From What to Why: A Multi-Agent System for Evidence-based Chemical Reaction Condition Reasoning
This addresses the need for explainable AI in high-stakes scientific workflows like chemistry, where existing methods lack rationale, making it a novel paradigm rather than incremental.
The paper tackles the problem of chemical reaction condition recommendation by proposing ChemMAS, a multi-agent system that provides evidence-based reasoning and interpretable justifications, achieving 20-35% gains over domain-specific baselines and 10-15% improvements over general-purpose LLMs in Top-1 accuracy.
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.