Sci‑MMR is a new benchmark for multi‑step evidence‑grounded scientific reasoning in multimodal agents, featuring 235 multi‑hop tasks across four disciplines and an average of nine figure panels per task. It evaluates not just final answer accuracy but also the recovery of structured evidence from scientific claims, citations, visual data, and supporting regions. Experiments on eight state‑of‑the‑art models show a gap of over 20 points between answer accuracy and complete evidence recovery, highlighting significant challenges in evidence acquisition and integration.
By Jiaqiang Li, Yajie Yang, Zhiheng Xi, Jiadong Chen, Enyu Zhou, Senjie Jin, Yang Nan, Jiazheng Zhang, Han Wang, Yanxin Li, Dingwei Zhu, Bicheng Deng, Yuhui Wang, Xiang Zheng, Qi Zhang, Lei Bai, Xingjun Ma, Tao Gui
arXiv:2609.33399v2 Announce Type: replace
Abstract: In realistic education, a solution is often expressed not only in words but in a drawing--a circuit, a geometric construction, a function plot--and...
By Jiali Chen, Zhengteng Lin, Zuqi Wang, Shirong Lin, Xi Yu, Xusen Hei, DingBa Fu, Jiayuan Xie, Yi Cai
arXiv:2607. 27084v1 Announce Type: cross Abstract: Scientific images are the core elements of presenting experimental conclusions, elaborating system architecture, and supporting comparative arguments in scientific papers.
By Zihan Deng, Chuanzhi Xu, Huiqi Liang, Haoyang Li, Xiaozhen Zhong, Lequan Yu
arXiv:2608. 06931v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly involved in scientific discovery, yet it remains unclear whether they can support complex real laboratory science.
By Taolin Han, Yuchen Zhang, Jinghang Wang, Yun Wu, Wai Yuet Chiu, Zhaohai Li, Yifei Zhang, Jinxin Wang, Yuhao Zhou, Chen Zhao, Jiajia Li, Jiaxin Li, Qile Jin, Kewei Sun, Shuang Wu, Weiqi Zhai, Renquan Lv, Junchao Li, Ruodan Chen, Qingteng Chen, Zhibo Yang, Hu Wei, Lin Qu, Shuai Bai, Bing Zhao
arXiv:2606. 13020v1 Announce Type: new Abstract: Three paradigmatic forms of inference recur across scientific reasoning: deduction, induction, and causal abduction.
By Pierre Beckmann, Marco Valentino, Andre Freitas
arXiv:2609.06192v1 Announce Type: new
Abstract: Scientific coding agents produce interdependent code, results, figures, and claims, yet evaluating final
outputs alone does not establish whether the...
By Bowen Liu, Shuo Nie, Bodong Du, Xiaomeng Li
arXiv:2608. 14075v1 Announce Type: new Abstract: Scientific figures and tables encode essential experimental evidence, yet remain difficult for digital libraries and multimodal AI systems to retrieve and interpret.
By Jennifer D'Souza, Fahad Ahmed, Cecilia Andrea Bustamante Andrade, Lina Frolova, Poorani Gnanasambandan, Dilshad Hussain, Muhammad Uzair Khan, Nkembeng Kevin Nkengfoa, Paul Praveen J., Fabio Priante, Sjoerd Franciscus van der Werf, Thomas Frederik Jan van Roeden
Scientific images are the core elements of presenting experimental conclusions, elaborating system architecture, and supporting comparative arguments in scientific papers. However, existing image quality assessment (IQA) methods are predominantly designed for natural photographs or AI-generated content, which cannot be directly applied to scientific papers.
arXiv:2606. 21005v2 Announce Type: replace Abstract: Scientific discovery workflows often depend on structured curation from the literature.
By Sheng Zhang, Qin Liu, Renqian Luo, Shufang Xie, Reuben Tan, Sean Hayes, Gregory Bryman, Wendong Ge, Ruilian Zhang, Oluwaseun Egbelowo, Kelly Yee, Hoifung Poon
arXiv:2604. 02794v2 Announce Type: replace Abstract: Charts are ubiquitous in scientific and financial literature for presenting structured data.
By Situo Zhang, Yifan Zhang, Zichen Zhu, Da Ma, Lei Pan, Danyang Zhang, Zihan Zhao, Lu Chen, Kai Yu
SciDocBench is a workflow-centered benchmark for scientific document understanding that includes 124 expert-authored questions across seven capability groups and 19 subtasks in five scientific domains. Each question is evaluated under four conditions—English or Chinese, all-images-first or interleaved document representations—resulting in 496 evaluation instances. The benchmark is paired with SciDocIR, a typed evidence-graph representation, and SciDocDataset, a collection of 15K fine-tuning and 8K reinforcement-learning samples, forming an evaluation-to-training framework for scientific-document assistants.
By Shenxi Wu, Yuhong Liu, Haosong Zhang, Tongjin Zou, Yanxun Zhang, Gaochang Chen, Dun Liang, Jiaqi Wang, Zhecan James Wang, Yuhang Zang, Dahua Lin
arXiv:2606. 29667v1 Announce Type: cross Abstract: The materials science literature encodes decades of experimental knowledge in figures, yet this visual record remains locked away and inaccessible to AI at scale.
By Subham Ghosh, Shubham Tiwari, Mohammad Ibrahim, Abhishek Tewari