Scientific reasoning inherently demands integrating sophisticated toolkits to navigate domain-specific knowledge. Yet, current benchmarks largely overlook agents' ability to orchestrate tools for such rigorous workflows. To bridge this gap, we introduce SciAgentGym, a scalable interactive environment featuring 1,780 domain-specific tools across four natural science disciplines, supported by a robust execution infrastructure. Complementing this, we present SciAgentBench, a tiered evaluation suite designed to stress-test agentic capabilities from elementary actions to long-horizon workflows. Our evaluation identifies a critical bottleneck: state-of-the-art models still struggle with complex scientific tool-use, and their performance degrades substantially as interaction horizons extend. To address this, we propose SciForge, a data synthesis method that models the tool action space as a dependency graph to generate logic-aware training trajectories. By fine-tuning on these trajectories, our SciAgent-8B outperforms the significantly larger Qwen3-VL-235B-Instruct while exhibiting positive cross-domain transfer of scientific tool-use capabilities. These results underscore the promising potential of next-generation autonomous scientific agents.
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)
Benchmarking Multimodal LLMs on Recognition and Understanding over Chemical Tables
State Key Laboratory of Cognitive Intelligence(认知智能国家重点实验室);University of Science and Technology of China(中国科学技术大学);Artificial Intelligence Research Institute(人工智能研究院);iFLYTEK Co., Ltd(iFLYTEK公司)
SciHorizon: Benchmarking AI-for-Science Readiness from Scientific Data to Large Language Models
Computer Network Information Center, Chinese Academy of Sciences(中国科学院计算机网络信息中心);University of Chinese Academy of Sciences(中国科学院大学);University of Science and Technology of China(中国科学技术大学);Hefei University of Technology(合肥工业大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州))
CausalGame: Benchmarking Causal Thinking of LLM Agents in Games
MBZUAI(穆罕默德·本·扎耶德人工智能大学);Carnegie Mellon University(卡内基梅隆大学);Hong Kong Baptist University(香港浸会大学);University of Oxford(牛津大学);New York University, Abu Dhabi(纽约大学阿布扎比分校)
InnoGym: Benchmarking the Innovation Potential of AI Agents
Zhejiang University(浙江大学);Ant Group(蚂蚁集团);National University of Singapore(新加坡国立大学);Zhejiang University - Ant Group Joint Laboratory of Knowledge Graph(知识图谱联合实验室)
MMSciBench: Benchmarking Language Models on Chinese Multimodal Scientific Problems
Department of Computer Science, Yale University(耶鲁大学计算机科学系);Department of Computer Science, Brown University(布朗大学计算机科学系);School of Data Science, Fudan University(复旦大学数据科学学院);Shanghai Key Laboratory of Data Science(上海数据科学关键实验室);Datawiz LLC
SciRerankBench: Benchmarking Rerankers Towards Scientific Retrieval-Augmented Generation with LLMs
Computer Network Information Center, Chinese Academy of Sciences(中国科学院计算机网络信息中心);University of California, Los Angeles(加州大学洛杉矶分校);Peking University(北京大学)
SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval
Multimodal Art Projection Research Community(多模态艺术投影研究共同体);University of Manchester(曼彻斯特大学);University of Waterloo(滑铁卢大学);Hong Kong University of Science and Technology(香港科技大学);Durham University(杜伦大学)
AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite
Asta Team, Allen Institute for AI(Asta团队,人工智能研究所);University of Maryland(马里兰大学);University of Arizona(亚利桑那大学);University of Zurich(苏黎世大学);Bar-Ilan University(巴伊兰大学);University of Washington(华盛顿大学)
BLADE: Benchmarking Language Model Agents for Data-Driven Science
University of Washington(华盛顿大学);UC Berkeley(伯克利大学);New York University(纽约大学);Stanford University(斯坦福大学);University of British Columbia(不列颠哥伦比亚大学);Microsoft(微软);George Washington University(乔治·华盛顿大学)
Into the Unknown: Benchmarking AI agents on open scientific research problems
Carnegie Mellon University(卡内基梅隆大学);University of Minnesota(明尼苏达大学);Stanford University(斯坦福大学);Trillion Labs;Los Alamos National Laboratory(洛斯阿拉莫斯国家实验室);Sandia National Laboratory(桑迪亚国家实验室);Lawrence Berkeley National Laboratory(劳伦斯伯克利国家实验室);Ames National Laboratory(艾姆斯国家实验室);Iowa State University(爱荷华州立大学);University of Colorado Boulder(科罗拉多大学博尔德分校);Michigan State University(密歇根州立大学);Lawrence Livermore National Laboratory(劳伦斯利弗莫尔国家实验室);TelePIX;Johns Hopkins University(约翰斯·霍普金斯大学);NEC Laboratories Europe(NEC欧洲实验室);Ss.Cyril and Methodius University of Skopje(斯科普里圣西里尔和圣美多德大学)
本研究推出Into the Unknown基准,测试9个前沿智能体撰写开放科学问题后续论文的能力,发现无智能体达到领域科学家标准,仍有较大提升空间。
STRUCTSENSE: A Task-Agnostic Agentic Framework for Structured Information Extraction with Human-In-The-Loop Evaluation and Benchmarking
McGovern Institute for Brain Research, Massachusetts Institute of Technology, Cambridge, MA, USA(麦戈文脑科学研究所,麻省理工学院,马萨诸塞州剑桥市);Fylo Labs Inc., New York, NY, USA(Fylo实验室公司,纽约州纽约市);Allen Institute for Brain Science, Seattle, WA, USA(艾伦脑科学研究所,华盛顿州西雅图市)
Benchmarking Retrieval-Augmented Generation for Chemistry
Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校Siebel计算与数据科学学院);National Library of Medicine, National Institutes of Health(美国国立卫生研究院国家医学图书馆)