driven methods often fail to discover valid laws when data is noisy or scarce. Accordingly, recent works combine regression and reasoning to eliminate formulae inconsistent with background theory. However, the problem of searching over the space of formulae consistent with background theory to find one that best fits the data is not well-solved. We propose a solution to this problem when all axioms and scientific laws are expressible via polynomial equalities and inequalities and argue that our approach is widely applicable. We model notions of minimal complexity using binary variables and logical constraints, solve polynomial optimization problems via mixed-integer linear or semidefinite optimization, and prove the validity of our scientific discoveries in a principled manner using Positivstellensatz certificates. The optimization techniques leveraged in this paper allow our approach to run in polynomial time with fully correct background theory under an assumption that the complexity of our derivation is bounded), or non-deterministic polynomial (NP) time with partially correct background theory. We demonstrate that some famous scientific laws, including Kepler's Third Law of Planetary Motion, the Hagen-Poiseuille Equation, and the Radiated Gravitational Wave Power equation, can be derived in a principled manner from axioms and experimental data.
Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator
Department of Information Science, University of North Texas(北卡罗来纳州立大学信息科学系);Department of Computer Science, North Carolina State University(北卡罗来纳州立大学计算机科学系);Department of Data Science, University of North Texas(得克萨斯大学数据科学系);School of Information Sciences, University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校信息科学学院)
Toward Greater Autonomy in Materials Discovery Agents: Unifying Planning, Physics, and Scientists
Department of Computer Science and Engineering, Texas A&M University(计算机科学与工程系,德克萨斯A&M大学);Department of Materials Science and Engineering, Texas A&M University(材料科学与工程系,德克萨斯A&M大学);Department of Electrical and Computer Engineering, Texas A&M University(电气与计算机工程系,德克萨斯A&M大学);Computing and Data Sciences, Brookhaven National Laboratory(布鲁赫斯国家实验室计算与数据科学部);Department of Physics and Astronomy, Texas A&M University(物理与天文学系,德克萨斯A&M大学)
Self-Evolving Cognitive Framework via Causal World Modeling for Embodied Scientific Intelligence
Graduate School of Advanced Science and Engineering, Hiroshima University(广岛大学先进科学与工程研究生院);Advanced Intelligence and Robotics Research Center, Brain Science Institute, Tamagawa University(玉川大学脑科学研究所先进智能与机器人研究中心)
SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources
Ray and Stephanie Lane Computational Biology Department, School of Computer Science, Carnegie Mellon University(卡内基梅隆大学计算机科学学院Ray and Stephanie Lane计算生物学系);Machine Learning Department, School of Computer Science, Carnegie Mellon University(卡内基梅隆大学计算机科学学院机器学习系)
HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Research
Peking University(北京大学);The University of Hong Kong(香港大学);The Hong Kong University of Science and Technology(香港科技大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)
Mimosa Framework: Toward Evolving Multi-Agent Systems for Scientific Research
Université Côte d’Azur(蔚蓝海岸大学);CNRS(法国国家科学研究中心);ICN(化学研究所);Interdisciplinary Institute for Artificial Intelligence (3iA) Côte d’Azur(蔚蓝海岸跨学科人工智能研究所);Inria(法国国家信息与自动化研究所);I3S(信息系统与软件工程实验室)
Unifying biomedical knowledge in a modern multimodal graph
Department of Biomedical Informatics, Harvard Medical School(哈佛医学院生物医学信息学系);Department of Engineering Science, University of Oxford(牛津大学工程科学系);Edison Scientific Inc.(Edison科学公司);Oxford Suzhou Centre for Advanced Research, University of Oxford(牛津大学苏格兰研究中心);Broad Institute of MIT and Harvard(MIT与哈佛大学Broad研究所);Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University(哈佛大学自然与人工智能研究所);Harvard Data Science Initiative(哈佛大学数据科学计划)
Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents
State Key Laboratory of Multimodal Artificial Intelligence Systems(多模态人工智能系统国家重点实验室);Foundation Model Research Center, Institute of Automation, CAS(自动化研究所基础模型研究中心);University of Chinese Academy of Science, Beijing, China(中国科学院大学,北京,中国);Wuhan AI Research, Wuhan, China(武汉人工智能研究)
Unifying Deductive and Abductive Reasoning in Knowledge Graphs with Masked Diffusion Model
Engineering Hong Kong University of Science;Engineering \ University Beijing China;Key Lab of Education Blockchain;Intelligent Technology \ Normal University Guilin China;Engineering \ University;Intelligent Technology \ Normal University
Owl-AuraID 1.0: An Intelligent System for Autonomous Scientific Instrumentation and Scientific Data Analysis
Shenzhen Loop Area Institute(深圳河套学院);The Chinese University of Hong Kong(香港中文大学);Dalian University of Technology(大连理工大学);Suzhou Laboratory(苏州实验室);The Hong Kong University of Science and Technology(香港科技大学)