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

arXiv: https://arxiv.org/abs/2509.23768 · HTML: https://mlsanity.com/paper/2509.23768/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 18 of its 43 references that are in the map.
- First posted on arXiv 28 Sep 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 18 of 18)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents](https://mlsanity.com/paper/2503.01935/) (2025)
- [Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2410.02506/) (2024)
- [MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency](https://mlsanity.com/paper/2502.09621/) (2025)
- [Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning](https://mlsanity.com/paper/2505.16410/) (2025)
- [Voting or Consensus? Decision-Making in Multi-Agent Debate](https://mlsanity.com/paper/2502.19130/) (2025)
- [Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations](https://mlsanity.com/paper/2505.21318/) (2025)
- [ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoning](https://mlsanity.com/paper/2501.06590/) (2025)
- [Chemist-X: Large Language Model-empowered Agent for Reaction Condition Recommendation in Chemical Synthesis](https://mlsanity.com/paper/2311.10776/) (2023)
- [PairJudge RM: Perform Best-of-N Sampling with Knockout Tournament](https://mlsanity.com/paper/2501.13007/) (2025)
- [Chemical reasoning in LLMs unlocks strategy-aware synthesis planning and reaction mechanism elucidation](https://mlsanity.com/paper/2503.08537/) (2025)
- [CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning](https://mlsanity.com/paper/2410.10336/) (2024)
- [Text-Augmented Multimodal LLMs for Chemical Reaction Condition Recommendation](https://mlsanity.com/paper/2407.15141/) (2024)
- [Locally-Deployed Chain-of-Thought (CoT) Reasoning Model in Chemical Engineering: Starting from 30 Experimental Data](https://mlsanity.com/paper/2502.12383/) (2025)

## Built on by (most cited first, 12 of 12)

- [Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks](https://mlsanity.com/paper/2511.15065/) (2025)
- [Beyond Static Tools: Test-Time Tool Evolution for Scientific Reasoning](https://mlsanity.com/paper/2601.07641/) (2026)
- [FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use](https://mlsanity.com/paper/2603.08262/) (2026)
- [Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?](https://mlsanity.com/paper/2510.16582/) (2025)
- [LungNoduleAgent: A Collaborative Multi-Agent System for Precision Diagnosis of Lung Nodules](https://mlsanity.com/paper/2511.21042/) (2025)
- [From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning](https://mlsanity.com/paper/2604.19516/) (2026)
- [CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpad](https://mlsanity.com/paper/2603.14575/) (2026)
- [ChemGraph-XANES: An Agentic Framework for XANES Simulation and Curation](https://mlsanity.com/paper/2604.16205/) (2026)
- [Latent Action Reparameterization for Efficient Agent Inference](https://mlsanity.com/paper/2605.18597/) (2026)
- [From Retrieval to Reasoning: Agentic Mechanism Prediction from Cell Painting Profiles](https://mlsanity.com/paper/2609.36406/) (2026)
- [RxnOptBench: Benchmarking LLMs for Reaction-Condition Optimization in Organic Methodology](https://mlsanity.com/paper/2610.02242/) (2026)
- [Masked Diffusion Language Agents for Tool-Integrated Chemical Reasoning](https://mlsanity.com/paper/2610.13330/) (2026)

## Abstract (arXiv)

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.