Data-driven social science research is inherently slow, relying on iterative cycles of observation, hypothesis generation, and experimental validation. While recent data-driven methods promise to accelerate parts of this process, they largely fail to support end-to-end scientific discovery. To address this gap, we introduce EXPERIGEN, an agentic framework that operationalizes end-to-end discovery through a Bayesian optimization inspired two-phase search, in which a Generator proposes candidate hypotheses and an Experimenter evaluates them empirically. Across multiple domains, EXPERIGEN consistently discovers 2-4x more statistically significant hypotheses that are 7-17 percent more predictive than prior approaches, and naturally extends to complex data regimes including multimodal and relational datasets. Beyond statistical performance, hypotheses must be novel, empirically grounded, and actionable to drive real scientific progress. To evaluate these qualities, we conduct an expert review of machine-generated hypotheses, collecting feedback from senior faculty. Among 25 reviewed hypotheses, 88 percent were rated moderately or strongly novel, 70 percent were deemed impactful and worth pursuing, and most demonstrated rigor comparable to senior graduate-level research. Finally, recognizing that ultimate validation requires real-world evidence, we conduct the first A/B test of LLM-generated hypotheses, observing statistically significant results with p less than 1e-6 and a large effect size of 344 percent.
Iteris: Agentic Research Loops for Computational Mathematics
School of Mathematical Sciences, Peking University(北京大学数学科学学院);Beijing International Center for Mathematical Research and the New Cornerstone Science Laboratory, Peking University(北京大学北京国际数学研究中心和新基石科学实验室);Center for Machine Learning Research, Peking University(北京大学机器学习研究中心);Center for Intelligent Computing, Great Bay Institute for Advanced Study, Great Bay University(大湾研究院先进研究所智能计算中心);Zhongguancun Academy(中关村学院)
A Practical Guide to Agentic AI Transition in Organizations
Old Dominion University(旧 Dominion 大学);Florida International University(佛罗里达国际大学);Nanyang Technological University(南洋理工大学);University of Colombo(科伦坡大学);Center for Wireless Communications, University of Oulu(无线通信中心,奥卢大学);University of Sri Jayewardenepura(斯里贾yenepura大学);Accenture Technology Labs(埃森哲技术实验室)
Agentic Workflow for Education: Concepts and Applications
East China Normal University(华东师范大学);Shanghai Institute of Artificial Intelligence for Education(上海人工智能教育研究院);Nanyang Technological University(南洋理工大学);National Institute of Education(国立教育学院)
SANEmerg: An Emergent Communication Framework for Semantic-aware Agentic AI Networking
1 School of Elect. Inform. \& Commun., Huazhong Univ. of Science \& Technology, China;2 Peng Cheng Laboratory, Shenzhen, China;3 Pazhou Laboratory (Huangpu), Guangzhou, China;4 Department of Electrical;Computer Engineering, the University of Arizona
The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning
Department for AI in Society, Science, and Technology(人工智能与社会、科学和技术部门);Zuse Institute Berlin(柏林Zuse研究所);Institute of Mathematics(数学研究所);Technische Universität Berlin(柏林技术大学)
Agentic Exploration of PDE Spaces using Latent Foundation Models for Parameterized Simulations
University of Michigan(密歇根大学);Universidad Politécnica de Madrid(马德里理工大学);Purdue University(普渡大学);Universitat Politècnica de València(瓦伦西亚理工大学);Caltech(加州理工学院);University of Washington(华盛顿大学)
La Agente Óptima: Towards Agentic Self-Driving Laboratories
University of Toronto(多伦多大学);Acceleration Consortium(加速联盟);Vector Institute for Artificial Intelligence(向量人工智能研究所);Canadian Institute for Advanced Research (CIFAR)(加拿大高级研究院);NVIDIA(英伟达);University of Amsterdam(阿姆斯特丹大学);Instituto de Micro y Nanotecnología, IMN-CNM, CSIC(西班牙国家研究委员会微纳米技术研究所);Sungkyunkwan University(成均馆大学);Merck KGaA(默克集团)
Centre for Longitudinal Studies, University College London(伦敦大学学院长期研究所在);Centre for Advanced Research Computing, University College London(伦敦大学学院先进计算研究中心)
From Phase Prediction to Phase Design: A ReAct Agent Framework for High-Entropy Alloy Discovery
Luxembourg Institute of Science and Technology (LIST)(卢森堡科学与技术研究院);Department of Physics and Materials Science, University of Luxembourg(卢森堡大学物理与材料科学系)
SciHorizon-eLab: An Agentic Protocol-to-Task Compiler for Scalable Benchmarking of Scientific Embodied Agents
Data Intelligence for Scientific Innovation Lab, Computer Network Information Center, Chinese Academy of Sciences(中国科学院计算机网络信息中心科学智能创新数据实验室);Beihang University(北京航空航天大学)
Spec-Driven AI for Science: The ARIA Framework for Automated and Reproducible Data Analysis
School of Environment, Tsinghua University(清华大学环境学院);Shanghai HiQ Smart Data Co., Ltd.(上海HiQ智能数据有限公司);State Key Laboratory of Iron and Steel Industry Environmental Protection, Tsinghua University(清华大学钢铁工业环境保护国家重点实验室);School of Management Science and Engineering, Beijing Information Science & Technology University(北京信息科技大学管理科学与工程学院)