SEARCH · Search NASA
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.
This is a small set of python scripts and HTML that uses OpenAI API to control large language models (LLMs) working agentically to solve a posed question / problem. There are 3 agents and they work to get it "just right" by taking on various "roles" of friendly and adversarial critics. It repeats a number of times specified by the user, and then writes a report.
Topological Data Analysis for Adversarial Detection (LANL O4937) - Detects adversarial examples in vision-language models using persistent homology and two-sample testing. Combines TDA features from CLIP embeddings with statistical methods (ME, SCF, SAMMD, C2ST) for robust detection across ImageNet, CIFAR-10/100.
SAND2025-14754O Atlas-UI-3 is the third iteration of the LLM chat user interface called Atlas. The tool does not share code with previous versions. It supports chat with large language models (LLMs), connects to retrieval-augmented generation (RAG) servers, features a marketplace/store for model and content providers (MCP), and enables tool calling. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.
SAND2026-16981O Bibcheck is designed to extract bibliographies from research papers and perform metadata searches to identify errors. It assists authors in checking their bibliographies for metadata errors during the writing process and helps reviewers identify errors in bibliographies of papers under review. The software uses large language models (LLMs) to extract bibliography entries from PDF documents, classifies the type of bibliography entry, and verifies referenced works. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.
SAND2025-14316O TalkPipe Writing Assistant offers AI assistance, providing help on a point-by-point basis. Authors can start with their own ideas—whether bullet points, partial paragraphs, or phrases—and specify the document type, desired tone, audience, and any other relevant context. As they write, the assistant provides tailored suggestions for each paragraph. They can request high-level concepts, draft a paragraph, or proofread existing text. The large language model (LLM) considers both preceding and following paragraphs to ensure coherence and flow. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.
Multi-Token Reliability Estimation (MTRE) is a lightweight, white-box hallucination detector for vision-language models. Instead of using only the first output token, MTRE aggregates logits from the first ~10 tokens and feeds them to a small attention-based reliability head; per-token scores are combined via a sequential log-likelihood-ratio test with early-stopping, and an MTRE-t variant calibrates thresholds via cross-fitting. MTRE reports average gains of +9.4% Accuracy and +14.8% AUROC over common baselines across MAD-Bench, MM-SafetyBench, MathVista, and arithmetic/counting tasks, while adding ~4.3M params and ~1% inference overhead (~26 MB VRAM, ~0.94 ms per detection). Key limitation: requires access to early token logits and is evaluated on a handful of open-source 7B VLMs.
A modular Python framework for information extraction using large language models with support for multiple backends and optional verification workflows.
CVEvolve is an agentic AI system for autonomous algorithm discovery for scientific data processing. It creates workflows where large language model agents freely set up and configure development environments and evaluation harnesses, develop and improve data processing algorithms with designed exploration-exploitation balancing mechanisms, log history and findings in a structured database, and run holdout testing to ensure algorithm generalizability. CVEvolve offers a zero-code interface and does not require users to provide structured data and evaluation scripts.
MADA (Multi-Agent Design Assistant) is a Large Language Model (LLM) powered multi-agent framework that coordinates specialized agents for complex design workflows. The system was designed for HPC workflows with the following agents in mind: 1) A Job Management Agent (JMA) launches and manages ensemble simulations on HPC systems, 2) a Geometry Agent (GA) generates meshes, and 3) an Inverse Design Agent (IDA) proposes new designs informed by simulation outcomes. Our framework reduces cumbersome manual workflow setup, and enables automated design exploration at scale. However, the software also enables users to rapidly create new multi-agent systems. Simply define new agents in a configuration file, giving each their own set of tools (via MCP), and then chat and prompt your new multi-agent system. Is
The Artificial Intelligence Ontology (AIO) is a systematization of artificial intelligence (AI) concepts, methodologies, and their interrelations. Developed via manual curation, with the additional assistance of large language models (LLMs), AIO aims to address the rapidly evolving landscape of AI by providing a comprehensive framework that encompasses both technical and ethical aspects of AI technologies. The primary audience for AIO includes AI researchers, developers, and educators seeking standardized terminology and concepts within the AI domain. We use the term “branches” for classes, and their subclasses, in our ontology that are subclasses of owl:Thing. AIO contains eight branches: Bias, Layer, Machine Learning Task, Mathematical Function, Model, Network, Preprocessing, and Training Strategy, each designed to support the modular composition of AI methods and facilitate a deeper understanding of deep learning architectures and ethical considerations in AI. AIO uses the Ontology Development Kit (ODK) for its creation and maintenance, with its content being more easily updated through AI-driven curation support. This approach not only ensures the ontology's relevance amidst the fast-paced advancements in AI but also significantly enhances its utility for researchers, developers, and educators by simplifying the integration of new AI concepts and methodologies. The ontology's utility is demonstrated through the annotation of AI methods data in a catalog of AI research publications and the integration into the BioPortal ontology resource, highlighting its potential for cross-disciplinary research. The AIO ontology is open source and is available on GitHub ( https://w3id.org/aio/ ) and BioPortal ( https://bioportal.bioontology.org/ontologies/AIO ).
Proteins are the molecular machines of life with numerous applications in energy, health, and sustainability. However, engineering proteins with desired functions for practical applications remains slow, expensive, and specialist-dependent. Here we report a generally applicable platform for autonomous enzyme engineering that integrates machine learning and large language models with biofoundry automation to eliminate the need for human intervention, judgement, and domain expertise. Requiring only an input protein sequence and a quantifiable way to measure fitness, this automated platform can be applied to engineer a wide array of proteins. As a proof of concept, we engineer Arabidopsis thaliana halide methyltransferase (AtHMT) for a 90-foldimprovement in substrate preference and 16-fold improvement in ethyl-transferase activity, along with developing a Yersinia mollaretii phytase (YmPhytase) variant with 26-fold improvement in activity at neutral pH. This is accomplished in four rounds over 4 weeks, while requiring construction and characterization of fewer than 500 variants for each enzyme. This platform for autonomous experimentation paves the way for rapid advancements across diverse industries, from medicine and biotechnology to renewable energy and sustainable chemistry.
Scientific advances due to conceptual or technological innovations can be revealed by examining how research topics have evolved. But such topical evolution is difficult to uncover and quantify because of the large body of literature and the need for expert knowledge in a wide range of areas in a field. Using plant biology as an example, we used machine learning and language models to classify plant science citations into topics representing interconnected, evolving subfields. The changes in prevalence of topical records over the last 50 years reflect shifts in major research trends and recent radiation of new topics, as well as turnover of model species and vastly different plant science research trajectories among countries. Our approaches readily summarize the topical diversity and evolution of a scientific field with hundreds of thousands of relevant papers, and they can be applied broadly to other fields.
The utilization of large language models (LLMs) such as ChatGPT has seen a remarkable increase in various fields over the past few years. These models have demonstrated their versatility and capability in understanding and generating human-like text, making them invaluable tools in numerous applications. In this project, we explore the integration of a LLM into the Experimental Physics and Industrial Control System (EPICS). The primary focus of this integration is to employ the LLM for advanced image processing and spatial analysis on images obtained from the beamlines. By leveraging the capabilities of the LLM, we aim to enhance the accuracy and efficiency of image interpretation, enabling more precise data analysis and decision-making within the EPICS framework. This integration not only showcases the potential of LLMs in scientific and industrial applications but also sets the stage for future advancements in automated control systems.
Epidemiological datasets are essential for public health analysis and decision-making, yet they remain scarce and often difficult to compile due to inconsistent data formats, language barriers, and evolving political boundaries. Traditional methods of creating such datasets involve extensive manual effort and are prone to errors in accurate location extraction. To address these challenges, we propose utilizing large language models (LLMs) to automate the extraction and geotagging of epidemiological data from textual documents. Our approach significantly reduces the manual effort required, limiting human intervention to validating a subset of records against text snippets and verifying the geotagging reasoning, as opposed to reviewing multiple entire documents manually to extract, clean, and geotag. Additionally, the LLMs identify information often overlooked by human annotators, further enhancing the dataset’s completeness. Our findings demonstrate that LLMs can be effectively used to semi-automate the extraction and geotagging of epidemiological data, offering several key advantages: (1) comprehensive information extraction with minimal risk of missing critical details; (2) minimal human intervention; (3) higher-resolution data with more precise geotagging; and (4) significantly reduced resource demands compared to traditional methods.
Multi-bit watermarking has emerged as a promising solution for embedding imperceptible binary messages into Large Language Model (LLM)-generated text, enabling reliable attribution and tracing of malicious usage of LLMs. Despite recent progress, existing methods still face key limitations: some become computationally infeasible for large messages, while others suffer from a poor trade-off between text quality and decoding accuracy. Moreover, the decoding accuracy of existing methods drops significantly when the number of tokens in the generated text is limited, a condition that frequently arises in practical usage. To address these challenges, we propose XMark, a novel method for encoding and decoding binary messages in LLM-generated texts. The unique design of XMark’s encoder produces a less distorted logit distribution for watermarked token generation, preserving text quality, and also enables its tailored decoder to reliably recover the encoded message with limited tokens. Extensive experiments across diverse downstream tasks show that XMark significantly improves decoding accuracy while preserving the quality of watermarked text, outperforming prior methods. The code will be made publicly available upon acceptance.
Energy storage has a unique and pivotal role to play in the transition to a low-carbon economy because it can help the electric grid accommodate more renewable energy. However, a number of barriers currently impede the process of connecting energy storage systems to the distribution grid. The Toolkit and Guidance for the Interconnection of Energy Storage and Solar-Plus-Storage (the “BATRIES Toolkit”), which is the publication subject to this Final Technical / Scientific Report, provides vetted solutions to eight regulatory and technical barriers to the interconnection of standalone storage and solar-plus-storage systems (referred to as “energy storage”) to the distribution grid. These recommendations are based on over a year of research and analysis by utility and industry experts. The BATRIES Toolkit also includes model language that utilities and utility regulators can use to update state interconnection rules to reduce the costs and time to safely interconnect energy storage and solar-plus-storage systems. The solutions are nationally applicable and can be applied in diverse states and markets across the U.S.
The goals and objectives of the grant DE‐SC0020892 were to apply a new computing paradigm, MemComputing, to efficiently simulate properties of correlated quantum systems. The method has been applied to a wide set of problems ranging from quantum state tomography to finding the ground state of correlated systems. In all cases, substantial advantages compared to state-of-the-art approaches have been obtained. The project has also led to the suggestion of the transformer architecture (used nowadays in large-language models) as an efficient quantum state representation, and a better understanding of the role of memory in the generation of long-range order in neural networks. This grant has supported the work of a PhD student, inspired a new class on unconventional computing taught at the University of California, San Diego and has generated several peer-reviewed papers.