|
|
--- |
|
|
language: |
|
|
- en |
|
|
library_name: transformers |
|
|
tags: |
|
|
- chemistry |
|
|
- molecular-editing |
|
|
- agentic-rl |
|
|
license: apache-2.0 |
|
|
datasets: |
|
|
- little1d/mol_edit_data |
|
|
base_model: |
|
|
- Qwen/Qwen2.5-3B-Instruct |
|
|
--- |
|
|
|
|
|
# MolEditAgent-{3B} |
|
|
|
|
|
**MolEditAgent** is the Stage-1 model of the **MolAct** framework. It is fine-tuned to master basic molecular editing primitives within an agentic loop. |
|
|
|
|
|
### Key Features |
|
|
- **Actionable Operations:** Learns to perform `Add`, `Delete`, and `Substitute` operations on SMILES. |
|
|
- **Tool-Augmented:** Trained to interact with chemical tools for validity checking and similarity control. |
|
|
- **Agentic Reasoning:** Unlike static generators, it can "Think" and "Call" tools to refine the editing process. |
|
|
|
|
|
### Training & Usage |
|
|
This model serves as the foundation for property-driven optimization. |
|
|
- **Code:** [https://github.com/little1d/MolAct](https://github.com/little1d/MolAct) |
|
|
- **ArXiv** [https://arxiv.org/abs/2512.20135](https://arxiv.org/abs/2512.20135) |
|
|
|
|
|
If you use MolAct in your research, please cite: |
|
|
|
|
|
```bibtex |
|
|
@article{molact2025, |
|
|
title={MolAct: An Agentic RL Framework for Molecular Editing and Property Optimization}, |
|
|
author={Zhuo Yang and Yeyun Chen and Jiaqing Xie and Ben Gao and Shuaike Shen and Wanhao Liu and Liujia Yang and Beilun Wang and Tianfan Fu and Yuqiang Li}, |
|
|
year={2025}, |
|
|
eprint={2512.20135}, |
|
|
archivePrefix={arXiv}, |
|
|
primaryClass={cs.AI}, |
|
|
url={https://arxiv.org/abs/2512.20135} |
|
|
} |
|
|
``` |
