The central challenge of AI for Science is not reasoning alone, but the ability to create computational methods in an open-ended scientific world. Existing LLM-based agents rely on static, pre-defined tool libraries, a paradigm that fundamentally fails in scientific domains where tools are sparse, heterogeneous, and intrinsically incomplete. In this paper, we propose Test-Time Tool Evolution (TTE), a new paradigm that enables agents to synthesize, verify, and evolve executable tools during inference. By transforming tools from fixed resources into problem-driven artifacts, TTE overcomes the rigidity and long-tail limitations of static tool libraries. To facilitate rigorous evaluation, we introduce SciEvo, a benchmark comprising 1,590 scientific reasoning tasks supported by 925 automatically evolved tools. Extensive experiments show that TTE achieves state-of-the-art performance in both accuracy and tool efficiency, while enabling effective cross-domain adaptation of computational tools. The code and benchmark have been released at https://github.com/lujiaxuan0520/Test-Time-Tool-Evol.
BiomedSQL: Text-to-SQL for Scientific Reasoning on Biomedical Knowledge Bases
Center for Alzheimer’s and Related Dementias, NIA, NIH(阿尔茨海默病及相关痴呆症研究中心,国家老龄化研究所,国立卫生研究院);DataTecnica LLC(DataTecnica公司);Johns Hopkins University(约翰霍普金斯大学);Laboratory of Neurogenetics, NIA, NIH(神经遗传学实验室,国家老龄化研究所,国立卫生研究院)
On LLM-Based Scientific Inductive Reasoning Beyond Equations
Dept. of Comp. Sci. & Tech., Institute for AI, BNRist Center, Tsinghua University(计算机科学与技术系,人工智能研究院,BNRist中心,清华大学);Jiangsu Collaborative Innovation Center for Language Ability, Jiangsu Normal University(江苏语言能力协同创新中心,江苏师范大学);Beijing Language and Culture University(北京语言文化大学);Xiamen University(厦门大学);Harbin Institute of Technology(哈尔滨工业大学)
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)
SciAgent: Tool-augmented Language Models for Scientific Reasoning
Microsoft(微软公司);University of California, Santa Barbara(加利福尼亚大学圣巴巴拉分校);Tsinghua University(清华大学);Singapore Management University(新加坡管理大学);Nanyang Technological University(南洋理工大学)
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
SciR: A Controllable Benchmark for Scientific Reasoning in LLMs
Idiap Research Institute(Idiap研究 institute);EPFL(瑞士联邦理工学院);School of Computer Science, University of Sheffield(谢菲尔德大学计算机科学学院);University of Manchester(曼彻斯特大学);National Biomarker Centre, CRUK Manchester Institute(国家生物标志物中心,CRUK曼彻斯特研究所)
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)
LSR-Ben: A Logical and Scientific Reasoning Benchmark for Evaluating Process Reward Models
Research Center for Social Computing(社会计算研究中心);Interactive Robotics, Harbin Institute of Technology, China(交互机器人学,哈尔滨工业大学,中国);Beijing Academy of Artificial Intelligence, Beijing, China(北京人工智能研究院,北京,中国)
Heterogeneous Element-Aware Cross-Version Differencing of Scientific Documents via Layout-Aware Alignment and Structure-Aware Reasoning
Beijing Renhe Information Technology Co., Ltd.(北京人和信息技术有限公司);Key Laboratory of Digital Publishing and Total Process Management of Scientific and Technical Journals(科技期刊数字出版与全程管理重点实验室)
The Marathon of Scientific Reasoning: Robustness of Scientific Agents to Perturbations in Multi-Turn Interactions
Inria(法国国家信息与自动化研究所);Agency for Science, Technology and Research (A*STAR)(新加坡科技研究局);Zhejiang Key Laboratory of Artificial Intelligence of Things (AIoT) Network and Data Security(浙江省人工智能物联网网络与数据安全重点实验室)
Reasoning With a Star: A Heliophysics Dataset and Benchmark for Agentic Scientific Reasoning
Frontier Development Lab(前沿发展实验室);Department of Mechanical and Aerospace Engineering, UCLA(机械与航空航天工程系,加州大学洛杉矶分校);Trillium Technologies Inc.(Trillium技术公司);Department of Engineering, University of Cambridge(工程系,剑桥大学)
Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO
HKUST Hong Kong SAR, China(香港科技大学);SEU Jiangsu, China(江苏大学);HKUST(GZ) Guangzhou, China(香港科技大学(广州));Zhipu AI Beijing, China(智谱AI);HKUST(GZ), HKUST Guangzhou, China(香港科技大学(广州)、香港科技大学)
Deciphering Scientific Reasoning Steps from Outcome Data for Molecule Optimization
Zhongguancun Academy(中关村学院);School of Computer Science and Technology, University of Science and Technology of China(中国科学技术大学计算机科学与技术学院);Global Health Drug Discovery Institute(全球健康药物发现研究所)
MSEarth: A Multimodal Scientific Dataset and Benchmark for Phenomena Uncovering in Earth Science
The Hong Kong Polytechnic University(香港理工大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Shanghai Jiao Tong University(上海交通大学);The Chinese University of Hong Kong(香港中文大学)