Frontier scientific reasoning is rapidly emerging as a key foundation for advancing AI agents in automated scientific discovery. Deep research agents offer a promising approach to this challenge. These models develop robust problem-solving capabilities through post-training on information-seeking tasks, which are typically curated via knowledge graph construction or iterative web browsing. However, these strategies face inherent limitations in frontier science, where domain-specific knowledge is scattered across sparse and heterogeneous academic sources, and problem solving requires sophisticated computation and reasoning far beyond factual recall. To bridge this gap, we introduce SciResearcher, a fully automated agentic framework for frontier-science data construction. SciResearcher synthesizes diverse conceptual and computational tasks grounded in academic evidence, while eliciting information acquisition, tool-integrated reasoning, and long-horizon capabilities. Leveraging the curated data for supervised fine-tuning and agentic reinforcement learning, we develop SciResearcher-8B, an agent foundation model that achieves 19.46% on the HLE-Bio/Chem-Gold benchmark, establishing a new state of the art at its parameter scale and surpassing several larger proprietary agents. It further achieves 13-15% absolute gains on SuperGPQA-Hard-Biology and TRQA-Literature benchmarks. Overall, SciResearcher introduces a new paradigm for automated data construction for frontier scientific reasoning and offers a scalable path toward future scientific agents.
SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks
Imperial College London(伦敦帝国学院);The Chinese University of Hong Kong(香港中文大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Shanghai Jiao Tong University(上海交通大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);University of Oxford(牛津大学);Shenzhen Loop Area Institute(深圳河套学院)
A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Monash University(莫纳什大学);Fudan University(复旦大学);Shanghai Jiao Tong University(上海交通大学);The Chinese University of Hong Kong(香港中文大学);University College London(伦敦大学学院);UNC-Chapel Hill(北卡罗来纳大学教堂山分校);Stanford University(斯坦福大学);Virginia Tech(弗吉尼亚理工大学);Purdue University(普渡大学);China Pharmaceutical University(中国药科大学);Beijing Institute of Heart, Lung and Blood Vessel Diseases(北京市心肺血管疾病研究所);Chinese Academy of Sciences(中国科学院);Johns Hopkins University(约翰斯·霍普金斯大学);Fuzhou University(福州大学);University of New South Wales(新南威尔士大学);University College Dublin(都柏林大学学院);The University of Hong Kong(香港大学);The Hong Kong Polytechnic University(香港理工大学);The Hong Kong University of Science and Technology(香港科技大学);South China University of Technology(华南理工大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Caltech(加州理工学院);North University of China(中北大学);MBZUAI(穆罕默德·本·扎耶德人工智能大学);University of Cambridge(剑桥大学);Nanjing University(南京大学)
Molecular LLM Agents: From Architectural Design to Scientific Autonomy
The Hong Kong Polytechnic University(香港理工大学);Shanghai AI Lab(上海人工智能实验室);National University of Singapore(新加坡国立大学);Shanghai Jiao Tong University(上海交通大学)
Science sandboxes measure the scientific capability of AI agents
The Broad Institute of MIT and Harvard(麻省理工学院与哈佛大学博德研究所);Harvard Medical School(哈佛医学院);The Jackson Laboratory(杰克逊实验室);Sutter Hill Ventures(萨特山风投);Massachusetts Institute of Technology(麻省理工学院);Howard Hughes Medical Institute(霍华德·休斯医学研究所);The Wyss Institute for Biologically Inspired Engineering at Harvard University(哈佛大学维斯生物启发工程研究所);Yale School of Medicine(耶鲁医学院);Harvard T.H. Chan School of Public Health(哈佛陈曾熙公共卫生学院);Harvard University(哈佛大学)
Benchmark Illusion: Disagreement among LLMs and Its Scientific Consequences
Department of Political Science, Purdue University(政治学系,普渡大学);Kellogg School of Management, Center for Science of Science and Innovation, Northwestern Innovation Institute, Ryan Institute on Complexity, and McCormick School of Engineering(凯洛格管理学院、科学与创新中心、西北创新研究所、复杂性研究院以及麦科马克工程学院)
PortexAI;University of Milano-Bicocca(米兰-比科卡大学);University of Calgary(卡尔加里大学);University of Chicago(芝加哥大学);Inria(法国国家信息与自动化技术研究院);Fraunhofer Institute for Individualized Medical Technology IMTE(弗劳恩霍夫个性化医疗技术研究所);University of Cambridge(剑桥大学);Independent(独立);McGill University(麦吉尔大学);Massachusetts Institute of Technology(麻省理工学院);École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院);Queen Mary University of London(伦敦大学玛丽女王学院);Dot Ingredients;National University of Singapore(新加坡国立大学);Georgia Institute of Technology(佐治亚理工学院);University of Edinburgh(爱丁堡大学);Murdoch University(墨尔本大学);University of Porto(波尔图大学);Stanford University(斯坦福大学);Stony Brook University(史泰津布鲁克大学)
From Research Goals to Scientific Closure: Evaluating Agents Through Evidence-Supported Physics Research
Shanghai AI Laboratory(上海人工智能实验室);Shanghai Jiao Tong University(上海交通大学);The HongKong University of Science and Technology(Guangzhou)(香港科技大学(广州));Nanyang Technological University(南洋理工大学)
AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?
MIT(麻省理工学院);Stanford University(斯坦福大学);University of California, Berkeley(加州大学伯克利分校);University of California, Los Angeles(加州大学洛杉矶分校);University of California, San Diego(加州大学圣地亚哥分校);University of Washington(华盛顿大学);University of Toronto(多伦多大学);University of Michigan(密歇根大学);National University of Singapore(新加坡国立大学);University of Tokyo(东京大学)
Advancing the Scientific Frontier with Increasingly Autonomous Systems
NASA Jet Propulsion Laboratory(美国国家航空航天局喷气推进实验室);University of California, Berkeley(加州大学伯克利分校);NASA Ames Research Center(美国国家航空航天局艾姆斯研究中心);Okean Solutions(Okean Solutions公司);NASA Goddard Space Flight Center(美国国家航空航天局戈达德太空飞行中心);Johns Hopkins University Applied Physics Laboratory(约翰斯·霍普金斯大学应用物理实验室);Southwest Research Institute(西南研究院);Arizona State University(亚利桑那州立大学)
PRL-Bench: A Comprehensive Benchmark Evaluating LLMs' Capabilities in Frontier Physics Research
School of Artificial Intelligence(人工智能学院);Zhiyuan College(智远学院);School of Physics and Astronomy(物理天文学院);Tsung-Dao Lee Institute(李政道研究所);State Key Laboratory of Dark Matter Physics(暗物质物理国家重点实验室);Shanghai Innovation Institute(上海创新研究院);Institute of Theoretical Physics(理论物理研究所);Chinese Academy of Sciences(中国科学院);Zhejiang Lab(浙江实验室);SciLand;DP Technology(DP技术)
Sci$Π$vot: Benchmarking Principal-Investigator Judgment at Pivotal Moments of Scientific AutoResearch Agents
University of Maryland, College Park(马里兰大学帕克分校);Gradient Network;Stanford University(斯坦福大学);The Chinese University of Hong Kong(香港中文大学);Dartmouth College(达特茅斯学院);University of California, Los Angeles(加州大学洛杉矶分校)
Evaluating Frontier LLMs on PhD-Level Mathematical Reasoning: A Benchmark on a Textbook in Theoretical Computer Science about Randomized Algorithms
Wyoming Seminary(怀俄明神学院);San Jose State University(圣何塞州立大学);Guilin University of Electronic Technology(桂林电子科技大学);University of California, Berkeley(加州大学伯克利分校);Northeastern University(东北大学);Guangdong University of Technology(广东工业大学)