发表机构
Stevens Institute of Technology; University of British Columbia; University of Maryland; Artificial Intelligence Interdisciplinary Institute at Maryland（史蒂文斯理工学院; 不列颠哥伦比亚大学; 马里兰大学; 马里兰人工智能跨学科研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出MAIL框架，将化学假说生成视为记忆驱动的时间推理过程，在TOMATO-Chem与HN-NS数据集上验证其能生成高质量新颖假说，展现了LLMs在化学领域自主探索的潜力。
AI 中文摘要
不断扩充的化学文献体量为生成新颖且有价值的假说提供了前所未有的机遇，但瓶颈在于如何高效地在这一庞大知识库中导航，以构建高质量、具有实验意义的见解。尽管大型语言模型（LLMs）在该任务上展现出潜力，现有方法却往往依赖静态灵感语料库、预定义启发式规则，或需要繁琐的人类参与的流程与决策支持框架，这限制了方法的可扩展性与新颖性。本研究提出一种自动化方法——记忆增强、自适应、增量式且基于文献的（MAIL）化学假说生成框架。MAIL方法将假说生成定义为基于时间、记忆驱动的推理过程，其中假说源于不断积累并重新解释先前知识的演化概念路径。我们在公开的TOMATO-Chem数据集以及新整理发布的高新颖性自然/科学挑战（HN-NS）数据集上对MAIL框架进行评估。在两个数据集上，MAIL均生成结构连贯、机制合理的假说，通过更有效地恢复历史目标假说的核心思想与方法元素，获得了最高的MIOS与MPOS值，且在科学质量的专家评估中取得了最高的整体分数。这些结果证明了LLMs在化学领域自主探索、生成兼具创新性与化学合理性的假说方面的潜力。
英文摘要
The ever-expanding volume of the chemical literature offers unprecedented opportunities to generate novel and impactful hypotheses. However, the bottleneck lies in efficiently navigating this vast knowledge base to formulate high-quality, experimentally meaningful insights. While Large Language Models (LLMs) show promise for this task, existing methods often rely on static inspiration corpora, predefined heuristics, or laborious human-in-the-loop pipelines and decision-support frameworks that limit scalability and novelty. In this work, we propose an automated approach, a Memory-augmented, Adaptive, Incremental, and Literature-grounded (MAIL) framework for hypothesis generation in chemistry. Our MAIL method formulates hypothesis generation as a temporally grounded, memory-driven reasoning process, where hypotheses emerge from an evolving conceptual path that continuously accumulates and reinterprets prior knowledge. We evaluated the MAIL framework on a public TOMATO-Chem dataset and a newly curated and disseminated high-novelty nature/science challenge (HN-NS) dataset. Across both datasets, MAIL generates structurally coherent and mechanistically plausible hypotheses, achieves the highest MIOS and MPOS by more effectively recovering the central ideas and methodological elements of the historical target hypotheses, and obtains the highest overall expert-evaluation scores for scientific quality. These results demonstrate the potential of LLMs to autonomously explore chemical domains and generate hypotheses that are both innovative and chemically plausible.
