Search NASA⌕ Search

SEARCH · Search NASA

Results for “RAG”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Sparsity of the electron repulsion integral tensor using different localized virtual orbital representations in local second-order Møller–Plesset theory

Utilizing localized orbitals, local correlation theory can reduce the unphysically high system-size scaling of post-Hartree–Fock (post-HF) methods to linear scaling in insulating molecules. The sparsity of the four-index electron repulsion integral (ERI) tensor is central to achieving this reduction. For second-order Møller–Plesset theory (MP2), one of the simplest post-HF methods, only the (ia|jb) ERIs are needed, coupling occupied orbitals i, j and virtuals a, b. In this paper, we compare the numerical sparsity (called the “ragged list”) and two other approaches revealing the low-rank sparsity of the ERI. The ragged list requires only one set of (localized) virtual orbitals, and we find that the orthogonal valence virtual-hard virtual set of virtuals originally proposed by Subotnik et al. gives the sparsest ERI tensor. To further compress the ERI tensor, the pair natural orbital (PNO) type representation uses different sets of virtual orbitals for different occupied orbital pairs, while the occupied-specific virtual (OSV) approach uses different virtuals for each occupied orbital. Here, our results indicate that while the low-rank PNO representation achieves significant rank reduction, it also requires more memory than the ragged list. The OSV approach requires similar memory to that of the ragged list, but it involves greater algorithmic complexity. An approximation (called the “fixed sparsity pattern”) for solving the local MP2 equations using the numerically sparse ERI tensor is proposed and tested to be sufficiently accurate and to have highly controllable error. A low-scaling local MP2 algorithm based on the ragged list and the fixed sparsity pattern is therefore promising.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Automating and Evaluating Large Language Models for Accurate Text Summarization Under Zero-Shot Conditions

Automated text summarization (ATS) is crucial for collecting specialized, domain-specific information. Zero-shot learning (ZSL) allows large language models (LLMs) to respond to prompts on information not included in their training, playing a vital role in this process. This study evaluates LLMs' effectiveness in generating accurate summaries under ZSL conditions and explores using retrieval augmented generation (RAG) and prompt engineering to enhance factual accuracy and understanding. We combined LLMs with summarization modeling, prompt engineering, and RAG, evaluating the summaries using the METEOR metric and keyword frequencies through word clouds. Results indicate that LLMs are generally well-suited for ATS tasks, demonstrating an ability to handle specialized information under ZSL conditions with RAG. However, web scraping limitations hinder a single generalized retrieval mechanism. While LLMs show promise for ATS under ZSL conditions with RAG, challenges like goal misgeneralization and web scraping limitations need addressing. Future research should focus on solutions to these issues.

Priebe Mendes Rocha, Maria Eduarda [ORNL]↗
DOE OSTI2023

First bromine doped cryogenic implosion at the National Ignition Facility

We report on the first experiment dedicated to the study of nuclear reactions on dopants in a cryogenic capsule at the National Ignition Facility (NIF). This was accomplished using bromine doping in the inner layers of the CH ablator of a capsule identical to that used in the NIF shot N140520. The capsule was doped with 3 × 1016 bromine atoms. The doped capsule shot, N170730, resulted in a DT yield that was 2.6 times lower than the undoped equivalent. The Radiochemical Analysis of Gaseous Samples (RAGS) system was used to collect and detect 79Kr atoms resulting from energetic deuteron and proton ion reactions on 79Br. RAGS was also used to detect 13N produced dominantly by knock-on deuteron reactions on the 12C in the ablator. High-energy reaction-in-flight neutrons were detected via the 209Bi(n,4n)206Bi reaction, using bismuth activation foils located 50 cm outside of the target capsule. The robustness of the RAGS signals suggests that the use of nuclear reactions on dopants as diagnostics is quite feasible.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

Retrieval Augmented Generation for Robust Cyber Defense

In cybersecurity, the ability to efficiently analyze and respond to vulnerabilities, weaknesses, attack patterns, and threat tactics is critical for effective defense strategies. With the increasing complexity and volume of cybersecurity data, traditional methods of querying and retrieving information are often inadequate. To address this challenge, we implemented Retrieval-Augmented Generation (RAG) systems—CyRAG and GraphCyRAG—that integrate large language models (LLMs) with both structured data from relational databases and knowledge graphs such as Neo4j. CyRAG is designed to handle structured data, focusing on CVE (Common Vulnerabilities and Exposures) and CWE (Common Weakness Enumeration) entities to generate accurate and context-rich responses. In contrast, GraphCyRAG leverages Neo4j knowledge graphs to retrieve interconnected information from CVE, CWE, CAPEC (Common Attack Pattern Enumeration and Classification), and ATT&CK (Adversarial Tactics, Techniques, and Common Knowledge) datasets. By utilizing Neo4j’s graph-based framework, GraphCyRAG enables deeper traversal of relationships between vulnerabilities and attack patterns, providing cybersecurity analysts with more comprehensive insights into potential attack vectors and mitigation strategies. Our preliminary results demonstrate that integrating knowledge graphs with RAG significantly enhances both the accuracy and depth of threat analysis, allowing for the retrieval of dynamic, real-time data and the generation of contextually aware responses. This approach helps analysts uncover hidden relationships between cyber entities, predict exploit paths, and prioritize mitigation efforts effectively. The integration of RAG with cybersecurity knowledge graphs represents a significant advancement in cybersecurity threat intelligence, enabling more informed decision-making and stronger defense strategies.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Evaluation of the Self Retrieval Augmented Generation Technique on Common Security Advisory Framework Data

This small experimental report evaluates a variation of Retrieval Augmented Generation (RAG), called Self-RAG. This method uses a generative language model that incorporates retrieved facts into its generation and is explicitly trained to be able to determine whether retrieved information is enough to answer the input query, with a user-defined threshold for confidence. We performed an experiment using data from the publicly available CISA Common Security Advisory Framework (CSAF) repository (https://github.com/cisagov/CSAF) as the database of facts to be used in retrieval. Qualitative results from the experiment demonstrate that the Self-RAG method has some ability to provide reasonable answers to queries that are in the dataset and will often ignore irrelevant information when asked outside of domain questions (e.g., general facts). In settings with deliberately confusing questions (the question is within domain, but asks about a fabricated advisory), it was able to refuse 40% of the time without further adjustments to the original framework. While this performance is not sufficient for current practical use, further improvements to data formatting, disambiguating results, and leveraging threshold values could improve performance significantly. However, evaluating this will require more extensive evaluations on larger datasets and potentially better models.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Large Language Model for Validation, Optical Calibration, and Learning (VOCAL) Distributed Temperature Sensing Interface

Distributed temperature sensing (DTS) using fiber optic sensors (FOS) offers a promising method for temperature measurements in advanced reactors, such as sodium fast reactors and molten salt cooled reactors. To support the calibration and validation of DTS measurements, Argonne National Laboratory developed the Validation, Optical Calibration, and Learning (VOCAL) software package. This report describes the integration of a local large language model (LLM) with a retrieval-augmented generation (RAG) system into the VOCAL interface to serve as an interactive user assistant. The LLM framework enhances the VOCAL platform’s accessibility to users by explaining interface components, clarifying inputs and outputs, and answering user queries dynamically in real-time. The accuracy of the LLM assistant performance was evaluated with 20 queries regarding the interface and its parameters using experimental data from the Thermal Hydraulic Experimental Test Article (THETA) facility. Results demonstrate that the LLM achieved a 95% accuracy rate, with a BERTScore of 0.8816 and SBERT value of 0.7417. Furthermore, validation of the RAG system within the LLM framework showed optimal accuracy with k-values between 1 and 2 using the k-refinement convergence test. The prompt perturbation analysis demonstrated good initial consistency for the RAG system, exhibiting the highest accuracy under punctuation variations and the greatest sensitivity under query reordering. Notably, the model’s errors were limited to data retrieval failures rather than factual hallucinations, reinforcing its baseline reliability. The integration of LLM provides a highly accurate, userfriendly enhancement to the VOCAL platform without disrupting its core computational capabilities for FOS calibration and validation.

Hong, Evan↗
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↗
DOE OSTI2025

Quantifying fission yields at the National Ignition Facility using depleted uranium foil experiments

There are programs for high-Z shell experiments at the National Ignition Facility (NIF). For shells made of actinide material, a quantitative fission diagnostic is needed in order to determine how much fission took place and whether the fission was sufficient to produce a non-negligible heat source in the burning capsule. Here, we present a viable coupled experimental and theoretical technique for making quantitative fission measurements possible. The proposed scheme involves using a well-characterized set of depleted uranium foils outside an NIF capsule to verify the conversion of xenon and krypton fission fragments collected at the Radiochemical Analysis of Gaseous Samples (RAGS) facility into total fission yield. We present the calculations needed for this conversion, including the decays in and out of fission fragment chains during the RAGS pump-down of the NIF chamber.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
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 OSTI2015

An anti-silencer– and SATB1-dependent chromatin hub regulates Rag1 and Rag2 gene expression during thymocyte development

Rag1 and Rag2 gene expression in CD4 + CD8 + double-positive (DP) thymocytes depends on the activity of a distant anti-silencer element (ASE) that counteracts the activity of an intergenic silencer. However, the mechanistic basis for ASE activity is unknown. Here, we show that the ASE physically interacts with the distant Rag1 and Rag2 gene promoters in DP thymocytes, bringing the two promoters together to form an active chromatin hub. Moreover, we show that the ASE functions as a classical enhancer that can potently activate these promoters in the absence of the silencer or other locus elements. In thymocytes lacking the chromatin organizer SATB1, we identified a partial defect in Tcra gene rearrangement that was associated with reduced expression of Rag1 and Rag2 at the DP stage. SATB1 binds to the ASE and Rag promoters, facilitating inclusion of Rag2 in the chromatin hub and the loading of RNA polymerase II to both the Rag1 and Rag2 promoters. Our results provide a novel framework for understanding ASE function and demonstrate a novel role for SATB1 as a regulator of Rag locus organization and gene expression in DP thymocytes.

histone H3 lysine 27 trimethylation↗
DOE OSTI2023

Formation of asymmetric arms in barred galaxies

We establish a dynamical mechanism to explain the origin of the asymmetry between the arms observed in some barred disc galaxies, where one of the two arms emanating from the bar ends is very well defined, while the second one displays a ragged structure, extending between its ridge and the bar. To this purpose, we study the invariant manifolds associated with the Lyapunov periodic orbits around the unstable equilibrium points at the ends of the bar. Matter from the galaxy centre is transported along these manifolds to the periphery, forming this way the spiral arms that emanate from the bar ends. If the mass distribution in the galaxy centre is not homogeneous, because of an asymmetric bar with one side stronger than the other, or because of a non-centred bulge, the dynamics about the two unstable Lagrange points at the ends of the bar will not be symmetric as well. One of their invariant manifolds becomes more extended than the other, enclosing a smaller section and the escaping orbits on it are fewer and dispersed in a wider region. The result is a weaker arm and more ragged than the one at the other end of the bar.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

brag

Basic RAG-A python application for retrieval augmented generation (RAG).

Lui, Arthur↗
DOE OSTI2025

ARCS: Agentic Retrieval-Augmented Code Synthesis with Iterative Refinement

Agentic Retrieval-Augmented Code Synthesis with Iterative RefinementIn supercomputing, efficient and optimized code generation is essential to leverage high-performance systems effectively. We have developed Agentic Retrieval-Augmented Code Synthesis (ARCS), an advanced framework for accurate, robust, and efficient code generation, completion, and translation. ARCS integrates Retrieval-Augmented Generation (RAG) with Chain-of-Thought (CoT) reasoning to systematically break down and iteratively refine complex programming tasks. An agent-based RAG mechanism retrieves relevant code snippets, while real-time execution feedback drives the synthesis of candidate solutions. This process is formalized as a state-action search tree optimization, balancing code correctness with editing efficiency. Evaluations on the Geeks4Geeks and HumanEval benchmarks demonstrate that ARCS significantly outperforms traditional prompting methods in translation and generation quality. By enabling scalable and precise code synthesis, ARCS offers transformative potential for automating and optimizing code development in supercomputing applications, enhancing computational resource utilization

Bhattarai, Manish [Los Alamos National Labs]↗
DOE OSTI2024

Towards Unlocking Insights from Logbooks Using AI

Electronic logbooks contain valuable information about activities and events concerning their associated particle accelerator facilities. However, the highly technical nature of logbook entries can hinder their usability and automation. As natural language processing (NLP) continues advancing, it offers opportunities to address various challenges that logbooks present. This work explores jointly testing a tailored Retrieval Augmented Generation (RAG) model for enhancing the usability of particle accelerator logbooks at institutes like DESY, BESSY, Fermilab, BNL, SLAC, LBNL and CERN. The RAG model uses a corpus built on logbook contributions and aims to unlock insights from these logbooks by leveraging retrieval over facility datasets, including discussion about potential multimodal sources. Our goals are to increase the FAIR-ness (findability, accessibility, interoperability, and reusability) of logbooks by exploiting their information content to streamline everyday use, to enable macro-analysis for root cause analysis, and to facilitate problem-solving automation.

43 PARTICLE ACCELERATORS↗
NASA NTRSDate not supplied

Retrieval-Augmented Generation and LLM Agents for Biomimicry Design Solutions

We present BIDARA, a Bio-Inspired Design And Research Assistant, to address the complexity of biomimicry – the practice of designing modern-day engineering solutions inspired by biological phenomena. Large Language Models (LLMs) have been shown to act as sufficient general purpose task solvers, but they often hallucinate and fail in regimes that require domain-specific and up-to-date knowledge. We integrate Retrieval-Augmented Generation (RAG) and Reasoning-and-Action agents to aid LLMs in avoiding hallucination and utilizing updated knowledge during generation of biomimetic design solutions. We find that incorporating RAG increases the feasibility of the design solutions in both prompting and agent settings, and we use these findings to guide our ongoing work. To the extent of our knowledge, this is the first work that integrates and evaluates Retrieval-Augmented Generation within LLM-generated biomimetic design solutions.

biomimicry↗
NASA NTRSDate not supplied

Retrieval-Augmented Generation and LLM Agents for Biomimicry Design Solutions

We present BIDARA, a Bio-Inspired Design And Research Assistant, to address the complexity of biomimicry – the practice of designing modern-day engineering solutions inspired by biological phenomena. Large Language Models (LLMs) have been shown to act as sufficient general purpose task solvers, but they often hallucinate and fail in regimes that require domain-specific and up-to-date knowledge. We integrate Retrieval-Augmented Generation (RAG) and Reasoning-and-Action agents to aid LLMs in avoiding hallucination and utilizing updated knowledge during generation of biomimetic design solutions. We find that incorporating RAG increases the feasibility of the design solutions in both prompting and agent settings, and we use these findings to guide our ongoing work. To the extent of our knowledge, this is the first work that integrates and evaluates Retrieval-Augmented Generation within LLM-generated biomimetic design solutions.

biomimicry↗
DOE OSTI2024

Towards Unlocking Insights from Logbooks Using AI

Electronic logbooks contain valuable information about activities and events concerning their associated particle accelerator facilities. However, the highly technical nature of logbook entries can hinder their usability and automation. As natural language processing (NLP) continues advancing, it offers opportunities to address various challenges that logbooks present. This work explores jointly testing a tailored Retrieval Augmented Generation (RAG) model for enhancing the usability of particle accelerator logbooks at institutes like DESY, BESSY, Fermilab, BNL, SLAC, LBNL, and CERN. The RAG model uses a corpus built on logbook contributions and aims to unlock insights from these logbooks by leveraging retrieval over facility datasets, including discussion about potential multimodal sources. Our goals are to increase the FAIR-ness (findability, accessibility, interoperability, and reusability) of logbooks by exploiting their information content to streamline everyday use, enable macro-analysis for root cause analysis, and facilitate problem-solving automation.

43 PARTICLE ACCELERATORS↗
DOE OSTI2018

The TORC1 signaling pathway regulates respiration-induced mitophagy in yeast

Mitophagy is an evolutionarily conserved autophagy process that selectively degrades mitochondria. This catabolic event is considered to be a mitochondrial quality control system crucial for cell homeostasis, however, mechanisms regulating mitophagy remain largely unknown. Here we show that the TORC1 (target of rapamycin complex 1) signaling pathway regulates mitophagy in budding yeast via SEACIT (Seh1-associated complex inhibiting TORC1) consisting of Iml1, Npr2, and Npr3. Cells lacking SEACIT displayed significant reductions in mitophagy during prolonged respiratory growth, while the other selective autophagy processes are less affected. Under the same conditions, mitophagy defects were strikingly rescued in the SEACIT mutants (1) treated with rapamycin, a specific TOR kinase inhibitor, (2) lacking Gtr1, a TORC1-stimulating Rag family GTPase downstream of SEACIT, and (3) devoid of Pib2, a phosphatidylinositol 3-phosphate-binding TORC1 activator. Notably, loss of Npr2 exacerbated mitophagy defects in cells lacking Atg13, a TORC1 effector crucial for activation of autophagy-related processes, suggesting additional mitophagy-specific regulator(s) downstream of TORC1. Finally, we found that npr2-null cells failed to stabilize the interaction of Atg32 with Atg11, a scaffold protein essential for mitophagy. Collectively, our data implicate SEACIT-mediated inactivation of TORC1 signaling as a critical step to promote respiration-induced mitophagy.

60 APPLIED LIFE SCIENCES↗