ReactBench: A Benchmark for Topological Reasoning in MLLMs on Chemical Reaction Diagrams

Computer Science > Artificial Intelligence [Submitted on 17 Apr 2026] ReactBench: A Benchmark for Topological Reasoning in MLLMs on Chemical Reaction Diagrams Qiang Xu, Shengyuan Bai, Yu Wang, He Cao, Leqing Chen, Yuanyuan Liu, Bin Feng, Zijing Liu, Yu Li Multimodal Large Language Models (MLLMs) excel at recognizing individual visual elements and reasoning over simple linear diagrams. However, when faced with complex topological structures involving branching paths, converging flows, and cyclic dependencies, their reasoning capabilities degrade sharply, even on tasks as basic as counting endpoints. Existing benchmarks fail to probe this gap, focusing on semantic comprehension rather than structural reasoning. We introduce ReactBench, a benchmark that reveals fundamental limitations in structural reasoning through chemical reaction diagrams. These real-world scientific diagrams offer an ideal testbed because they naturally span diverse structures from linear chains to cyclic graphs, while requiring both precise local recognition and coherent global reasoning. Our benchmark comprises 1,618 expert-annotated QA pairs across four hierarchical task dimensions. Extensive evaluation across 17 MLLMs reveals a significant performance gap exceeding 30% between anchor-based tasks and holistic structural reasoning tasks. Controlled ablations confirm this bottleneck lies in reasoning, not perception. These findings expose a fundamental deficit in structural understanding and establish directions for advancing visual reasoning. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2604.15994 [cs.AI]   (or arXiv:2604.15994v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.15994 Focus to learn more Submission history From: Qiang Xu [view email] [v1] Fri, 17 Apr 2026 12:16:57 UTC (4,944 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)