MoLRSI: A Recursive Self-Improving AI agent for Molecular Discovery
Northeastern University(东北大学);Broad Institute of MIT and Harvard(麻省理工学院与哈佛大学博德研究所);Harvard University(哈佛大学);Wyss Institute for Biologically Inspired Engineering, Harvard University(哈佛大学怀斯生物启发工程研究所);Massachusetts Institute of Technology(麻省理工学院);University of California, Berkeley(加州大学伯克利分校);University of Toronto(多伦多大学);The Ohio State University(俄亥俄州立大学);University of Washington(华盛顿大学);Howard Hughes Medical Institute(霍华德·休斯医学研究所);Yale University(耶鲁大学);Microsoft Research New England(微软研究院新英格兰分部);Massachusetts General Hospital(麻省总医院);Brigham and Women’s Hospital and Dana-Farber Cancer Institute(布莱根妇女医院与丹娜法伯癌症研究院)
Yikun Zhang, Xiwei Cheng, Mingze Yuan, Yu Zhang, Brian Shim, Aarti Krishnan, Daniel Rosen, Kunyang Sun, Yingze Wang, Zhenfeng Deng, Botao Yu, Bingxu Liu, David … 展开作者
Yikun Zhang, Xiwei Cheng, Mingze Yuan, Yu Zhang, Brian Shim, Aarti Krishnan, Daniel Rosen, Kunyang Sun, Yingze Wang, Zhenfeng Deng, Botao Yu, Bingxu Liu, David Liu, Tianyu Liu, Yuanqi Du, Nir Hacohen, James J. Collins, Wengong Jin
Molecular discovery requires navigating vast combinatorial search spaces while balancing competing biological objectives. AI agents can automate expert-defined molecular design protocols, but automation alone does not address how to optimize workflows for new tasks or improve their development through experience. Here we introduce MoLRSI, an AI agent that combines systematic optimization of workflows and model architectures with persistent cross-task memory to recursively improve its search policy for molecular discovery. Workflow performance, refinement outcomes, and execution feedback guide subsequent searches, allowing the agent to improve both its workflows and its strategy for developing them. We evaluate MoLRSI in two challenging molecular discovery settings that require balancing competing properties. In antibiotic discovery, MoLRSI developed a screening workflow balancing antibacterial activity, cytotoxicity and structural novelty, achieving an experimental hit rate of 15.9%, compared with 8.7% for a previous expert-led workflow using the same training data and screening library. In de novo peptide-MHC binder design, MoLRSI developed workflows that jointly consider target binding and specificity, producing eight experimentally validated hits against MART-1 and SARS-CoV-1 pMHCs with preferential binding over tested off-targets while Claude Science completely failed. These findings demonstrate how experience-guided workflow optimization can address competing discovery objectives while improving the search strategies used in subsequent campaigns.
Scalable Causal Discovery from Recursive Nonlinear Data via Truncated Basis Function Scores and Tests
Department of Philosophy(哲学系);Carnegie Mellon University(卡内基梅隆大学);Department of Psychiatry & Behavioral Sciences(精神病学与行为科学系);University of Minnesota(明尼苏达大学)
A Recursive Decomposition Framework for Causal Structure Learning in the Presence of Latent Variables
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China(深圳先进技术研究院,中国科学院,中国深圳);College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China(复旦大学计算机科学与人工智能学院,中国上海)
Limited Perfect Monotonical Surrogates constructed using low-cost recursive linkage discovery with guaranteed output
ITIS Software, University of M\'alaga M\'alaga Spain 29071;University of S\ ao Paulo Ribeir\ ao Preto Brazil 14040901;ITIS Software, University of M\'alaga;University of S\ ao Paulo
Eureka: Task-Conditioned Meta-Agent Orchestration for Scientific Discovery
ManXis(万熙科技(ManXis));Guangdong University of Technology(广东工业大学);South China Normal University(华南师范大学);Shanghai Jiao Tong University(上海交通大学);Duke University(杜克大学);Hokkaido University(北海道大学)