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 325 records · Page 18
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Operating advanced scientific instruments with AI agents that learn on the job

Advanced scientific user facilities, such as next generation X-ray light sources and self-driving laboratories, are revolutionizing scientific discovery by automating routine tasks and enabling rapid experimentation and characterizations. However, these facilities must continuously evolve to support new experimental workflows, adapt to diverse user projects, and meet growing demands for more intricate instruments and experiments. This continuous development introduces significant operational complexity, necessitating a focus on usability, reproducibility, and intuitive human-instrument interaction. In this work, we explore the integration of agentic AI, powered by Large Language Models (LLMs), as a transformative tool to achieve this goal. We present our approach to developing a human-in-the-loop pipeline for operating advanced instruments including an X-ray nanoprobe beamline and an autonomous robotic station dedicated to the design and characterization of materials. Specifically, we evaluate the potential of various LLMs as trainable scientific assistants for orchestrating complex, multi-task workflows, which also include multimodal data, optimizing their performance through optional human input and iterative learning. We demonstrate the ability of AI agents to bridge the gap between advanced automation and user-friendly operation, paving the way for more adaptable and intelligent scientific facilities.

Large Language Models↗
DOE OSTI2025

Confidence-weighted integration of human and machine judgments for superior decision-making

Large language models (LLMs) can surpass humans in certain forecasting tasks. What role does this leave for humans in the overall decision process? One possibility is that humans, despite performing worse than LLMs, can still add value when teamed with them. A human and machine team can surpass each individual teammate when team members’ confidence is well calibrated and team members diverge in which tasks they find difficult (i.e., calibration and diversity are needed). We simplified and extended a Bayesian approach to combining judgments using a logistic regression framework that integrates confidence-weighted judgments for any number of team members. Using this straightforward method, we demonstrated its effectiveness in both image classification and neuroscience forecasting tasks. Combining human judgments with one or more machines consistently improved overall team performance. Our hope is that this simple and effective strategy for integrating the judgments of humans and machines will lead to productive collaborations.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2004

Development of a State Machine Sequencer for the Keck Interferometer: Evolution, Development and Lessons Learned using a CASE Tool Approach

This paper presents a discussion of the evolution of a sequencer from a simple EPICS (Experimental Physics and Industrial Control System) based sequencer into a complex implementation designed utilizing UML (Unified Modeling Language) methodologies and a CASE (Computer Aided Software Engineering) tool approach. The main purpose of the sequencer (called the IF Sequencer) is to provide overall control of the Keck Interferometer to enable science operations be carried out by a single operator (and/or observer). The interferometer links the two 10m telescopes of the W. M. Keck Observatory at Mauna Kea, Hawaii. The IF Sequencer is a high-level, multi-threaded, Hare1 finite state machine, software program designed to orchestrate several lower-level hardware and software hard real time subsystems that must perform their work in a specific and sequential order. The sequencing need not be done in hard real-time. Each state machine thread commands either a high-speed real-time multiple mode embedded controller via CORB A, or slower controllers via EPICS Channel Access interfaces. The overall operation of the system is simplified by the automation. The UML is discussed and our use of it to implement the sequencer is presented. The decision to use the Rhapsody product as our CASE tool is explained and reflected upon. Most importantly, a section on lessons learned is presented and the difficulty of integrating CASE tool automatically generated C++ code into a large control system consisting of multiple infrastructures is presented.

interferometer↗
NASA NTRSDate not supplied

Combinatorial Reasoning: Selecting Reasons in Generative AI Pipelines via Combinatorial Optimization

Recent Large Language Models (LLMs) have demonstrated impressive capabilities at tasks that require human intelligence and are a significant step towards human-like artificial intelligence (AI). Yet the performance of LLMs at reasoning tasks have been subpar and the reasoning capability of LLMs is a matter of significant debate. While it has been shown that the choice of the prompting technique to the LLM can alter its performance on a multitude of tasks, including reasoning, the best performing techniques require human-made prompts with the knowledge of the tasks at hand. We introduce a framework for what we call Combinatorial Reasoning (CR), a fully-automated prompting method, where reasons are sampled from an LLM pipeline and mapped into a Quadratic Unconstrained Binary Optimization (QUBO) problem. The framework investigates whether QUBO solutions can be profitably used to select a useful subset of the reasons to construct a Chain-of-Thought style prompt. We explore the acceleration of CR with specialized solvers. We also investigate the performance of simpler zero-shot strategies such as linear majority rule or random selection of reasons. Our preliminary study indicates that coupling a combinatorial solver to generative AI pipelines is an interesting avenue for AI reasoning and elucidates design principles for future CR methods.

combinatorial reasoning↗
DOE OSTI2026

Agentic traffic intelligence: Augmented human-in-the-loop scenario generation for microscopic traffic simulation

Traditional microscopic traffic simulation generation often relies on static datasets and manual design, limiting its ability to simulate complex conditions easily. This paper presents a novel framework, Agentic Traffic Intelligence, which combines human approval large language models (LLMs), the Real-Twin tool, and multi-agent systems to perform realistic microscopic traffic simulation scenario generation. The proposed framework incorporates human-in-the-loop (HIL) control, retrieval-augmented generation (RAG), and multi-agent control mechanisms. HIL mechanisms are used to guide multiple LLMs focused on attributes for microscopic simulation generation and to improve the interpretability and transparency of LLM execution for users. RAG enhances context extraction by dynamically integrating external knowledge sources for traffic scenario generation foundations. A multi-agent architecture with supervisory control coordinates the interaction of simulation components, including traffic simulators, control logic, and calibration tools. This enables the synthesis of simulation-ready scenarios that reflect dynamic demand profiles and behavior controls. Furthermore, the framework fuses multisource traffic data with unstructured context and supports iterative refinement through interactive user feedback. Validated through microscopic simulation using Simulation of Urban Mobility, the generated scenarios demonstrate high-fidelity network generation with inflow and turn movement and behavioral calibration, offering a robust and efficient tool for stress-testing and optimizing urban mobility systems.

Hierarchical multi-agent control↗
NASA NTRS1985

An abstract specification language for Markov reliability models

Markov models can be used to compute the reliability of virtually any fault tolerant system. However, the process of delineating all of the states and transitions in a model of complex system can be devastatingly tedious and error-prone. An approach to this problem is presented utilizing an abstract model definition language. This high level language is described in a nonformal manner and illustrated by example.

Butler, R. W.↗
NASA NTRS2016

Effort to Accelerate MBSE Adoption and Usage at JSC

This paper describes the authors' experience in adopting Model Based System Engineering (MBSE) at the NASA/Johnson Space Center (JSC). Since 2009, NASA/JSC has been applying MBSE using the Systems Modeling Language (SysML) to a number of advanced projects. Models integrate views of the system from multiple perspectives, capturing the system design information for multiple stakeholders. This method has allowed engineers to better control changes, improve traceability from requirements to design and manage the numerous interactions between components. As the project progresses, the models become the official source of information and used by multiple stakeholders. Three major types of challenges that hamper the adoption of the MBSE technology are described. These challenges are addressed by a multipronged approach that includes educating the main stakeholders, implementing an organizational infrastructure that supports the adoption effort, defining a set of modeling guidelines to help engineers in their modeling effort, providing a toolset that support the generation of valuable products, and providing a library of reusable models. JSC project case studies are presented to illustrate how the proposed approach has been successfully applied.

Wang, Lui↗
DOE OSTI2025

Automated Waterbox Inspection for Nuclear Power Plants Using Computer Vision - Based Change Detection

Nuclear power plant waterboxes require regular inspection for leaks, missing components, and structural damage during maintenance outages. Traditional manual inspection is time-consuming and poses safety risks from confined space entry. We developed an automated computer vision system for drone-based waterbox inspection in partnership with Florida Light and Power. Our approach uses feature detection and matching to identify critical changes between baseline and current inspection images, automatically flagging additions (leaks/debris), removals (missing plugs), and translations (displaced components) while compensating for drone movement and environmental variations. We systematically evaluated six feature matching methods, from classical approaches (SIFT+BF) to state-of-the-art neural networks (SuperPoint+SuperGlue), using both standard benchmarks (HPatches) and waterbox-specific validation with real-world augmentations. SuperPoint+SuperGlue achieved superior performance with 7.82 pixels RMSE and 100% success rate—2.8x better accuracy than our baseline. While the pre-trained model has commercial licensing restrictions for nuclear deployment, our findings validate this architecture for custom training. We implemented a real-time GUI demonstrating the SIFT+BF approach for immediate deployment, processing drone feeds at 30 FPS with color-coded change visualization. Future work includes training a custom SuperPoint+SuperGlue model on waterbox data and integrating Vision-Language Models for automated reporting and maintenance guidance.

46 - INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AN↗
DOE OSTI2025

Dynamic in-context learning with conversational models for data extraction and materials property prediction

The advent of natural language processing and large language models (LLMs) has revolutionized the extraction of data from unstructured scholarly papers. However, ensuring data trustworthiness remains a significant challenge. In this paper, we introduce PropertyExtractor, an open-source tool that leverages advanced conversational LLMs such as Google gemini-pro and OpenAI gpt-4, blends zero-shot with few-shot in-context learning, and employs engineered prompts for the dynamic refinement of structured information hierarchies—enabling autonomous, efficient, scalable, and accurate identification, extraction, and verification of material property data. Our tests on material data demonstrate precision and recall that exceed 95% with an error rate of ∼9%, highlighting the effectiveness and versatility of the toolkit. Finally, databases for 2D material thicknesses, a critical parameter for device integration, and energy bandgap values are developed using PropertyExtractor. In particular, for the thickness database, the rapid evolution of the field has outpaced both experimental measurements and computational methods, creating a significant data gap. Our work addresses this gap and showcases the potential of PropertyExtractor as a reliable and efficient tool for the autonomous generation of various material property databases, advancing the field.

Ekuma, Chinedu E. (ORCID:0000000258527556)↗
DOE OSTI2026

Bayesian Optimization of Catalysis with In-Context Learning

Large language models (LLMs) can perform accurate classification with zero or few examples through in-context learning (ICL), allowing the model to observe query-relevant examples at inference time and eliminating the need for additional weight updates to generalize beyond its original training data. We extend this capability to regression with uncertainty estimation using frozen LLMs (e.g., GPT-4o, Gemini), enabling Bayesian optimization (BO) in natural language without explicit model training or feature engineering. We apply this to materials discovery by representing materials as synthesis and testing procedures for use in natural language prompts. This Bayesian, design-first approach prioritizes optimization toward target material properties before detailed characterization, in contrast to conventional experimental workflows that often emphasize characterization of suboptimal materials. On benchmarks like aqueous solubility and oxidative coupling of methane (OCM), BO-ICL matches or outperforms Gaussian processes. In live experiments on the reverse water–gas shift (RWGS) reaction, BO-ICL identifies multimetallic catalysts that approach equilibrium CO yield within 6 and 10 iterations from a pool of 3,700 and 360,000 candidates, respectively. Our method redefines materials representation and accelerates discovery, with broad applications across catalysis, materials science, and AI.

Calibration↗
NASA NTRS2013

Model-based Systems Engineering: Creation and Implementation of Model Validation Rules for MOS 2.0

Model-based Systems Engineering (MBSE) is an emerging modeling application that is used to enhance the system development process. MBSE allows for the centralization of project and system information that would otherwise be stored in extraneous locations, yielding better communication, expedited document generation and increased knowledge capture. Based on MBSE concepts and the employment of the Systems Modeling Language (SysML), extremely large and complex systems can be modeled from conceptual design through all system lifecycles. The Operations Revitalization Initiative (OpsRev) seeks to leverage MBSE to modernize the aging Advanced Multi-Mission Operations Systems (AMMOS) into the Mission Operations System 2.0 (MOS 2.0). The MOS 2.0 will be delivered in a series of conceptual and design models and documents built using the modeling tool MagicDraw. To ensure model completeness and cohesiveness, it is imperative that the MOS 2.0 models adhere to the specifications, patterns and profiles of the Mission Service Architecture Framework, thus leading to the use of validation rules. This paper outlines the process by which validation rules are identified, designed, implemented and tested. Ultimately, these rules provide the ability to maintain model correctness and synchronization in a simple, quick and effective manner, thus allowing the continuation of project and system progress.

Model-based Systems Engineering (MBSE)↗
DOE OSTI2026

An Autonomous MCP Bridge to Rucio: Enhancing Data Management Accessibility for High Energy Physics

The Rucio Data Management System [1] is an important tool used by High Energy Physics experiments, including those at Fermi National Accelerator Laboratory, to store and manage exabyte-scale scientific datasets. Despite its central role in coordinating data across globally distributed storage sites, Rucio's command line interface (CLI) presents a steep learning curve, and makes it difficult for scientists to navigate through. To solve this issue, a containerized Model Context Protocol (MCP) [2] server was built that connects Large Language Models directly to Rucio, allowing AI agents to handle data tasks by using simple, natural language rather than memorized terminal commands. The core engineering focus of this project was moving the server away from slow terminal commands that require text parsing and replacing them with a native Python Client API toolset and a planned REST API framework. Moving to the Python API handles data operations directly in memory, which helps clear up formatting errors, provides the AI with clean, structured JSON data and speeds up tool execution. To prove that the system actually works, a benchmarking pipeline was also built with various questions to test the AI across four different model configurations. The questions included finding data scopes, tracking down specific datasets, and checking replication rules. Through benchmarking, early runs showed that with raw terminal text, the model would get confused and stuck, whereas switching to the Python API to feed the AI clean, structured data yielded massive improvement. By creating an intelligent and autonomous bridge to a storage network, this project shows how AI can be implemented in scientific data management, which ultimately helps scientists at Fermilab spend less time sorting through data and more time focusing on their experiments and analysis.

Akella, Kashyap [William Rainey Harper Coll.]↗
NASA NTRS2012

On Using SysML, DoDAF 2.0 and UPDM to Model the Architecture for the NOAA's Joint Polar Satellite System (JPSS) Ground System (GS)

The JPSS Ground System is a lIexible system of systems responsible for telemetry, tracking & command (TT &C), data acquisition, routing and data processing services for a varied lIeet of satellites to support weather prediction, modeling and climate modeling. To assist in this engineering effort, architecture modeling tools are being employed to translate the former NPOESS baseline to the new JPSS baseline, The paper will focus on the methodology for the system engineering process and the use of these architecture modeling tools within that process, The Department of Defense Architecture Framework version 2,0 (DoDAF 2.0) viewpoints and views that are being used to describe the JPSS GS architecture are discussed. The Unified Profile for DoOAF and MODAF (UPDM) and Systems Modeling Language (SysML), as ' provided by extensions to the MagicDraw UML modeling tool, are used to develop the diagrams and tables that make up the architecture model. The model development process and structure are discussed, examples are shown, and details of handling the complexities of a large System of Systems (SoS), such as the JPSS GS, with an equally complex modeling tool, are described

Hayden, Jeffrey L.↗
NASA NTRS2015

Analyzing Cyber Security Threats on Cyber-Physical Systems Using Model-Based Systems Engineering

The spectre of cyber attacks on aerospace systems can no longer be ignored given that many of the components and vulnerabilities that have been successfully exploited by the adversary on other infrastructures are the same as those deployed and used within the aerospace environment. An important consideration with respect to the mission/safety critical infrastructure supporting space operations is that an appropriate defensive response to an attack invariably involves the need for high precision and accuracy, because an incorrect response can trigger unacceptable losses involving lives and/or significant financial damage. A highly precise defensive response, considering the typical complexity of aerospace environments, requires a detailed and well-founded understanding of the underlying system where the goal of the defensive response is to preserve critical mission objectives in the presence of adversarial activity. In this paper, a structured approach for modeling aerospace systems is described. The approach includes physical elements, network topology, software applications, system functions, and usage scenarios. We leverage Model-Based Systems Engineering methodology by utilizing the Object Management Group's Systems Modeling Language to represent the system being analyzed and also utilize model transformations to change relevant aspects of the model into specialized analyses. A novel visualization approach is utilized to visualize the entire model as a three-dimensional graph, allowing easier interaction with subject matter experts. The model provides a unifying structure for analyzing the impact of a particular attack or a particular type of attack. Two different example analysis types are demonstrated in this paper: a graph-based propagation analysis based on edge labels, and a graph-based propagation analysis based on node labels.

MBSE↗
NASA NTRSDate not supplied

Open Innovation for a NASA Architecture Library

NASA’s Center of Excellence for Collaborative Innovation (CoECI) uses open innovation, or “crowdsourcing”, to access the global public to find ideas, concepts, designs, or solutions that meet a previously unmet need possibly resulting in significant advances in performance. The Center of Excellence for Collaborative Innovation was launched at the request of the White House Office of Science and Technology Policy. This is both a non-traditional method of innovation and a non-traditional method of outreach to the public to involve them in space technologies and programs. It has been used often for software development and new hardware technology. In this case we applied it to innovate with systems engineering tools for creating space architectures. The challenge was sponsored by NASA Engineering and Safety Center Systems Engineering Technical Fellow as part of a program for NASA’s adoption of MBSE. It was a trial to see if there would be as much participation or quality submissions with this more specialized topic and skill. The challenge sought space architecture representations and decompositions to create a library of modeled parts in a system modeling language (SysML). Mission architects mostly start from scratch to build model elements representing the functional and physical architecture of a system in SysML. There are a few beginning libraries, but these are also local to a program or group. A common library will save system engineers a large amount of time, will allow project stakeholders to recognize common graphics and quickly understand the architecture options. The challenge was promoted internationally, especially through professional organizations and universities with a systems engineering focus. It was open for 4 months, purposefully over the winter holiday break time to allow participants extra time outside of work or school. The challenge was designed so that expertise in space hardware was not necessary but getting to play with models of space architecture could provide motivation to participate. We did not receive as many entries as other broader outreach challenges, but the ones we received were extremely thorough and high quality. Solutions came from individuals and teams, students and professional consultants from the United States and Europe. We learned a few lessons about how to engage with the public and what characteristics of a problem result in good crowdsourcing results. The outreach challenge produced several useful ideas and modeled space elements, and the group will be engaging the winners to learn more about their new approaches.

innovation↗
NASA NTRS2015

The Use of UML for Software Requirements Expression and Management

It is common practice to write English-language "shall" statements to embody detailed software requirements in aerospace software applications. This paper explores the use of the UML language as a replacement for the English language for this purpose. Among the advantages offered by the Unified Modeling Language (UML) is a high degree of clarity and precision in the expression of domain concepts as well as architecture and design. Can this quality of UML be exploited for the definition of software requirements? While expressing logical behavior, interface characteristics, timeliness constraints, and other constraints on software using UML is commonly done and relatively straight-forward, achieving the additional aspects of the expression and management of software requirements that stakeholders expect, especially traceability, is far less so. These other characteristics, concerned with auditing and quality control, include the ability to trace a requirement to a parent requirement (which may well be an English "shall" statement), to trace a requirement to verification activities or scenarios which verify that requirement, and to trace a requirement to elements of the software design which implement that requirement. UML Use Cases, designed for capturing requirements, have not always been satisfactory. Some applications of them simply use the Use Case model element as a repository for English requirement statements. Other applications of Use Cases, in which Use Cases are incorporated into behavioral diagrams that successfully communicate the behaviors and constraints required of the software, do indeed take advantage of UML's clarity, but not in ways that support the traceability features mentioned above. Our approach uses the Stereotype construct of UML to precisely identify elements of UML constructs, especially behaviors such as State Machines and Activities, as requirements, and also to achieve the necessary mapping capabilities. We describe this approach in the context of a space-based software application currently under development at the Jet Propulsion Laboratory.

model-based engineering↗
DOE OSTI2025

BuildingQA: A Benchmark for Natural Language Question Answering over Building Knowledge Graphs

Graph-based representations of building metadata using ontologies like Brick are vital for smart building applications, but querying them remains a challenge for practitioners. Knowledge Graph Question Answering (KGQA) systems, meant to retrieve answers from natural language questions, traditionally require large-scale training data, making them ill-suited for the specialized and data-scarce building domain. The advent of Large Language Models (LLMs) offers a paradigm shift, enabling zero-shot natural language querying without building/domain-specific training. Yet, there is no standardized benchmark for building-specific KGQA which can guide and validate research in this area. To address this gap, our work makes three primary contributions. First, we introduce the BuildingQA Benchmark Dataset, constructed through a multi-stage process of collecting practitioner data, augmenting it with LLMs for linguistic diversity, and curating a final set of 188 questions across 4 buildings. Second, we characterize the benchmark's complexity and ambiguity, introducing a novel method to quantify its "lexical gap" and providing a four-stage diagnostic framework for analyzing how systems fail. Third, we benchmark zero-shot LLM-powered KGQA systems to establish baseline performance and analyze their failure modes. Our evaluation reveals that top-performing systems achieve a maximum F1 score of only 0.38. This result does not indicate a failure of these powerful systems, but rather underscores the unique challenges posed by our benchmark. It demonstrates a critical performance gap, showing that current methods successful on general KGs struggle with the specific lexical and structural nuances of the building domain. BuildingQA1 thus provides the benchmark dataset and foundational analysis needed to drive the development of novel, domain-aware methods required to unlock the use of semantic data in buildings.

Mulayim, Ozan Baris↗
DOE OSTI2025

HALLUFIELD: DETECTING LLM HALLUCINATIONS VIA FIELD-THEORETIC MODELING

A research-focused Python package that implements our hallucination-detection method for large language models(LLMs). The code computes stability signals from LLM predictions across various hyperparameters sweeps and combines free-energy/entropy–style metrics to flag likely hallucinations, with tunable thresholds for batch scoring. The repo includes evaluation scripts, config files, and example notebooks to reproduce benchmark results and ablations; it depends on standard open-source libraries (PyTorch, Hugging Face) and runs on CPU/GPU. The repository examples only use public models/datasets only.

Bhattarai, Manish [Los Alamos National Labs]↗