ChemGraph-XANES: An Agentic Framework for XANES Simulation and Analysis
Summary: arXiv:2604.16205v1 Announce Type: cross
Abstract: Computational X-ray absorption near-edge structure (XANES) is widely used to probe local coordination environments, oxidation states, and electronic structure in chemically complex systems. However, the use of computational XANES at scale is constrained more by workflow complexity than by the underlying simulation method itself. To address this challenge, we present ChemGraph-XANES, an agentic framework for automated XANES simulation and analysis that unifies natural-language task specification, structure acquisition, FDMNES input generation, task-parallel execution, spectral normalization, and provenance-aware data curation.
Built on a robust technological foundation, ChemGraph-XANES integrates several advanced tools and frameworks:
- ASE: Atomic Simulation Environment, a set of tools for atomistic simulations.
- FDMNES: A program used for calculating X-ray absorption spectra.
- Parsl: A parallel scripting language designed to simplify the execution of complex computational tasks.
- LangGraph/LangChain: A tool interface that enables interaction with large language model agents.
The framework exposes XANES workflow operations as typed Python tools that can be orchestrated by large language model (LLM) agents. This innovative approach allows for:
- Multi-Agent Mode: In this mode, a retrieval-augmented expert agent consults the FDMNES manual to ground parameter selection, ensuring accuracy and reliability.
- Executor Agents: These agents translate user requests into structured tool calls, enhancing user experience and workflow efficiency.
One of the significant advantages of ChemGraph-XANES is its ability to support both explicit structure-file inputs and chemistry-level natural-language requests. This flexibility is pivotal for researchers who may be more familiar with chemical concepts than with technical file formats.
Moreover, the framework’s design inherently favors task-parallel execution, making it particularly well-suited for high-throughput deployment on high-performance computing (HPC) systems. This capability is essential for:
- Scalable XANES Database Generation: Researchers can efficiently generate large datasets for downstream analysis.
- Machine-Learning Applications: The extensive data generated can be utilized in various machine-learning models, further advancing research in computational spectroscopy.
In conclusion, ChemGraph-XANES provides a reproducible and extensible workflow layer for physics-based XANES simulation, spectral curation, and agent-compatible computational spectroscopy. This framework not only streamlines complex workflows but also opens new avenues for research and application in the field of X-ray absorption spectroscopy.