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

• URL: http://arxiv.org/abs/2509.23768v1
• Date: Sun, 28 Sep 2025 09:34:35 GMT
• Title: From What to Why: A Multi-Agent System for Evidence-based Chemical Reaction Condition Reasoning
• Authors: Cheng Yang, Jiaxuan Lu, Haiyuan Wan, Junchi Yu, Feiwei Qin,
• Abstract summary: ChemMAS is a multi-agent system that reframes condition prediction as an evidence-based reasoning task.<n>ChemMAS achieves 20-35% gains over domain-specific baselines and outperforms general-purpose LLMs by 10-15% in Top-1 accuracy.
• Score: 15.34060627861624
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Modular Multi-Task Learning for Chemical Reaction Prediction [1.443416244644791]
  Low-Rank Adaptation (LoRA) is a parameter-efficient alternative to full fine-tuning for organic reaction prediction.<n>LoRA achieves accuracy comparable to full fine-tuning while effectively mitigating catastrophic forgetting and better preserving multi-task performance.
  arXiv  Detail & Related papers  (2026-02-11T01:17:06Z)
• ChemLabs on ChemO: A Multi-Agent System for Multimodal Reasoning on IChO 2025 [10.434011696348561]
  ChemO is a new benchmark built from the International Chemistry Olympiad (IChO) 2025.<n>ChemLabs is a hierarchical multi-agent framework that mimics human expert collaboration.<n>Our top configuration achieves a score of 93.6 out of 100, surpassing an estimated human gold medal threshold.
  arXiv  Detail & Related papers  (2025-11-20T10:15:39Z)
• oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning [44.36582860924775]
  We introduce oMeBench, the first large-scale, expert-curated benchmark for organic mechanism reasoning in organic chemistry.<n>We also propose oMeS, a dynamic evaluation framework that combines step-level logic and chemical similarity.
  arXiv  Detail & Related papers  (2025-10-09T03:13:31Z)
• Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations [43.623140005091535]
  We introduce ChemCoTBench, a reasoning framework that bridges molecular structure understanding with arithmetic-inspired operations.<n>ChemCoTBench formalizes chemical problem-solving into transparent, step-by-step reasoning.<n>We evaluate models on two high-impact tasks: Molecular Property Optimization and Chemical Reaction Prediction.
  arXiv  Detail & Related papers  (2025-05-27T15:15:44Z)
• ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoning [64.2106664137118]
  ChemAgent is a novel framework designed to improve the performance of large language models (LLMs)<n>It is developed by decomposing chemical tasks into sub-tasks and compiling these sub-tasks into a structured collection that can be referenced for future queries.<n>When presented with a new problem, ChemAgent retrieves and refines pertinent information from the library, which we call memory.
  arXiv  Detail & Related papers  (2025-01-11T17:10:30Z)
• Learning Chemical Reaction Representation with Reactant-Product Alignment [50.28123475356234]
  RAlign is a novel chemical reaction representation learning model for various organic reaction-related tasks.<n>By integrating atomic correspondence between reactants and products, our model discerns the molecular transformations that occur during the reaction.<n>We introduce a reaction-center-aware attention mechanism that enables the model to concentrate on key functional groups.
  arXiv  Detail & Related papers  (2024-11-26T17:41:44Z)
• BatGPT-Chem: A Foundation Large Model For Retrosynthesis Prediction [65.93303145891628]
  BatGPT-Chem is a large language model with 15 billion parameters, tailored for enhanced retrosynthesis prediction. Our model captures a broad spectrum of chemical knowledge, enabling precise prediction of reaction conditions. This development empowers chemists to adeptly address novel compounds, potentially expediting the innovation cycle in drug manufacturing and materials science.
  arXiv  Detail & Related papers  (2024-08-19T05:17:40Z)
• Text-Augmented Multimodal LLMs for Chemical Reaction Condition Recommendation [38.76977853056086]
  Chemma-RC is a text-augmented multimodal LLM to identify effective conditions through task-specific dialogue and condition generation.<n>Chemma-RC learns a unified representation of chemical reactions by aligning multiple modalities-including text corpus, reaction SMILES, and reaction graphs-within a shared embedding module.<n>Performance benchmarking on datasets showed high precision in identifying optimal conditions, with up to 17% improvement over the current state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-07-21T12:27:26Z)
• ChemMiner: A Large Language Model Agent System for Chemical Literature Data Mining [56.15126714863963]
  ChemMiner is an end-to-end framework for extracting chemical data from literature.<n>ChemMiner incorporates three specialized agents: a text analysis agent for coreference mapping, a multimodal agent for non-textual information extraction, and a synthesis analysis agent for data generation.<n> Experimental results demonstrate reaction identification rates comparable to human chemists while significantly reducing processing time, with high accuracy, recall, and F1 scores.
  arXiv  Detail & Related papers  (2024-02-20T13:21:46Z)
• Chemist-X: Large Language Model-empowered Agent for Reaction Condition Recommendation in Chemical Synthesis [55.30328162764292]
  Chemist-X is a comprehensive AI agent that automates the reaction condition optimization (RCO) task in chemical synthesis.<n>The agent uses retrieval-augmented generation (RAG) technology and AI-controlled wet-lab experiment executions.<n>Results of our automatic wet-lab experiments, achieved by fully LLM-supervised end-to-end operation with no human in the lope, prove Chemist-X's ability in self-driving laboratories.
  arXiv  Detail & Related papers  (2023-11-16T01:21:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.