# xChemAgents: Agentic AI for Explainable Quantum Chemistry

arXiv: https://arxiv.org/abs/2505.20574 · HTML: https://mlsanity.com/paper/2505.20574/

## Key facts

- Cited by 7 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 14 of its 40 references that are in the map.
- First posted on arXiv 26 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, 14 of 14)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [E(n) Equivariant Graph Neural Networks](https://mlsanity.com/paper/2102.09844/) (2021)
- [E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials](https://mlsanity.com/paper/2101.03164/) (2021)
- [SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks](https://mlsanity.com/paper/2006.10503/) (2020)
- [Equivariant message passing for the prediction of tensorial properties and molecular spectra](https://mlsanity.com/paper/2102.03150/) (2021)
- [Crystal Diffusion Variational Autoencoder for Periodic Material Generation](https://mlsanity.com/paper/2110.06197/) (2021)
- [TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentials](https://mlsanity.com/paper/2202.02541/) (2022)
- [Graph neural networks for materials science and chemistry](https://mlsanity.com/paper/2208.09481/) (2022)
- [Interpretable and Explainable Machine Learning for Materials Science and Chemistry](https://mlsanity.com/paper/2111.01037/) (2021)
- [CrysMMNet: Multimodal Representation for Crystal Property Prediction](https://mlsanity.com/paper/2307.05390/) (2023)
- [MARS: Multi-Agent Adaptive Reasoning with Socratic Guidance for Automated Prompt Optimization](https://mlsanity.com/paper/2503.16874/) (2025)
- [Understanding the Capabilities of Molecular Graph Neural Networks in Materials Science Through Multimodal Learning and Physical Context Encoding](https://mlsanity.com/paper/2505.12137/) (2025)

## Built on by (most cited first, 7 of 7)

- [From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery](https://mlsanity.com/paper/2508.14111/) (2025)
- [El Agente Quntur: A research collaborator agent for quantum chemistry](https://mlsanity.com/paper/2602.04850/) (2026)
- [Stress-Testing Multimodal Foundation Models for Crystallographic Reasoning](https://mlsanity.com/paper/2506.13051/) (2025)
- [Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence](https://mlsanity.com/paper/2608.21156/) (2026)
- [EMPATHIA: Multi-Faceted Human-AI Collaboration for Refugee Integration](https://mlsanity.com/paper/2508.07671/) (2025)
- [QuantumCanvas: A Multimodal Benchmark for Visual Learning of Atomic Interactions](https://mlsanity.com/paper/2512.01519/) (2025)
- [Grounded verification of chemical and materials reasoning: detection is the bottleneck](https://mlsanity.com/paper/2607.17417/) (2026)

## Abstract (arXiv)

Recent progress in multimodal graph neural networks has demonstrated that augmenting atomic XYZ geometries with textual chemical descriptors can enhance predictive accuracy across a range of electronic and thermodynamic properties. However, naively appending large sets of heterogeneous descriptors often degrades performance on tasks sensitive to molecular shape or symmetry, and undermines interpretability. xChemAgents proposes a cooperative agent framework that injects physics-aware reasoning into multimodal property prediction. xChemAgents comprises two language-model-based agents: a Selector, which adaptively identifies a sparse, weighted subset of descriptors relevant to each target, and provides a natural language rationale; and a Validator, which enforces physical constraints such as unit consistency and scaling laws through iterative dialogue. On standard benchmark datasets, xChemAgents achieves up to a 22% reduction in mean absolute error over the state-of-the-art baselines, while producing faithful, human-interpretable explanations. Experiment results highlight the potential of cooperative, self-verifying agents to enhance both accuracy and transparency in foundation-model-driven materials science. The implementation and accompanying dataset are available at https://github.com/KurbanIntelligenceLab/xChemAgents.