Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2505.20574 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908423162953728 |
|---|---|
| author | Polat, Can Tuncel, Mehmet Kurban, Mustafa Serpedin, Erchin Kurban, Hasan |
| author_facet | Polat, Can Tuncel, Mehmet Kurban, Mustafa Serpedin, Erchin Kurban, Hasan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_20574 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | xChemAgents: Agentic AI for Explainable Quantum Chemistry Polat, Can Tuncel, Mehmet Kurban, Mustafa Serpedin, Erchin Kurban, Hasan Multiagent Systems Chemical Physics Computational Physics 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. |
| title | xChemAgents: Agentic AI for Explainable Quantum Chemistry |
| topic | Multiagent Systems Chemical Physics Computational Physics |
| url | https://arxiv.org/abs/2505.20574 |