5 papers
SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence
Yiheng Wang, Yixin Chen, Shuo Li +33
We introduce SciEvalKit, a unified benchmarking toolkit designed to evaluate AI models for science across a broad range of scientific disciplines and task capabilities. Unlike gene…
FlowSearch: Advancing deep research with dynamic structured knowledge flow
Yusong Hu, Runmin Ma, Yue Fan +11
Deep research is an inherently challenging task that demands both breadth and depth of thinking. It involves navigating diverse knowledge spaces and reasoning over complex, multi-s…
SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines
Yizhou Wang, Chen Tang, Han Deng +29
We present a scientific reasoning foundation model that aligns natural language with heterogeneous scientific representations. The model is pretrained on a 206B-token corpus spanni…
Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning
Yuhao Zhou, Yiheng Wang, Xuming He +26
Scientific discoveries increasingly rely on complex multimodal reasoning based on information-intensive scientific data and domain-specific expertise. Empowered by expert-level sci…
EarthSE: A Benchmark for Evaluating Earth Scientific Exploration Capability of LLMs
Wanghan Xu, Xiangyu Zhao, Yuhao Zhou +5
Advancements in Large Language Models (LLMs) drive interest in scientific applications, necessitating specialized benchmarks such as Earth science. Existing benchmarks either prese…