Scientific literature is growing exponentially, creating a critical bottleneck for researchers to efficiently synthesize knowledge. While general-purpose Large Language Models (LLMs) show potential in text processing, they often fail to capture scientific domain-specific nuances (e.g., technical jargon, methodological rigor) and struggle with complex scientific tasks, limiting their utility for interdisciplinary research. To address these gaps, this paper presents SciGPT, a domain-adapted foundation model for scientific literature understanding and ScienceBench, an open source benchmark tailored to evaluate scientific LLMs.
Built on the Qwen3 architecture, SciGPT incorporates three key innovations: (1) low-cost domain distillation via a two-stage pipeline to balance performance and efficiency; (2) a Sparse Mixture-of-Experts (SMoE) attention mechanism that cuts memory consumption by 55\% for 32,000-token long-document reasoning; and (3) knowledge-aware adaptation integrating domain ontologies to bridge interdisciplinary knowledge gaps.
Experimental results on ScienceBench show that SciGPT outperforms GPT-4o in core scientific tasks including sequence labeling, generation, and inference. It also exhibits strong robustness in unseen scientific tasks, validating its potential to facilitate AI-augmented scientific discovery.
A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery
University of Washington（华盛顿大学）；Texas A&M University（德克萨斯农工大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
SciTopic: Enhancing Topic Discovery in Scientific Literature through Advanced LLM
Computer Network Information Center, Chinese Academy of Sciences, Beijing, China（中国科学院计算机网络信息中心）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学）；Department of Computer Science, Portland State University, Portland, US（波特兰州立大学计算机科学系）；Information Science and Technology College, Dalian Maritime University, Dalian, China（大连海事大学信息科学与技术学院）
An LLM-based Knowledge Synthesis and Scientific Reasoning Framework for Biomedical Discovery
Idiap Research Institute（伊迪亚普研究所）；National Biomarker Centre（国家生物标志物中心）；CRUK-MI（英国癌症研究中心曼彻斯特研究所）；Univ. of Manchester（曼彻斯特大学）；Department of Computer Science, Univ. of Manchester（曼彻斯特大学计算机科学系）
ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition
Fudan University（复旦大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Nanyang Technological University（南洋理工大学）；University of New South Wales（新南威尔士大学）；National University of Singapore（新加坡国立大学）；Wuhan University（武汉大学）
Scaling Laws in Scientific Discovery with AI and Robot Scientists
University of Toronto（多伦多大学）；Istituto Italiano di Tecnologia（意大利技术研究院）；Universita di Genova（热那亚大学）；Tsinghua University（清华大学）；Zhejiang University（浙江大学）；Rutgers University（罗格斯大学）；Harvard University（哈佛大学）；Georgia Tech（佐治亚理工学院）；University College of London（伦敦大学学院）
A Search Engine for Discovery of Scientific Challenges and Directions
Tel Aviv University（特拉维夫大学）；Allen Institute for AI（艾伦人工智能研究所）；University of Washington（华盛顿大学）；Georgia Institute of Technology（佐治亚理工学院）；Microsoft（微软公司）；Swedish Medical Group（瑞典医疗集团）
A Computational Inflection for Scientific Discovery
The Allen Institute for AI（艾伦人工智能研究所）；The Hebrew University of Jerusalem（希伯来大学）；Northwestern University（西北大学）；The University of Washington（华盛顿大学）；Microsoft（微软）
Enhancing Agentic Autonomous Scientific Discovery with Vision-Language Model Capabilities
Department of Physics, University of Cambridge, Cambridge, United Kingdom（剑桥大学物理系）；Kavli Institute for Cosmology, University of Cambridge, Cambridge, United Kingdom（剑桥大学卡弗利天文研究所）；Department of Physics and Astronomy, Haverford College, 370 Lancaster Avenue, Haverford, PA 19041, USA（哈弗福德学院物理与天文学系）；Division of Physics, Mathematics and Astronomy, California Institute of Technology, Pasadena, CA 91125, USA（加州理工学院物理、数学与天文学系）；Institute of Astronomy, University of Cambridge, Cambridge, United Kingdom（剑桥大学天文研究所）
