ACL Findings2026
CheMM-R1: Enhancing Chemical Structure Recognition and Elucidation with Reasoning Multimodal Large Language Models
Abstract
While Multimodal Large Language Models (MLLMs) demonstrate strong reasoning capabilities, they lack domain-specific expertise to effectively perform chemical tasks. For example, existing MLLMs struggle with both the lower-level task of molecular structure recognition and the higher-level task of chemical spectral data elucidation. When faced with complex molecular structures and multimodal chemical data (including spectral images and texts), they often fail to provide reliable inference, resulting in poor performance. Moreover, there are no benchmark datasets for evaluating multi-step multimodal reasoning capacities in the chemistry domain. To this end, we establish CheMM-Bench, a comprehensive benchmark dataset with 48,500 reasoning steps across four chemical tasks (SmilesQA, IupacQA, MwQA, SpectraQA) for evaluating visual reasoning in both molecular structure recognition and spectral analysis. On top of this, we present CheMM-R1, a state-of-the-art chemistry-specific MLLM trained with CheM-MGRPO, a novel adaptation of Group Relative Policy Optimisation tailored for chemical reasoning. CheMMGRPO employs domainspecific reward functions to assess chemical validity, structural accuracy, format compliance, and factual correctness. CheMM-R1 surpasses leading proprietary models (GPT-o3, Gemini-2.5-Pro, Claude-3.5-Sonnet, and Grok-2) across all CheMM-Bench tasks. The evaluation code and model are publicly available 1 .
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search cites R1-VL: Learning to Reason with Multimodal Large Language Models via Step-Wise Group Relative Policy Optimization
- R1-VL: Learning to Reason with Multimodal Large Language Models via Step-Wise Group Relative Policy Optimization cites Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search
- Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- R1-VL: Learning to Reason with Multimodal Large Language Models via Step-Wise Group Relative Policy Optimization cites Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
Builds on5
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language ModelsWenxuan Huang, Bohan Jia, Shaosheng Cao, Zheyu Ye et al.ICLR 2026 · 670 citations
- Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree SearchHuanjin Yao, Jiaxing Huang, Wenhao Wu, Jingyi Zhang et al.NeurIPS 2025 · 147 citations
- ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry AreaJunxian Li, Di Zhang, Xunzhi Wang, Zeying Hao et al.AAAI 2025 · 71 citations
- R1-VL: Learning to Reason with Multimodal Large Language Models via Step-Wise Group Relative Policy OptimizationJingyi Zhang, Jiaxing Huang, Huanjin Yao, Shunyu Liu et al.ICCV 2025 · 17 citations
Related papers
- MolErr2Fix: Benchmarking LLM Trustworthiness in Chemistry via Modular Error Detection, Localization, Explanation, and CorrectionYuyang Wu, Jinhui Ye, Shuhao Zhang, Lu Dai et al.EMNLP 2025 · 1 citation
- MolecularIQ: Characterizing Chemical Reasoning Capabilities Through Symbolic Verification on Molecular GraphsChristoph Bartmann, Johannes Schimunek, Mykyta Ielanskyi, Philipp Seidl et al.ICLR 2026 · 5 citations
- MMSciBench: Benchmarking Language Models on Chinese Multimodal Scientific ProblemsXinwu Ye, Chengfan Li, Siming Chen, Wei Wei et al.ACL Findings 2025 · 1 citation
- Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning BenchmarkYunzhuo Hao, Jiawei Gu, Huichen Will Wang, Linjie Li et al.ICML 2025
- LLMs as Lab Engineers: A Benchmark for Analytical Method Lifecycle ManagementXiaoyi Chen, Mahsa Monshizadeh, Chaoqi Zhang, Jianjun Lang et al.ACL Findings 2026
