Search NASA⌕ Search
Home/Archive/DOE OSTI

DOE OSTI · 3006464

ADEPT: A Pedagogical Framework for Integrating Agentic AI with Deterministic Scientific Workflows

George, August [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States). Environmental Molecular Sciences Laboratory (EMSL)] (ORCID:0000000178764359)·Bilbao, Aivett [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States). Environmental Molecular Sciences Laboratory (EMSL)] (ORCID:0000000329858249)·Agarwal, Khushbu [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)] (ORCID:0000000218922439)·Mejia-Rodriguez, Daniel [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)] (ORCID:0000000203502941)·Samantray, Suman [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)] (ORCID:0000000333619582)·Kim, Hoshin [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)] (ORCID:0000000288662126)·Rice, Peter S. [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)] (ORCID:0000000329463781)·Jacob, Bruno [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)] (ORCID:0009000153613105)·Baer, Marcel [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)] (ORCID:0000000152230447)·Raugei, Simone [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)] (ORCID:0000000191188480)·Cheung, Margaret S. [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States). Environmental Molecular Sciences Laboratory (EMSL)] (ORCID:0000000192357661)·Rigor, Paul [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)] (ORCID:0000000307240421)
View original source ↗Read source document ↗Export metadata ↓

Abstract

The integration of Large Language Models (LLMs) into scientific research promises to accelerate discovery, yet a significant gap remains between the dynamic reasoning of Artificial Intelligence (AI) agents and the static, deterministic nature of canonical scientific workflows. This paper introduces ADEPT (Agentic Discovery and Exploration Platform for Tools), a reference architecture and pedagogical framework explicitly designed to bridge this gap. ADEPT's primary mission is to provide a transparent, "glass-box" environment where researchers and engineers can learn to effectively wrap established scientific software (e.g., BLAST, Nextflow pipelines) and compose it into reliable, agent-driven workflows. We describe its modular, multi-server architecture, which leverages the Model Context Protocol (MCP) for tool serving, LangGraph for robust agentic orchestration, and a secure nsjail-based sandbox for safe code execution. By prioritizing architectural clarity, safety, and modularity, ADEPT serves as an extensible blueprint for building trustworthy AI-augmented systems and fosters the collaborative development necessary to responsibly employ agentic AI for science. We provide practical examples of how to adapt and extend this framework, highlighting its utility in workforce development and AI-readiness capabilities across research and development projects.

Explore related subjects

97 MATHEMATICS AND COMPUTINGArtificial IntelligenceComputational BiologyComputational scienceEngineeringPedagogySoftwareSoftware development

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

George, August [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States). Environmental Molecular Sciences Laboratory (EMSL)] (ORCID:0000000178764359), Bilbao, Aivett [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States). Environmental Molecular Sciences Laboratory (EMSL)] (ORCID:0000000329858249), Agarwal, Khushbu [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)] (ORCID:0000000218922439), Mejia-Rodriguez, Daniel [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)] (ORCID:0000000203502941), Samantray, Suman [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)] (ORCID:0000000333619582), Kim, Hoshin [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)] (ORCID:0000000288662126), Rice, Peter S. [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)] (ORCID:0000000329463781), Jacob, Bruno [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)] (ORCID:0009000153613105), Baer, Marcel [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)] (ORCID:0000000152230447), Raugei, Simone [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)] (ORCID:0000000191188480), Cheung, Margaret S. [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States). Environmental Molecular Sciences Laboratory (EMSL)] (ORCID:0000000192357661), Rigor, Paul [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)] (ORCID:0000000307240421). 2025-10-10. ADEPT: A Pedagogical Framework for Integrating Agentic AI with Deterministic Scientific Workflows. https://doi.org/10.5281/zenodo.17315801

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related reports

DOE OSTI2026

TANTE: Time-adaptive operator learning via neural Taylor expansion

Operator learning for time-dependent partial differential equations (PDEs) has seen rapid progress in recent years, enabling efficient approximation of complex spatiotemporal dynamics. However, most existing methods rely on fixed time step sizes during rollout, which limits their ability to adapt to varying temporal complexity and often leads to error accumulation. In this work, we propose the Time-Adaptive Transformer with Neural Taylor Expansion (TANTE), a novel operator-learning framework that produces continuous-time predictions with adaptive step sizes. TANTE predicts future states by performing a Taylor expansion at the current state, where neural networks learn both the higher-order temporal derivatives and the local radius of convergence. This allows the model to dynamically adjust its rollout based on the local behavior of the solution, thereby reducing cumulative error and improving computational efficiency. We demonstrate the effectiveness of TANTE across a wide range of PDE benchmarks, achieving superior accuracy and adaptability compared to fixed-step baselines, delivering accuracy gains of 60-80 % and speed-ups of 30-40 % at inference time.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Structured illumination for surface-resolved grazing-incidence X-ray scattering

Grazing-incidence (GI) scattering techniques are widely used to characterize thin films, offering high surface sensitivity and insight into morphology and structure. However, these approaches typically provide statistical averaged information due to elongated footprint or limited spatial resolution due to beam size. Here we introduce a method that combines structured illumination with GI X-ray scattering and leverages our computational imaging approach to resolve local structural details. We demonstrate that our method captures local features of an organic semiconductor thin film without the need for sample rotation as in tomography. The method expands GI techniques from statistical averaging to high-resolution imaging, thereby providing the capability for detailed analysis of local material properties, such as domain shape, orientation and polymorphism, which are critical for advancing material design towards more efficient and tailored materials.

97 MATHEMATICS AND COMPUTING↗