ChemGraph-XANES: An Agentic Framework for XANES Simulation and Analysis
| Authors | Vitor F. Grizzi et al. |
| Year | 2026 |
| Field | AI / Agents |
| arXiv | 2604.16205 |
| Download | |
| Categories | cs.AI |
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 ASE, FDMNES, Parsl, and a LangGraph/LangChain-based tool interface, the framework exposes XANES workflow operations as typed Python tools that can be orchestrated by large language model (LLM) agents. In multi-agent mode, a retrieval-augmented expert agent consults the FDMNES manual to ground parameter selection, while executor agents translate user requests into structured tool calls. We demonstrate documentation-grounded parameter retrieval and show that the same workflow supports both explicit structure-file inputs and chemistry-level natural-language requests. Because independent XANES calculations are naturally task-parallel, the framework is well suited for high-throughput deployment on high-performance computing (HPC) systems, enabling scalable XANES database generation for downstream analysis and machine-learning applications. ChemGraph-XANES thus provides a reproducible and extensible workflow layer for physics-based XANES simulation, spectral curation, and agent-compatible computational spectroscopy.
Engineering Breakdown
Plain English
undefined
Key Engineering Insight
The critical insight is that scientific simulation bottlenecks aren't usually the math—they're the workflow plumbing. By exposing domain-specific operations as typed Python tools that an LLM-based agent can compose and sequence, the authors made complex multi-step computational chemistry accessible without manual orchestration, which is the pattern that works for production AI agents.
Why It Matters for Engineers
Materials scientists and chemists waste engineering effort on glue code between different tools (structure databases, simulation engines, analysis pipelines). This pattern—using agents to wrap heterogeneous tools with a unified interface—directly applies to any domain where you're automating workflows across multiple specialized systems. It's a blueprint for production agentic systems that need to coordinate real tools.
Research Context
Computational XANES has been a bottleneck in materials discovery, but not because the physics is hard—it's because running it at scale requires coordinating structure databases, simulation parameters, job scheduling, and result validation manually. ChemGraph-XANES advances the practical use of LLM agents beyond chatbots into scientific automation by showing how to bridge natural-language task specification with provenance-tracked, production-grade computational workflows at scale.
:::tip Subscribe Get weekly breakdowns of papers like this in AI Letters - the newsletter for engineers building production AI systems. :::