A novel, large-scale reasoning dataset of reaction mechanisms, and the FukuyamaBench, a difficult benchmark derived from Fukuyama's Advanced Organic Reaction Mechanism book, to rigorously evaluate model performance on hierarchical mechanism reasoning, demonstrate that mechanism-aware training substantially enhances chemical reasoning in language models.
Abstract
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.
The proposed Chem-R, a general Chemical Reasoning model designed to emulate the deliberative processes of chemists, achieves state-of-the-art performance on comprehensive benchmarks, surpassing leading LLMs, including Gemini-3-Pro and Kimi-k2.5.
Weida Wang, Benteng Chen, Di Zhang et al.· Proceedings of the 32nd ACM...· 0 citations
Single-step retrosynthesis is a central component of computer-aided synthesis planning, yet its intrinsically one-to-many nature is poorly captured by single-answer evaluation and benchmarking protocols. To address this, we introduce Top-K prompting as a robust training and inference paradigm to better capture diverse, plausible reaction predictions. We compile CREED-CCV-2+USPTO-XL, an ultra-large-scale dataset of ~45.6 million verified reactions to train the C3LM (Chemistry Constraint-Consistent Language Model). By integrating fine-tuning with ChemCensor-based and novelty-oriented rewards, our model achieves state-of-the-art performance on the OOD URSA-expert-2026 benchmark. Further analysis of reaction uniqueness shows that LLMs and conventional models explore complementary reaction spaces, motivating ensemble-based retrosynthesis systems. Overall, our results establish Top-K, plausibility-aware training as a practical new direction for robust future LLM-based synthesis planning.
B. Zagribelnyy, Ivan D. Ilin, N. Bondarev et al.· 0 citations
A task-adaptive large reasoning model that integrates chemical knowledge through a synergistic multispecialist architecture, chain-of-thought supervision, and molecule-informed reinforcement learning is presented, demonstrating a versatile multitask framework for knowledge-guided molecular reasoning and design.
Pengfei Liu, Shuang Ge, Xiaobo Wang et al.· Journal of Physical Chemistr...· 0 citations
Self-supervised pretraining substantially improves TS prediction for previously unseen systems, lowering the median root-mean-square deviation of TS geometries on Transition1x-TMC reactions and reducing fine-tuning data requirements, enabling reliable performance even in low-data regimes.
Samir Darouich, Jacob W. Toney, Weiliang Luo et al.· Nature Computational Science· 0 citations
Catalysts are essential for sustainable chemical manufacturing, yet discovering novel architectures remains a bottleneck dominated by trial-and-error experimentation and computationally intensive screening. In complex reactions such as electrochemical carbon dioxide reduction, product selectivity is governed by dynamic interfacial, electrolyte, and potential factors as well as kinetic pathway competition. Conventional descriptor-based machine learning and computational potentials struggle to resolve these mechanistic branch points, primarily relying on static ground-state descriptors or bulk structural correlations rather than end-to-end topological pathway analysis. Here, we show that frontier language models, when strictly constrained to reason over explicit reaction networks, can discover novel catalysts by identifying the physical levers that govern pathway competition. We developed a human-AI co-thinking framework that enforces network invariance to extract testable hypotheses from complex chemical graphs. Applied to CO2 electroreduction, the framework identified ketene desorption and hydroxide capture as the acetate-forming pathway, and predicted a distinct adsorbed CO and CH2 coupling route to ketene. By isolating actionable control levers, specifically local alkalinity, controlled iron incorporation, and restricted interfacial proton-donor accessibility, the framework guided the prospective synthesis of a copper-iron oxide catalyst demonstrating a threefold increase in acetate selectivity over matched Cu-rich baselines. This mechanism-guided reasoning architecture shifts the computational paradigm from retrospective statistical prediction to forward-looking hypothesis generation, providing a broadly applicable blueprint for mechanism-guided materials discovery.
Sutanay Choudhury, Anwesha Banerjee, Udishnu Sanyal et al.· 0 citations
Chemical reasoning language models are expected to derive molecular answers through faithful chain-of-thought (CoT). However, across four reasoning model families and twelve chemistry tasks, hallucination is widespread and largely decoupled from answer correctness: correct answers often coexist with fabricated structural claims absent from the relevant molecules. Yet this does not make the reasoning trace computationally irrelevant. Attribution analyses suggest a shared scratchpad function expressed in model-specific forms: Chem-R and ether-0 rely on fragmented SMILES drafts, whereas ChemDFM-R emphasizes scaffold, positional, and naming cues. Notably, perturbing Chem-R's SMILES sketches degrades generation, showing that structural drafts can be causally load-bearing even when verbal structural claims are largely inert. Together, these results show that chemical CoT is neither a faithful explanation nor merely a post-hoc rationalization, but a hallucination-prone molecular scratchpad. This finding cautions against treating CoT as direct evidence of faithful reasoning and motivates process-level supervision beyond answer-only evaluation.
Jiatong Li, Yuxuan Ren, Weida Wang et al.· 1 citation