# Chem-R: Learning to Reason as a Chemist

arXiv: https://arxiv.org/abs/2510.16880 · HTML: https://mlsanity.com/paper/2510.16880/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2025.

## Built on by (most cited first, 17 of 17)

- [LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning](https://mlsanity.com/paper/2602.07075/) (2026)
- [Agentic reinforcement learning empowers next-generation chemical language models for molecular design and synthesis](https://mlsanity.com/paper/2601.17687/) (2026)
- [MiST: Understanding the Role of Mid-Stage Scientific Training in Developing Chemical Reasoning Models](https://mlsanity.com/paper/2512.21231/) (2025)
- [Chemical Chain-of-Thought Functions as a Hallucination-Prone Molecular Scratchpad](https://mlsanity.com/paper/2607.20935/) (2026)
- [ChemDIRT: A Diversified Instruction, Representation, and Task Benchmark for Robust Chemistry-LLM Evaluation](https://mlsanity.com/paper/2608.21504/) (2026)
- [PolyReal: A Benchmark for Real-World Polymer Science Workflows](https://mlsanity.com/paper/2604.02934/) (2026)
- [Learning Mechanistic Reasoning for Chemical Reactions with Large Language Models](https://mlsanity.com/paper/2607.12771/) (2026)
- [A Scientific Reasoning Model for Organic Synthesis Procedure Generation](https://mlsanity.com/paper/2512.13668/) (2025)
- [RetroReasoner: A Reasoning LLM for Strategic Retrosynthesis Prediction](https://mlsanity.com/paper/2603.12666/) (2026)
- [Deciphering Scientific Reasoning Steps from Outcome Data for Molecule Optimization](https://mlsanity.com/paper/2603.20262/) (2026)
- [Reinforced Reasoning for End-to-End Retrosynthetic Planning](https://mlsanity.com/paper/2603.29723/) (2026)
- [S1-Omni: A Unified Multimodal Reasoning Model for Scientific Understanding, Prediction, and Generation](https://mlsanity.com/paper/2607.15686/) (2026)
- [MolGVR: A Chemistry-Grounded Framework for Text-to-Molecule Generation](https://mlsanity.com/paper/2607.29479/) (2026)
- [Molecular LLM Agents: From Architectural Design to Scientific Autonomy](https://mlsanity.com/paper/2608.23104/) (2026)
- [TMCS: Tool-Grounded Multi-Agent Reasoning for Compositional Chemical Problem Solving](https://mlsanity.com/paper/2609.35336/) (2026)
- [Latent JEPA: Abstract Future Prediction for Latent Reasoning in Chemistry](https://mlsanity.com/paper/2610.01947/) (2026)
- [MolLean: A Process-Verifiable Language for Chemical Reasoning](https://mlsanity.com/paper/2610.20459/) (2026)

## Abstract (arXiv)

Although large language models (LLMs) have significant potential to advance chemical discovery, current LLMs lack core chemical knowledge, produce unreliable reasoning trajectories, and exhibit suboptimal performance across diverse chemical tasks. To address these challenges, we propose Chem-R, a generalizable Chemical Reasoning model designed to emulate the deliberative processes of chemists. Chem-R is trained through a three-phase framework that progressively builds advanced reasoning capabilities, including: 1) Chemical Foundation Training, which establishes core chemical knowledge. 2) Chemical Reasoning Protocol Distillation, incorporating structured, expert-like reasoning traces to guide systematic and reliable problem solving. 3) Multi-task Group Relative Policy Optimization that optimizes the model for balanced performance across diverse molecular- and reaction-level tasks. This structured pipeline enables Chem-R to achieve state-of-the-art performance on comprehensive benchmarks, surpassing leading large language models, including Gemini-2.5-Pro and DeepSeek-R1, by up to 32% on molecular tasks and 48% on reaction tasks. Meanwhile, Chem-R also consistently outperforms the existing chemical foundation models across both molecular and reaction level tasks. These results highlight Chem-R's robust generalization, interpretability, and potential as a foundation for next-generation AI-driven chemical discovery. The code and model are available at https://github.com/davidweidawang/Chem-R.