Learning Transferable Reaction Mechanisms from Visual Chemical Knowledge

Yujian Yuan; Jiaxin Xu; Xin Cai; Yufan Chen; Zhichao Tan; Ziqi Zhou; Hanyu Gao

cs.CESep 27, 2026

Learning Transferable Reaction Mechanisms from Visual Chemical Knowledge

Authors: Yujian Yuan, Jiaxin Xu, Xin Cai, Yufan Chen, Zhichao Tan, Ziqi Zhou, Hanyu Gao

Organizations: The Hong Kong University of Science and Technology · The Chinese University of Hong Kong · University of Edinburgh

Abstract

Reaction mechanisms describe the step-by-step transformations underlying chemical reactions and are central to reaction analysis and synthesis. Learning-based models have achieved strong performance on established mechanism-prediction benchmarks, but transferring them to unseen chemistry remains challenging. Such transfer is difficult because familiar mechanisms must be applied to unfamiliar molecular structures, and some target mechanisms may be poorly covered by the training data. To address these challenges, we introduce MechaVLM, a visual framework that combines transferable chemical representations with external mechanistic knowledge. It learns reusable visual features through multiscale chemical grounding and cross-rendering contrastive learning. For open-book prediction, MechaVLM retrieves a fixed set of precedents from 70,384 literature mechanism figures and re-reads relevant visual evidence as the molecular state evolves, directly using the figures without symbolic mechanism parsing. An atom-indexed language decoder then recursively generates executable electron edits to construct the complete mechanism. We further introduce MechBench, a challenging literature-derived benchmark with 2,184 mechanisms and 9,146 elementary steps. Across cross-dataset and literature-derived benchmarks, MechaVLM establishes strong zero-shot mechanism prediction. Its closed-book model alone improves Step/Pathway Top-1 by 12.50/13.93 percentage points on FlowER-to-ReactMech transfer, while external visual precedents unlock further gains on challenging OOD reactions. The learned representation also generalizes beyond mechanism prediction to atom mapping and reaction center prediction.

Figures & tables

Figure 1: Transferable reaction mechanism prediction with MechaVLM. Visual modeling supports complementary closed-book and open-book transfer for OOD chemistry, while retrieved pathway-level precedents are dynamically transferred to step-wise electron-edit predictions.

Figure 2: Overview of MechaVLM . (a) Chemically grounded and rendering-robust visual representation learning. (b) Reaction-level precedent retrieval via global screening and fine-grained reranking. (c) Step-wise cross-image transfer dynamically extracts relevant evidence from the retrieved precedents and grounds it to indexed query atoms for executable electron-edit decoding. The updated state is re-rendered for the next step.

		FlowER				ReactMech
		Step		Pathway		Step		Pathway
Source	Method	Top-1	Top-5	Top-1	Top-5	Top-1	Top-5	Top-1	Top-5
FlowER	NERF ( Bi et al., 2021 )	67.11	72.60	65.51	75.58	33.32	43.12	14.93	36.32
	Graph2SMILES ( Tu and Coley, 2022 )	89.09	98.66	92.51	97.76	42.71	55.00	31.84	61.19
	Graph2SMILES+H ( Tu and Coley, 2022 )	87.39	97.67	89.22	96.19	40.42	52.37	29.67	59.74
	MT ( Schwaller et al., 2019 )	88.75	98.92	88.31	97.59	44.52	52.45	39.30	58.21

Table 1: Cross-domain reaction mechanism prediction (%). Models are trained on the source dataset indicated in the first column. White cells report in-distribution (ID) performance, while gray cells denote zero-shot out-of-distribution (OOD) transfer without target-domain adaptation.

		FukuyamaBench				MechBench
		Step		Pathway		Step		Pathway
Source	Method	Top-1	Top-5	Top-1	Top-5	Top-1	Top-5	Top-1	Top-5
ReactMech	Closed-book
	NERF ( Bi et al., 2021 )	6.56	8.86	0.31	0.31	0.72	1.20	0.14	0.18
	Graph2SMILES ( Tu and Coley, 2022 )	2.35	4.01	0.31	0.31	0.14	0.36	0.00	0.05
	Molecular Transformer ( Schwaller et al., 2019 )	3.41	7.51	0.00	0.63	0.39	1.07	0.09	0.14

Table 2: Zero-shot prediction on FukuyamaBench and MechBench (%). Models are trained on the source dataset and evaluated without target-domain adaptation. ∗ : derived from ( Dang et al., 2026 )

Specialized atom-mapping methods
Method	USPTO -50K (2K)	Schneider	Jaworski
Indigo ( EPAM Systems, 2026 )	30.35	38.98	15.93
G.Mapper ( Nugmanov et al., 2022 )	79.40	92.20	80.40
RxnMapper ( Schwaller et al., 2021 )	81.05	93.12	83.15
LocalMapper ( Chen et al., 2024 )	–	90.08	86.98
Vision-language models

Table 3: Transfer to atom mapping (%).

Specialized atom-mapping methods
Method	USPTO -50K (2K)	Schneider	Jaworski
Indigo ( EPAM Systems, 2026 )	30.35	38.98	15.93
G.Mapper ( Nugmanov et al., 2022 )	79.40	92.20	80.40
RxnMapper ( Schwaller et al., 2021 )	81.05	93.12	83.15
LocalMapper ( Chen et al., 2024 )	–	90.08	86.98
Vision-language models

Table 3: Transfer to atom mapping (%).

Specialized reaction-center methods
	Class Unknown		Class Known
Method	Top-1	Top-5	Top-1	Top-5
RetroXpert ( Yan et al., 2020 )	64.9	–	86.0	–
G2Gs ( Shi et al., 2020 )	75.8	85.6	90.2	95.0
GDiffRetro ( Sun et al., 2025 )	86.2	98.8	–	–
Vision-language models

Table 4: Transfer to reaction center prediction.

Input modality
	FlowER (ID)		ReactMech		FukuyamaBench		MechBench
Variant	Step	Path.	Step	Path.	Step	Path.	Step	Path.
SMILES input	87.85	90.92	43.38	23.88	10.67	0.63	4.31	0.18
Graph input	88.35	91.36	45.87	25.91	12.32	0.94	5.08	0.32
Closed-book: transferable representation learning
Mechanism SFT only (image input)	88.41	91.96	52.32	32.47	15.87	1.57	6.82	0.60

Table 5: Cumulative ablation of MechaVLM (Top-1 %). All variants are trained on FlowER. White cells report in-distribution performance, while gray cells denote zero-shot OOD evaluation.

Figure 3: Examples of closed-book and open-book prediction of MechaVLM for OOD reactions.

	ReactMech		FukuyamaBench		MechBench
Retriever	Step	Path.	Step	Path.	Step	Path.
Random	68.52	52.41	21.83	5.64	9.38	1.47
CLIP image similarity ( Radford et al., 2021 )	70.74	54.63	23.44	6.27	10.17	1.60
OCSR structure similarity ( Fan et al., 2024 )	71.08	55.12	23.74	5.96	10.37	1.65
Global similarity	72.93	56.76	24.89	6.90	11.31	2.15
Late interaction	74.41	58.92	25.99	7.52	12.13	2.15

Table 6: Ablation of external precedent retrieval strategies (%). All models are trained on FlowER.

Appendix figures & tables12 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 4: Distribution of elementary steps by pathway length in MechBench and FukuyamaBench. Bars indicate the total number of elementary steps contributed by pathways of each length.

Benchmark	Source	# Publications	# Pathways	# Steps
FukuyamaBench	Mechanism book	–	319	1,997
MechBench	Journal literature	417	2,184	9,146

Appendix

Table 7: Comparison of the fully held-out mechanism benchmarks used in this work. Neither benchmark is used for training or target-domain adaptation.

Figure 5: Example of multiscale chemical grounding.

Category	#	Canonical vocabulary
Unsaturated / aromatic	4	alkene, alkyne, conjugated diene, aromatic ring
Oxygen-containing	8	alcohol, phenol, ether, epoxide, peroxide, acetal, hemiacetal, silyl ether
Carbonyl / acyl	15	aldehyde, ketone, carboxylic acid, ester, lactone, amide, lactam, imide, anhydride, acyl fluoride, acyl chloride, acyl bromide, carbonate, carbamate, urea
Nitrogen-containing	13	primary amine, secondary amine, tertiary amine, quaternary ammonium, imine, enamine, oxime, nitrile, nitro, azo, diazonium, azide, isocyanate
Sulfur-containing	9	thiol, thioether, disulfide, sulfoxide, sulfone, sulfonamide, sulfonate ester, thioester, sulfonyl halide
Boron-containing	3	boronic acid, boronate ester, organotrifluoroborate

Appendix

Table 8: Functional-group vocabulary used for atom-anchored functional-group grounding. Multiple entries may be valid for the same queried atom when SMARTS patterns overlap.

Figure 6: Example of input/output of the image-based atom mapping and reaction center prediction.

		Conservation
Method	Validity	Atom	Proton	Electron
Graph2SMILES Tu and Coley (2022)	76.31	30.72	18.67	17.19
Graph2SMILES+H Tu and Coley (2022)	78.80	27.66	19.73	19.02
Molecular Transformer Schwaller et al. (2019)	70.16	39.11	33.69	33.04
FlowER Joung et al. (2025)	94.94	94.94	94.94	94.94
MechaVLM	95.12	95.12	95.12	95.12

Appendix

Table 9: Comparison of prediction validity and conservation (%).

	FlowER (ID)		ReactMech		FukuyamaBench		MechBench
Grounding supervision	Step	Path.	Step	Path.	Step	Path.	Step	Path.
None	88.41	91.96	52.32	32.47	15.87	1.57	6.82	0.60
Atom	88.86	92.51	57.18	37.06	17.38	2.19	7.54	0.78
Atom + Bond	89.31	93.08	60.74	42.26	18.63	3.13	8.16	0.96
Atom + Bond + Functional Group	89.63	93.42	62.74	45.58	19.58	3.76	8.58	1.10

Appendix

Table 10: Effect of chemical grounding granularity (%). All variants use the same Stage-I training data and subsequent mechanism training protocol. Only Top-1 Step/Pathway accuracy is reported.

	ReactMech		FukuyamaBench		MechBench
Retrieval strategy	Step	Path.	Step	Path.	Step	Path.
Re-retrieve at every step	74.68	58.93	25.87	7.47	12.08	2.15
Reaction-level retrieval (ours)	76.21	61.52	27.14	8.15	12.72	2.52

Appendix

Table 11: Effect of precedent retrieval frequency (%).

		FukuyamaBench		MechBench
Bank fraction	# Figures	Step	Path.	Step	Path.
$0\%$	0	22.28	5.96	9.59	1.56
$25\%$	17,596	24.29	6.58	10.74	1.88
$50\%$	35,192	25.74	7.52	11.58	2.15
$100\%$	70,384	27.14	8.15	12.72	2.52

Appendix

Table 12: Scaling with the external visual precedent bank (%).

Figure 7: Example of input and output format of MechaVLM in closed-book setting.

Figure 8: Example of input and output format of MechaVLM in closed-book setting.

Image Encoder
Component	Qwen2.5-VL-3B
Architecture	Vision Transformer
Layers	32
Hidden Size	1280
Attention Heads	16
Patch Size	14

Appendix

Table 13: Architecture details of the Qwen2.5-VL-3B backbone.

Explore similar work

Learning Mechanistic Reasoning for Chemical Reactions with Large Language Models
Jul 14, 2026Xingyu Dang, Haocheng Tang, Junmei Wang +1Reaction Chemistry
Department of Computer Science, Princeton University, Princeton, NJ, 08540, United States · School of Pharmacy, University of Pittsburgh, Pittsburgh, PA, 15261, United States · Khoury College of Computer Science, Northeastern University, Boston, MA, 02115, United States +2
oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning
Oct 9, 2025Ruiling Xu, Yifan ZhangReaction Large Language Model Benchmarks
University of Illinois Urbana-Champaign
ChemVA: Advancing Large Language Models on Chemical Reaction Diagrams Understanding
May 17, 2026Mingyang Rao, Kehua Feng, Zhihui Zhu +4Chemical Structures Efficient Latent Reasoning
College of Computer Science and Technology, Zhejiang University Hangzhou, Zhejiang, China · ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University Hangzhou, Zhejiang, China · Department of Chemistry, Fudan University Shanghai, China

Jul 14, 2026, cs.LGJ/K move · Enter open · S save

Learning Mechanistic Reasoning for Chemical Reactions with Large Language Models

Xingyu Dang, Haocheng Tang, Junmei Wang, Yanjun Li

Department of Computer Science, Princeton University, Princeton, NJ, 08540, United States · School of Pharmacy, University of Pittsburgh, Pittsburgh, PA, 15261, United States · Khoury College of Computer Science, Northeastern University, Boston, MA, 02115, United States+2

Reaction Chemistry LLM Reasoning Strategies

Open paper AskPDF arXiv

Reaction mechanisms consist of the step-by-step sequences of elementary reactions that explain chemical transformations. Learning the mechanism logic is therefore essential for enhancing the fundamental chemical intelligence of large language models (LLMs). The stepwise deduction of reaction mechanism aligns naturally with the reasoning paradigms of reasoning LLMs. However, current chemical LLMs primarily emphasize coarse-grained name reactions for product prediction and retrosynthesis, often leading to physical inconsistencies and hallucinations. In contrast, specialized small-scale generative models for mechanism inference typically suffer from restricted generalization capacity across diverse chemical spaces. To overcome these limitations, we built a novel, large-scale reasoning dataset of reaction mechanisms. Furthermore, we established the FukuyamaBench, a difficult benchmark derived from Fukuyama's Advanced Organic Reaction Mechanism book, to rigorously evaluate model performance on hierarchical mechanism reasoning. Our fine-tuned Qwen3-30B-A3B achieves 8.3% exact pathway match on FukuyamaBench Set~A, surpassing the specialized FlowER model (5.1%), demonstrating that mechanism-aware training substantially enhances chemical reasoning in language models.

Abstract

Explore similar work

Learning Mechanistic Reasoning for Chemical Reactions with Large Language Models

oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning

ChemVA: Advancing Large Language Models on Chemical Reaction Diagrams Understanding