Research2026-04-20
ReactBench: A Benchmark for Topological Reasoning in MLLMs on Chemical Reaction Diagrams
Source: Arxiv CS.AI
arXiv:2604.15994v1 Announce Type: new Abstract: 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...
arxivpapersreasoningbenchmark