LegoSR: A Unified Framework for Self-Improving Agent-Guided Scientific Discovery
The Hong Kong Polytechnic University(香港理工大学);Eastern Institute of Technology(宁波东方理工大学);Amazon Web Services(亚马逊云科技);University of Washington(华盛顿大学);Beijing EEO Education Technology(北京EEO教育科技);Jiangxi University of Finance and Economics(江西财经大学)
Discovering equations from data provides governing laws, constitutive relations and closure models for scientific understanding and prediction. Yet a method that succeeds on one system may fail on another or on noisy data, so discovery depends on expert trial and error. Unsuccessful searches can still reveal useful parts of an equation, but these clues must be recognized and combined. We present LegoSR, a unified framework for agent-guided equation discovery built on composable discovery and cumulative experience. Seven complementary equation discovery methods and shared computational modules form reusable building blocks, connected through a common equation representation. Researchers can launch discovery with one command and guide it with partially known equations. LegoSR Agent selects methods, revises searches using feedback and combines partial findings into new hypotheses. Its Experience Library consolidates graded outcomes into lessons that guide later tasks across equation families. Evaluation covers 134 algebraic regression problems, 40 ordinary differential equation targets and 25 partial differential equation problems at several noise levels, together with three case studies. On noisy PDEs, LegoSR Agent recovers more equations than seven expert-tuned methods combined and stays close to them on ODEs. It also exceeds a generic agent with the same model, tools and budget by up to 28 percentage points, with 63-73% shorter median wall-clock time on PDE problems.
Theory-guided hard constraint projection (HCP): a knowledge-based data-driven scientific machine learning method
Peng Cheng Laboratory(鹏城实验室);The University of Tokyo(东京大学);Southern University of Science and Technology(南方科技大学);Peking University(北京大学);Malardalen University(马拉达伦大学);LocationMind Inc.(LocationMind公司)
Theory-guided Data Science: A New Paradigm for Scientific Discovery from Data
University of Minnesota(明尼苏达大学);University of Cincinnati(辛辛那提大学);Icahn School of Medicine at Mount Sinai(西奈山伊坎医学院);Northeastern University(东北大学);North Carolina State University(北卡罗来纳州立大学)
BayesEvolve: Explicit Belief States for Autonomous Scientific Discovery
Pfizer(辉瑞公司);Independent Researcher(独立研究员);University of California San Diego(加州大学圣地亚哥分校);Institute of Humanities and Social Science Data, Fudan University(复旦大学人文社会科学数据研究院)
Deploy-Master: Automating the Deployment of 50,000+ Agent-Ready Scientific Tools in One Day
DP Technology Beijing China(DP技术北京中国);AI for Science Institute Beijing China(AI for Science研究院北京中国);Shanghai Jiao Tong University Shanghai China(上海交通大学上海中国)
SPARK: Skeleton-Guided Reasoning Synthesis from Large-Scale Scientific Literature
Shanghai AI Laboratory(上海人工智能实验室);University of Science and Technology of China(中国科学技术大学);East China Normal University(华东师范大学);Peking University(北京大学);Renmin University of China(中国人民大学)
InsightGUIDE: An Opinionated AI Assistant for Guided Critical Reading of Scientific Literature
Information Management Systems Institute(信息管理系统研究所);ATHENA Research Centre(ATHENA研究中心);Department of Informatics and Telecommunications(信息与电信系);University of the Peloponnese(希腊皮埃里亚大学)
Automated Algorithmic Discovery for Scientific Computing through LLM-Guided Evolutionary Search: A Case Study in Gravitational-Wave Detection
International Centre for Theoretical Physics Asia-Pacific(国际理论物理中心亚太中心);University of Chinese Academy of Sciences(中国科学院大学);Taiji Laboratory for Gravitational Wave Universe(引力波宇宙Taiji实验室);Tsinghua University(清华大学)
FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration
University of Chinese Academy of Sciences(中国科学院大学);Dalian University of Technology(大连理工大学);UNSW Sydney(新南威尔士大学悉尼分校);Shenzhen University of Advanced Technology(深圳理工大学);Xiamen University(厦门大学)
Compass: Navigating Global Marine Lead Data Integration through Expert-Guided LLM Agent
School of Information Science;Electronic Engineering,\ Jiao Tong University Shanghai China;School of Artificial Intelligence,\ Jiao Tong University Shanghai China;State Key Laboratory of Estuarine;Coastal Research,\ China Normal University Shanghai China;School of Oceanography,\ Jiao Tong University Shanghai China;Institute of Geographical Science;Natural Resources Research,\ Academy of Sciences Beijing China;Electronic Engineering,\ Jiao Tong University;School of Artificial Intelligence,\ Jiao Tong University;Coastal Research,\ China Normal University;School of Oceanography,\ Jiao Tong University;Natural Resources Research,\ Academy of Sciences
ScienceCUA: Resource-to-Skill Construction and Execution-Guided Skill Evolution for Scientific Computer Use Agents
DeepAutonomy Technology Co., Ltd.(深度自主科技有限公司);Peking University(北京大学);College of AI, Tsinghua University(清华大学人工智能学院);The Hong Kong Polytechnic University(香港理工大学);Singapore Management University(新加坡管理大学)
Physics-Guided Multimodal Transformers are the Necessary Foundation for the Next Generation of Meteorological Science
School of Artificial Intelligence, Beijing University of Posts;Huawei Noah's Ark Lab;Department of Earth System Science, Tsinghua University;College of Computing \& Data Science, Nanyang Technological University;State Key Laboratory of Networking;Switching Technology, Beijing University of Posts
Budget-Sensitive Discovery Scoring: A Formally Verified Framework for Evaluating AI-Guided Scientific Selection
Indian Institute of Information Technology Allahabad (IIITA)(印度阿瓦德理工学院信息学院(IIITA));National Institute of Electronics & Information Technology (NIELIT)(国家电子与信息科技研究所(NIELIT))
MatPhaseBench: A Semantics-Guided Benchmark for Materials Phase Diagrams Understanding
Computer Network Information Center, Chinese Academy of Sciences(中国科学院计算机网络信息中心);University of Chinese Academy of Sciences(中国科学院大学);University of Manchester(曼彻斯特大学);Institute of Metal Research, Chinese Academy of Sciences(中国科学院金属研究所);China University of Geosciences(中国地质大学)
Learning-guided Kansa collocation for forward and inverse PDEs beyond linearity
Department of Computer Science and Technology(计算机科学与技术系);Department of Applied Mathematics and Theoretical Physics(应用数学与理论物理系);University of Cambridge(剑桥大学)
Discovery of Interpretable Physical Laws in Materials via Language-Model-Guided Symbolic Regression
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);School of Physics(物理学院);Hefei National Laboratory(合肥国家实验室);Institute for Advanced Study in Physics(物理高级研究学院);Shenzhen Institute of Advanced Technology(深圳先进技术研究院)
VDSAgents: A PCS-Guided Multi-Agent System for Veridical Data Science Automation
School of Management, Xi’an Jiaotong University(西安交通大学管理学院);School of Computing, National University of Singapore(新加坡国立大学计算机学院);School of Data Science and Media Intelligence, Communication University of China(中国传媒大学数据科学与媒体智能学院);Beijing Baixingkefu Network Technology Co., Ltd.(北京百星科技网络技术有限公司)
SciWalker: Synthesizing Scientific Coding Problems with Operator Graphs and Execution Feedback
The Hong Kong University of Science and Technology(香港科技大学);Shanghai AI Laboratory(上海人工智能实验室);Tsinghua University(清华大学);Nanyang Technological University(南洋理工大学)
Delegating Earth science model calibration to knowledge-guided LLM agents
State Key Laboratory of Water Disaster Prevention, Hohai University(河海大学水灾害防御国家重点实验室);Yangtze Institute for Conservation and Development, Hohai University(河海大学长江保护与发展研究院);Meta Platforms Inc.(Meta平台公司);Nanjing Hydraulic Research Institute(南京水利科学研究院)
Scientific Logicality Enriched Methodology for LLM Reasoning: A Practice in Physics
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China;Beijing Wenge Technology Co., Ltd, Beijing, China;School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China