Chem-R：學習像化學家一樣推理

摘要

尽管大型语言模型（LLMs）在推动化学发现方面具有巨大潜力，但当前的LLMs缺乏核心化学知识，产生的推理轨迹不可靠，且在多种化学任务中表现欠佳。为解决这些挑战，我们提出了Chem-R，一种可推广的化学推理模型，旨在模拟化学家的深思熟虑过程。Chem-R通过一个三阶段框架进行训练，逐步构建高级推理能力，包括：1）化学基础训练，建立核心化学知识；2）化学推理协议蒸馏，融入结构化的专家级推理轨迹，以指导系统且可靠的问题解决；3）多任务组相对策略优化，优化模型在多种分子和反应级别任务中的平衡表现。这一结构化流程使Chem-R在综合基准测试中达到最先进的性能，在分子任务上超越领先的大型语言模型（如Gemini-2.5-Pro和DeepSeek-R1）高达46%，在反应任务上高达66%。同时，Chem-R在分子和反应级别任务上均持续优于现有的化学基础模型。这些结果凸显了Chem-R在泛化能力、可解释性以及作为下一代AI驱动化学发现基础的潜力。

English

Although large language models (LLMs) have significant potential to advance chemical discovery, current LLMs lack core chemical knowledge, produce unreliable reasoning trajectories, and exhibit suboptimal performance across diverse chemical tasks. To address these challenges, we propose Chem-R, a generalizable Chemical Reasoning model designed to emulate the deliberative processes of chemists. Chem-R is trained through a three-phase framework that progressively builds advanced reasoning capabilities, including: 1) Chemical Foundation Training, which establishes core chemical knowledge. 2) Chemical Reasoning Protocol Distillation, incorporating structured, expert-like reasoning traces to guide systematic and reliable problem solving. 3) Multi-task Group Relative Policy Optimization that optimizes the model for balanced performance across diverse molecular- and reaction-level tasks. This structured pipeline enables Chem-R to achieve state-of-the-art performance on comprehensive benchmarks, surpassing leading large language models, including Gemini-2.5-Pro and DeepSeek-R1, by up to 46% on molecular tasks and 66% on reaction tasks. Meanwhile, Chem-R also consistently outperforms the existing chemical foundation models across both molecular and reaction level tasks. These results highlight Chem-R's robust generalization, interpretability, and potential as a foundation for next-generation AI-driven chemical discovery.

Chem-R：學習像化學家一樣推理

Chem-R: Learning to Reason as a Chemist

摘要

Support