ChemAmp: Amplified Chemistry Tools via Composable Agents
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913039460073472 |
|---|---|
| author | Li, Zhucong Chang, Powei Xiao, Jin Zhou, Zhijian He, Qianyu Liang, Jiaqing Cao, Fenglei Yinghui, Xu Qi, Yuan |
| author_facet | Li, Zhucong Chang, Powei Xiao, Jin Zhou, Zhijian He, Qianyu Liang, Jiaqing Cao, Fenglei Yinghui, Xu Qi, Yuan |
| contents | Although LLM-based agents are proven to master tool orchestration in scientific fields, particularly chemistry, their single-task performance remains limited by underlying tool constraints. To this end, we propose tool amplification, a novel paradigm that enhances the collective capabilities of specialized tools through optimized, dynamic coordination within individual tasks. Instantiating this paradigm, we introduce ChemAmp, a computationally lightweight framework that dynamically treats chemistry tools (e.g., UniMol2, Chemformer) as composable building-block agents. It constructs task-specialized super-agents that transcend atomic tool constraints with limited data ($\leq$10 samples). Our evaluations across four core chemistry tasks molecular design, molecule captioning, reaction prediction, and property prediction demonstrate that ChemAmp outperforms chemistry-specialized models, generalist LLMs, and agent systems with tool orchestration. Critically, this bottom-up construction strategy enables 94\% inference token cost reductions versus vanilla multi-agent systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_21569 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ChemAmp: Amplified Chemistry Tools via Composable Agents Li, Zhucong Chang, Powei Xiao, Jin Zhou, Zhijian He, Qianyu Liang, Jiaqing Cao, Fenglei Yinghui, Xu Qi, Yuan Machine Learning Artificial Intelligence Computation and Language Although LLM-based agents are proven to master tool orchestration in scientific fields, particularly chemistry, their single-task performance remains limited by underlying tool constraints. To this end, we propose tool amplification, a novel paradigm that enhances the collective capabilities of specialized tools through optimized, dynamic coordination within individual tasks. Instantiating this paradigm, we introduce ChemAmp, a computationally lightweight framework that dynamically treats chemistry tools (e.g., UniMol2, Chemformer) as composable building-block agents. It constructs task-specialized super-agents that transcend atomic tool constraints with limited data ($\leq$10 samples). Our evaluations across four core chemistry tasks molecular design, molecule captioning, reaction prediction, and property prediction demonstrate that ChemAmp outperforms chemistry-specialized models, generalist LLMs, and agent systems with tool orchestration. Critically, this bottom-up construction strategy enables 94\% inference token cost reductions versus vanilla multi-agent systems. |
| title | ChemAmp: Amplified Chemistry Tools via Composable Agents |
| topic | Machine Learning Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2505.21569 |