從“是什麼”到“為什麼”：基於證據的化學反應條件推理多智能體系統

摘要

化学反应条件的推荐旨在为化学反应选取适宜的反应条件参数，这对加速化学科学的发展至关重要。随着大语言模型（LLMs）的迅速发展，利用其推理与规划能力进行反应条件推荐引起了越来越多的关注。尽管现有方法已取得一定成功，但它们鲜少解释推荐反应条件背后的逻辑，这限制了其在高风险科学工作流程中的应用。在本研究中，我们提出了ChemMAS，一个将条件预测重构为基于证据推理任务的多智能体系统。ChemMAS将该任务分解为机制基础、多通道回忆、约束感知的智能体辩论及理由聚合四个部分。每一项决策均基于化学知识与检索到的先例，提供可解释的论证。实验表明，ChemMAS在Top-1准确率上较领域特定基线提升了20-35%，并优于通用LLMs 10-15%，同时提供了可证伪、可信赖的人类理解理由，为科学发现中的可解释人工智能确立了新范式。

English

The chemical reaction recommendation is to select proper reaction condition parameters for chemical reactions, which is pivotal to accelerating chemical science. With the rapid development of large language models (LLMs), there is growing interest in leveraging their reasoning and planning capabilities for reaction condition recommendation. Despite their success, existing methods rarely explain the rationale behind the recommended reaction conditions, limiting their utility in high-stakes scientific workflows. In this work, we propose ChemMAS, a multi-agent system that reframes condition prediction as an evidence-based reasoning task. ChemMAS decomposes the task into mechanistic grounding, multi-channel recall, constraint-aware agentic debate, and rationale aggregation. Each decision is backed by interpretable justifications grounded in chemical knowledge and retrieved precedents. Experiments show that ChemMAS achieves 20-35% gains over domain-specific baselines and outperforms general-purpose LLMs by 10-15% in Top-1 accuracy, while offering falsifiable, human-trustable rationales, which establishes a new paradigm for explainable AI in scientific discovery.

從“是什麼”到“為什麼”：基於證據的化學反應條件推理多智能體系統

From What to Why: A Multi-Agent System for Evidence-based Chemical Reaction Condition Reasoning

摘要

Support