# ChemAmp: Amplified Chemistry Tools via Composable Agents

arXiv: https://arxiv.org/abs/2505.21569 · HTML: https://mlsanity.com/paper/2505.21569/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 17 of its 34 references that are in the map.
- First posted on arXiv 27 May 2025.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 17 of 17)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [Molecular Transformer - A Model for Uncertainty-Calibrated Chemical Reaction Prediction](https://mlsanity.com/paper/1811.02633/) (2018)
- [What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks](https://mlsanity.com/paper/2305.18365/) (2023)
- [Multi-agent Architecture Search via Agentic Supernet](https://mlsanity.com/paper/2502.04180/) (2025)
- [Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network](https://mlsanity.com/paper/1709.04555/) (2017)
- [Few-Shot Graph Learning for Molecular Property Prediction](https://mlsanity.com/paper/2102.07916/) (2021)
- [ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoning](https://mlsanity.com/paper/2501.06590/) (2025)
- [Chemical-Reaction-Aware Molecule Representation Learning](https://mlsanity.com/paper/2109.09888/) (2021)
- [ReLM: Leveraging Language Models for Enhanced Chemical Reaction Prediction](https://mlsanity.com/paper/2310.13590/) (2023)
- [Uni-Mol2: Exploring Molecular Pretraining Model at Scale](https://mlsanity.com/paper/2406.14969/) (2024)
- [A quantitative analysis of knowledge-learning preferences in large language models in molecular science](https://mlsanity.com/paper/2402.04119/) (2024)
- [From Generalist to Specialist: A Survey of Large Language Models for Chemistry](https://mlsanity.com/paper/2412.19994/) (2024)
- [Cross-Modal Learning for Chemistry Property Prediction: Large Language Models Meet Graph Machine Learning](https://mlsanity.com/paper/2408.14964/) (2024)

## Built on by (most cited first, 1 of 1)

- [From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery](https://mlsanity.com/paper/2508.14111/) (2025)

## Abstract (arXiv)

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 (≤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.