Search NASA⌕ Search

SEARCH · Search NASA

Results for “Language model”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 289 records · Page 16
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

ChemGraph as an agentic framework for computational chemistry workflows

Atomistic simulations are essential in chemistry and materials science but remain challenging to run due to the expert knowledge required for the setup, execution, and validation stages of these calculations. We present ChemGraph, an agentic framework powered by artificial intelligence and state-of-the-art simulation tools to streamline and automate computational chemistry and materials science workflows. ChemGraph leverages graph neural network-based foundation models for accurate yet computationally efficient calculations and large language models (LLMs) for natural language understanding, task planning, and scientific reasoning to provide an intuitive and interactive interface. We evaluate ChemGraph across 13 benchmark tasks and demonstrate that smaller LLMs (GPT-4o-mini, Claude-3.5-haiku, Qwen-2.5-14B) perform well on simple workflows, while more complex tasks benefit from using larger models. Importantly, we show that decomposing complex tasks into smaller subtasks through a multi-agent framework enables GPT-4o to reach perfect accuracy and smaller LLMs to match or exceed single-agent GPT-4o's performance in these benchmarks.

Computational chemistry↗
DOE OSTI2026

GridCoPilot for Thermal Events: An LLM-Based Platform for Power Grid Reliability Analysis

Large Language Models show promise for translating natural language into database queries, but deploying such systems in safety-critical domains requires high reliability. We present an application of GridCoPilot to thermal event analysis (heatwaves and coldwaves) that affect power grid reliability. Our approach uses a LangChain SQL Agent to translate natural language queries into auditable SQL statements, with deterministic visualization routines that parse the structured query results. We introduce structural framing as a design principle, we integrate a NERC-region-level event library with county-level meteorology and decompose the combined data into three relational tables (event metadata, county-level event details, and a county-to-NERC subregion mapping), using prompt-guided joins to direct the model toward correct multi-table queries. For two core analytical patterns (identifying worst events by region and by region-year), the system achieved 100% SQL accuracy across all 16 NERC subregions and both event types (64 queries total). These results validate the approach for target use cases, though performance on diverse natural language formulations requires further investigation. We discuss design trade-offs, failure modes including JSON output truncation, and pathways for extending this approach to other hazard domains.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

VISION: a modular AI assistant for natural human-instrument interaction at scientific user facilities

Scientific user facilities, such as synchrotron beamlines, are equipped with a wide array of hardware and software tools that require a codebase for human-computer-interaction. This often necessitates developers to be involved to establish connection between users/researchers and the complex instrumentation. The advent of generative AI presents an opportunity to bridge this knowledge gap, enabling seamless communication and efficient experimental workflows. Here we present a modular architecture for the Virtual Scientific Companion by assembling multiple AI-enabled cognitive blocks that each scaffolds large language models (LLMs) for a specialized task. With VISION, we performed LLM-based operation on the beamline workstation with low latency and demonstrated the first voice-controlled experiment at an x-ray scattering beamline. The modular and scalable architecture allows for easy adaptation to new instruments and capabilities. Development on natural language-based scientific experimentation is a building block for an impending future where a science exocortex—a synthetic extension to the cognition of scientists—may radically transform scientific practice and discovery.

36 MATERIALS SCIENCE↗
DOE OSTI2026

PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space

Background Protein language models (PLMs) have revolutionized protein fitness prediction, yet their application to rapidly evolving viral pathogens is often confounded by extreme sequence homology. This homology leads to “data leakage” in standard random validation splits, yielding inflated performance metrics that fail to translate into real-world biosurveillance utility. Results We present Protein Representation Inference for Mutation Evaluation (PRIME), a framework that integrates domain-specific fine-tuning with a rigorous position-stratified validation protocol to evaluate viral threats. Using a dataset of 347,432 SARS-CoV-2 receptor binding domain (RBD) sequences, we demonstrate that while random training data split yields deceptive R 2 values (> 0.90), they fail to generalize to novel mutational sites. By benchmarking models up to 650 M parameters, we show that domain-specific fine-tuning of the ESM-C 600 M model with correctly stratified data provides an initial demonstration of predictive signal for binding affinity and expression at unseen mutational sites of binding affinity and expression on unseen sites (R 2 ~0.23), a significant advancement over base foundation models which exhibit no predictive power (R 2 <0). PRIME’s embedding-based clustering identified 3.03% of bat coronavirus sequences as candidates for further experimental prioritization based on their functional similarity to human-infective strains in embedding space, offering a perspective complementary to traditional phylogenetic methods. Conclusion PRIME establishes a new benchmark for the application of PLMs in pathogen surveillance. Our findings demonstrate that state-of-the-art models and fine-tuning, when paired with stratified validation, provide biologically meaningful insights into pathogen evolution and zoonotic risk.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Protein–Protein Interaction Networks Derived from Classical and Machine Learning-Based Natural Language Processing Tools

The study of protein-protein interactions (PPIs) provides insight into various biological mechanisms, including the binding of antibodies to antigens, enzymes to inhibitors or promoters, and receptors to ligands. Recent studies of PPIs have led to significant biological breakthroughs. For example, the study of PPIs involved in the human:SARS-CoV-2 viral infection mechanism aided in the development of the SARS-CoV-2 vaccines. Though several databases exist for the manual curation of PPI networks, text mining methods have been routinely demonstrated as useful alternatives for newly studied or understudied species where databases are incomplete. Here, the relationship extraction (RE) performance of several open-source classical text processing, machine learning (ML)-based natural language processing (NLP), and large language model (LLM)-based NLP tools were compared. Overall, our results indicated that networks derived from classical methods tend to have high true positive rates at the expense of having overconnected-networks, ML-based NLP methods have lower true positive rates but networks with the closest structures to the target network, and LLM-based NLP methods tend to exist in-between the two other approaches, with variable performances. Finally, the selection of a specific NLP approach should be tied to the needs of a study and text availability, as models varied in performance due to the amount of text provided.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS2014

Improved Traceability of Mission Concept to Requirements Using Model Based Systems Engineering

Model Based Systems Engineering (MBSE) has recently been gaining significant support as a means to improve the traditional document-based systems engineering (DBSE) approach to engineering complex systems. In the spacecraft design domain, there are many perceived and propose benefits of an MBSE approach, but little analysis has been presented to determine the tangible benefits of such an approach (e.g. time and cost saved, increased product quality). This thesis presents direct examples of how developing a small satellite system model can improve traceability of the mission concept to its requirements. A comparison of the processes and approaches for MBSE and DBSE is made using the NASA Ames Research Center SporeSat CubeSat mission as a case study. A model of the SporeSat mission is built using the Systems Modeling Language standard and No Magics MagicDraw modeling tool. The model incorporates mission concept and requirement information from the missions original DBSE design efforts. Active dependency relationships are modeled to analyze the completeness and consistency of the requirements to the mission concept. Overall experience and methodology are presented for both the MBSE and original DBSE design efforts of SporeSat.

Systems Engineering↗
NASA NTRS2022

A Systems Model for System-Wide Safety Safety Demonstrator (SD-1): Wildfire Response Operations

The aim of this internship-based project was to contribute to the ongoing development of a systems model for System-Wide Safety’s first Technical Challenge 5 (TC5) series Safety Demonstrator (SD-1), which will be a demonstration of an In-Time Aviation Safety Management System (IASMS) in emerging wildfire response operations. Using Models-Based Systems Engineering (MBSE) principles to develop the model, I organized and traced previously collected stakeholder needs from the Spring 2022 NASA System-Wide Safety Wildland Firefighting Operations Virtual Workshop (https://nari.arc.nasa.gov/sws-wildfire) to system elements, creating connections which can be used in the future by the project engineers to identify and address requirements gaps throughout the system design process. I also identified and modeled preliminary use case scenarios for aerial assets in the demonstrator and, building on previously produced preliminary high-level models of the 8 SD-1 Services, Functions, and Capabilities (SFCs) and their IASMS data flows, worked to model the Real-Time Risk Assessment (RTRA) tool as an implementation of Risk Assessment and Management that can take in multiple sets of data monitored by SFCs. Project deliverables include stakeholder requirements tables and matrices and systems model diagrams produced with MagicDraw software in the SysML Systems Modeling Language, with eventual plans to connect model diagrams to a Department of Defense Operational Viewpoint (OV-1) graphic, a high-level operational concept graphic that will be used to visualize the SD-1 scenarioin a future phase. The system model serves to provide a common understanding of the scope of and activities necessary for the completion of SD-1,and traces how stakeholder needs are to be addressed.

model-based systems engineering↗
NASA NTRSDate not supplied

Problem Complexity and LLM: H-M Team Reliability in Challenging Environments

In traditional human-machine operations, the functional decomposition of actions and responsibilities among various agents is assigned a priori. For instance, in current air traffic operations, although assisted by software, human pilots have the ultimate control of aircraft. Multiagent human-machine and machine-machine systems will face problems of varying and potentially unpredicted complexity in future challenging scenarios of planetary, en route, and orbital activities. Hence, it is important to enable dynamic transfer of decision-making to appropriate team members, human or machine, depending on which agent is best equipped to solve that specific problem on a time budget. In this paper, we consider aspects of problem-solving and its modeling that affect the outcomes of decision-making as a function of solution quality and the likelihood of solving the problem on a required time budget. We focus on Large Language Models (LLM) as potential machine teammates and conclude that practical, predictive modeling of their performance, at the current stage of their development, is infeasible. Simple examples help us illustrate that current LLM will require fundamental advancements to provide reliable support in team decision-making, especially in safety-critical and time-critical domains. The study is not meant to diminish the value of the remarkable capabilities of LLM, but rather to gain a better understanding of the technology’s appropriate use and the needed additions.

function allocation↗
DOE OSTI2025

genomeocean: a pretrained microbial genome foundational model (genomeoceanLLM) v1.0

We present Genomeocean, a foundational genome language model that represents the microbial genome sequences from complex environmental samples. By training on a large, diverse metagenomic dataset, Genomeocean learns species-specific sequence composition and can generate long, realistic open reading frames (ORFs). Our model employs a Byte-pair-encoding (BPE) tokenization strategy, allowing it to efficiently process large genomic datasets and generate long sequences up to 50kb. We demonstrate that fine-tuning Genomeocean can generate novel gene clusters encoding biosynthetic pathways, showcasing its ability to model both fundamental and complex biological processes. Our work establishes Genomeocean as a powerful tool for understanding microbial genome biology and paves the way for its application in a range of fields, from synthetic biology to microbiome research.

Wang, Zhong [Lawrence Berkeley National Laboratory↗
DOE OSTI2026

BrickQA: Bridging the Semantic Gap in Building Operations with Dynamic Graph Exploration

While standardized ontologies like the Brick schema address data heterogeneity in Building Automation Systems (BAS), accessing this semantic data remains a challenge as domain experts often lack the expertise to formulate complex SPARQL queries. To bridge this gap, we present BrickQA, a Large Language Model (LLM)-based framework that translates natural language into executable SPARQL queries through structured query decomposition, dynamic schema exploration, and inline validation. BrickQA utilizes an iterative reasoning agent to actively navigate graph topology through dynamic exploration actions without requiring exhaustive context injection or model fine-tuning. This approach effectively mitigates hallucinations, particularly in large-scale building knowledge graphs. Empirical evaluation on BuildingQA, a standardized benchmark, demonstrates that BrickQA significantly outperforms ReAct baselines, delivering a 0.291–0.355 absolute F1 improvement while achieving 3 × –12.7 × higher token cost-efficiency. Beyond these metrics, the framework maintains structural fidelity across heterogeneous buildings and remains resilient to ambiguous queries without requiring site-specific fine-tuning. Furthermore, a case study on operational analytics validates the framework’s capability to handle temporal and aggregation constraints, effectively transforming abstract semantic models into actionable facility management insights.1

Ko, Yun-Dam↗
DOE OSTI2025

ON THE EFFECTIVENESS OF LLMS IN UNIT TEST GENERATION FOR STRUCTURED TEXT PROGRAMS

The reliability of industrial automation systems heavily depends on the correctness of Programmable Logic Controller (PLC) programs, which are often written in Structured Text (ST). While Large Language Models (LLMs) have shown promise in automating test generation for mainstream programming languages, their effectiveness for the syntactically strict ST language remains underexplored. This thesis presents a systematic empirical evaluation of three state-of-the-art LLMs—GPT-4o, Gemini 2.5 Pro, and Claude Sonnet 4.5—for generating ST unit tests. We examine three prompting strategies: Natural Language (NL), Code Language (CL), and Chain-of-Thought (CoT), across a curated set of 11 ST function blocks. The quality of the generated tests is assessed using Compilation Success Rate (CSR), Statement Coverage (SC), and Branch Coverage (BC). In the zero-shot setting, Claude Sonnet 4.5 achieves the highest CSR, while Gemini 2.5 Pro consistently delivers the best statement and branch coverage, particularly under CL prompts. By incorporating a one-shot CL prompt, all models exhibit substantial improvements—most notably GPT-4o, whose CSR increases from 45.45% to 90.91%, with substantial gains in both SC and BC. To further contextualize these findings, we compare GPT-4o’s one-shot results with PLCAutoTester, a state-ofthe- art ST unit test generation tool, on an additional benchmark dataset. While LLMgenerated tests approach competitive coverage levels, PLCAutoTester maintains significantly higher and more stable coverage across programs. This study provides the first comprehensive benchmark of modern LLMs for ST unit testing, highlighting their strengths, limitations, and improvements through one-shot prompting, and positioning their performance relative to specialized automated testing tools in industrial automation.

42 ENGINEERING↗
NASA NTRS2012

Specification and Design of Electrical Flight System Architectures with SysML

Modern space flight systems are required to perform more complex functions than previous generations to support space missions. This demand is driving the trend to deploy more electronics to realize system functionality. The traditional approach for the specification, design, and deployment of electrical system architectures in space flight systems includes the use of informal definitions and descriptions that are often embedded within loosely coupled but highly interdependent design documents. Traditional methods become inefficient to cope with increasing system complexity, evolving requirements, and the ability to meet project budget and time constraints. Thus, there is a need for more rigorous methods to capture the relevant information about the electrical system architecture as the design evolves. In this work, we propose a model-centric approach to support the specification and design of electrical flight system architectures using the System Modeling Language (SysML). In our approach, we develop a domain specific language for specifying electrical system architectures, and we propose a design flow for the specification and design of electrical interfaces. Our approach is applied to a practical flight system.

specifications↗
DOE OSTI2025

Generative AI for design of nanoporous materials: review and future prospects

Generative artificial intelligence (AI) is emerging as a powerful tool for advancing the design of nanoporous materials such as metal–organic frameworks, covalent–organic frameworks, and zeolites. These materials have potential application in important areas such as carbon capture, catalysis, gas storage, chemical separation, and drug delivery due to their modular, tunable structures, and their performance in these areas depends on precise control over their structure, chemical functionalities, and properties. Herein, we provide a review of generative AI algorithms that are emerging as powerful tools for the design of nanoporous materials, namely generative adversarial networks, variational autoencoders, diffusion models, genetic algorithms, reinforcement learning, and large language models. Some models are particularly good at generating diverse and high-quality designs, while others excel at exploring large design spaces or optimizing materials with desired properties. Certain algorithms also allow for efficient transitions between different designs, and some offer versatility in generating materials based on textual input. We discuss the advantages, limitations, and applications of these algorithms in porous material design and emphasize the future potential of integrating AI with experimental workflows to accelerate the development and validation of AI-generated materials.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Expert evaluation of LLM world models: A high-T c superconductivity case study

Large Language Models (LLMs) show great promise as a powerful tool for scientific literature exploration. However, their effectiveness in providing scientifically accurate and comprehensive answers to complex questions within specialized domains remains an active area of research. Using the field of high-temperature cuprates as an exemplar, we evaluate the ability of LLM systems to understand the literature at the level of an expert. We construct an expert-curated database of 1,726 scientific papers that covers the history of the field, and a set of 67 expert-formulated questions that probe deep understanding of the literature. We then evaluate six different LLM-based systems for answering these questions, including both commercially available closed models and a custom retrieval-augmented generation (RAG) system capable of retrieving images alongside text. Experts then evaluate the answers of these systems against a rubric that assesses balanced perspectives, factual comprehensiveness, succinctness, and evidentiary support. Among the six systems, two using RAG on curated literature outperformed existing closed models across key metrics, particularly in providing comprehensive and well-supported answers. We discuss promising aspects of LLM performances as well as critical short-comings of all the models. The set of expert-formulated questions and the rubric will be valuable for assessing expert level performance of LLM based reasoning systems.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Scaling Laws of Graph Neural Networks for Atomistic Materials Modeling

Atomistic materials modeling is a critical task with wide-ranging applications, from drug discovery to materials science, where accurate predictions of the target material property can lead to significant advancements in scientific discovery. Graph Neural Networks (GNNs) represent the state-of-the-art approach for modeling atomistic material data thanks to their capacity to capture complex relational structures. While machine learning performance has historically improved with larger models and datasets, GNNs for atomistic materials modeling remain relatively small compared to large language models (LLMs), which leverage billions of parameters and terabyte-scale datasets to achieve remarkable performance in their respective domains. To address this gap, we explore the scaling limits of GNNs for atomistic materials modeling by developing a foundational model with billions of parameters, trained on extensive datasets in terabytescale. Our approach incorporates techniques from LLM libraries to efficiently manage large-scale data and models, enabling both effective training and deployment of these large-scale GNN models. This work addresses three fundamental questions in scaling GNNs: the potential for scaling GNN model architectures, the effect of dataset size on model accuracy, and the applicability of LLM-inspired techniques to GNN architectures. Specifically, the outcomes of this study include (1) insights into the scaling laws for GNNs, highlighting the relationship between model size, dataset volume, and accuracy, (2) a foundational GNN model optimized for atomistic materials modeling, and (3) a GNN codebase enhanced with advanced LLM-based training techniques. Our findings lay the groundwork for large-scale GNNs with billions of parameters and terabyte-scale datasets, establishing a scalable pathway for future advancements in atomistic materials modeling.

Li, Chaojian [ORNL] (ORCID:0000000340309777)↗
DOE OSTI2026

A roadmap toward scaling, reasoning and self-evolving foundation models for nuclear and particle physics

Foundation models have revolutionized artificial intelligence, with Large Language Models demonstrating unprecedented capabilities in multimodal understanding, reasoning and tool use. Nuclear and particle physics stands at a critical juncture where similar transformative potential awaits realization. The field generates exabytes of experimental data, exascale simulations, and decades of theoretical insights — yet these remain largely disconnected from modern Artifical Intelligence (AI) capabilities, with most physics AI applications confined to narrow, task-specific models that suffer from domain shifting when applied to real experimental data. We present a roadmap for FM4NPP (Foundation Model for Nuclear and Particle Physics), systematically scaling from current proof-of-concept models to trillion-parameter architectures capable of autonomous discovery. Our approach advances three critical frontiers: unified data infrastructure integrating detector data, scientific knowledge and computational tools across global facilities; multi-facility foundation models enabling cross-experiment knowledge transfer and accelerated discovery; and agentic AI capabilities for reasoning and autonomous tool use. The resulting self-evolving FM4NPP will transform physics research by converting time-intensive data analysis, theory derivation and computational bottlenecks into rapid AI–human collaborative discovery. This paradigm shift promises to fundamentally accelerate scientific progress in nuclear and particle physics, enabling researchers to focus on high-level insights while AI handles routine analysis and explores vast parameter spaces beyond human capacity.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

RingX: Scalable Parallel Attention for Long-Context Learning on HPC

The attention mechanism has become foundational for remarkable AI breakthroughs since the introduction of the Transformer, driving the demand for increasingly longer context to power frontier models such as large-scale reasoning language models and high-resolution image/video generators. However, its quadratic computational and memory complexities present substantial challenges. Current state-of-the-art parallel attention methods, such as ring attention, are widely adopted for long-context training but utilize a point-to-point communication strategy that fails to fully exploit the capabilities of modern HPC network architectures. In this work, we propose ringX, a scalable family of parallel attention methods optimized explicitly for HPC systems. By enhancing workload partitioning, refining communication patterns, and improving load balancing, ringX achieves up to 3.4 × speedup compared to conventional ring attention on the Frontier supercomputer. Optimized for both bi-directional and causal attention mechanisms, ringX demonstrates its effectiveness through training benchmarks of a Vision Transformer (ViT) on a climate dataset and a Generative Pre-Trained Transformer (GPT) model, Llama3 8B. Our method attains an end-to-end training speedup of approximately 1.5 × in both scenarios. To our knowledge, the achieved 38% model FLOPs utilization (MFU) for training Llama3 8B with a 1M-token sequence length on 4,096 GPUs represents one of the highest training efficiencies reported for long-context learning on HPC systems. Our code implementation is available at https://github.com/jqyin/ringX-attention.

Yin, Junqi [ORNL] (ORCID:0000000338435520)↗
NASA NTRS1999

Using Model Checking to Validate AI Planner Domain Models

This report describes an investigation into using model checking to assist validation of domain models for the HSTS planner. The planner models are specified using a qualitative temporal interval logic with quantitative duration constraints. We conducted several experiments to translate the domain modeling language into the SMV, Spin and Murphi model checkers. This allowed a direct comparison of how the different systems would support specific types of validation tasks. The preliminary results indicate that model checking is useful for finding faults in models that may not be easily identified by generating test plans.

Penix, John↗