Search NASA⌕ Search

SEARCH · Search NASA

Results for “Structured Natural Language”

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
NASA NTRSDate not supplied

FRET Tutorial

In this tutorial, we present the FRET tool for writing, understanding, formalizing and analyzing requirements. In practice, requirements are typically written in natural language, which is ambiguous and consequently not amenable to formal analysis. Since formal, mathematical notations are unintuitive, requirements in FRET are entered in a restricted, natural language, called FRETish with precise unambiguous meaning. This tutorial explains how requirements can be captured in FRETish and subsequently formalized in temporal logics and in the synchronous data flow language Lustre. We show, through multiple examples, how FRET assists users in understanding FRETish requirements and clarifying subtle semantic issues through English and diagrammatic explanations as well as interactive simulation. FInally, this tutorial describes how FRET can be used to perform realizability checking for identifying conflicting requirements and the connection of FRET with (1) the CoCoSim automated analysis tool for the verification of Simulink and Stateflow models, and (2) the Copilot runtime monitoring tool for the analysis of C programs.

FRET↗
DOE OSTI2025

Chemical classification program synthesis using generative artificial intelligence

Accurately classifying chemical structures is essential for cheminformatics and bioinformatics, including tasks such as identifying bioactive compounds of interest, screening molecules for toxicity to humans, finding non-organic compounds with desirable material properties, or organizing large chemical libraries for drug discovery or environmental monitoring. However, manual classification is labor-intensive and difficult to scale to large chemical databases. Existing automated approaches either rely on manually constructed classification rules, or are deep learning methods that lack explainability. This work presents an approach that uses generative artificial intelligence to automatically write chemical classifier programs for classes in the Chemical Entities of Biological Interest (ChEBI) database. These programs can be used for efficient deterministic run-time classification of SMILES structures, with natural language explanations. The programs themselves constitute an explainable computable ontological model of chemical class nomenclature, which we call the ChEBI Chemical Class Program Ontology (C3PO). We validated our approach against the ChEBI database, and compared our results against deep learning models and a naive SMARTS pattern based classifier. C3PO outperforms the naive classifier, but does not reach the performance of state of the art deep learning methods. However, C3PO has a number of strengths that complement deep learning methods, including explainability and reduced data dependence. C3PO can be used alongside deep learning classifiers to provide an explanation of the classification, where both methods agree. The programs can be used as part of the ontology development process, and iteratively refined by expert human curators.

Artificial Intelligence↗
NASA NTRS1995

Automated database design from natural language input

Users and programmers of small systems typically do not have the skills needed to design a database schema from an English description of a problem. This paper describes a system that automatically designs databases for such small applications from English descriptions provided by end-users. Although the system has been motivated by the space applications at Kennedy Space Center, and portions of it have been designed with that idea in mind, it can be applied to different situations. The system consists of two major components: a natural language understander and a problem-solver. The paper describes briefly the knowledge representation structures constructed by the natural language understander, and, then, explains the problem-solver in detail.

Gomez, Fernando↗
NASA NTRS1989

Interset: A natural language interface for teleoperated robotic assembly of the EASE space structure

A teleoperated robot was used to assemble the Experimental Assembly of Structures in Extra-vehicular activity (EASE) space structure under neutral buoyancy conditions, simulating a telerobot performing structural assembly in the zero gravity of space. This previous work used a manually controlled teleoperator as a test bed for system performance evaluations. From these results several Artificial Intelligence options were proposed. One of these was further developed into a real time assembly planner. The interface for this system is effective in assembling EASE structures using windowed graphics and a set of networked menus. As the problem space becomes more complex and hence the set of control options increases, a natural language interface may prove to be beneficial to supplement the menu based control strategy. This strategy can be beneficial in situations such as: describing the local environment, maintaining a data base of task event histories, modifying a plan or a heuristic dynamically, summarizing a task in English, or operating in a novel situation.

Boorsma, Daniel K.↗
DOE OSTI2026

Agentic artificial intelligence for multistage physics experiments at a large-scale user facility particle accelerator

We present a language-model-driven agentic artificial intelligence (AI) system to autonomously execute multistage physics experiments on a production synchrotron light source. Implemented at the Advanced Light Source particle accelerator, the system translates natural language user prompts into structured execution plans that combine archive data retrieval, control-system channel resolution, automated script generation, controlled machine interaction, and analysis. In a representative machine physics task, we show that preparation time was reduced by 2 orders of magnitude relative to manual scripting even for a system expert, while operator-standard safety constraints were strictly upheld. Core architectural features, plan-first orchestration, bounded tool access, and dynamic capability selection, enable transparent, auditable execution with fully reproducible artifacts. These results establish a blueprint for the safe integration of agentic AI into accelerator experiments and demanding machine physics studies, as well as routine operations, with direct portability across accelerators worldwide and, more broadly, to other large-scale scientific infrastructures.

Accelerator/storage ring control systems↗
DOE OSTI2026

matsim-agents v1.0

matsim-agents is a multi-agent AI framework for atomistic materials simulation and discovery. It orchestrates large language models (LLMs), machine-learned interatomic potentials (MLIPs), and DFT codes into a single agentic loop running on laptops and DOE leadership-class supercomputers. MULTI-AGENT ORCHESTRATION A LangGraph state machine with three nodes: a Planner that converts a natural-language research objective into structured tasks; an Executor that dispatches atomistic tools and loops until the queue is empty; and an Analyst that summarizes results into a human-readable report. State is checkpointed after every step and human-in-the-loop gates can be inserted at any edge. HYPOTHESIS-DRIVEN DISCOVERY CHAT An interactive REPL (matsim-agents chat) that couples LLM dialogue with atomistic simulation. Chemical formulas are automatically detected in conversation turns and trigger a full crystal-phase exploration: structure generation → relaxation → stability scoring → result injection back into the conversation, creating a closed hypothesis-refinement loop. CRYSTAL PHASE ENUMERATION Given a composition, the phase explorer enumerates prototypes by stoichiometry: elemental (fcc/bcc/hcp/sc/diamond), binary 1:1 (rocksalt/CsCl/zincblende/ wurtzite/fluorite/rutile), ternary 1:1:3 (cubic perovskite), ternary 1:2:4 (perovskite + spinel), quaternary 1:1:2:6 (Fm-3m double perovskite). 2-D prototypes (graphene, h-BN, MoS2 2H/1T) and multilayer stacking are also supported via --include-2d and --num-layers. SUPERCELL GENERATION AND SITE DECORATION Auto-tiling to a minimum atom count (--min-atoms), explicit NxNxN tiling (--supercell), symmetry-distinct site decorations (--n-orderings), and isotropic lattice-scale sweeps (--lattice-scales) for volume bracketing. MLFF RELAXATION AND STABILITY SCORING HydraGNN (multi-headed GNN) drives structure relaxation via ASE with FIRE, BFGS, or BFGSLineSearch. Stability output: delta-E/atom ranking across phases and a max-residual-force dynamical-stability proxy. Other MLIPs (MACE, NequIP, Orb) can be plugged in through the same interface. DFT BACKENDS Quantum ESPRESSO pw.x and VASP 6.6 are first-class labellers. Both have validated GPU builds and SLURM/PBS launchers for three DOE platforms: Frontier (AMD MI250X, ROCm), Aurora (Intel PVC, oneAPI), Perlmutter (NVIDIA A100, CUDA). QE produces ~100 binaries (pw.x, ph.x, epw.x, ...). VASP supports scf, relax, vc-relax, and vc-relax-shape run types. ACTIVE-LEARNING LOOP matsim-agents al run CONFIG.yaml drives an iterative HydraGNN-DFT loop: MD generates candidates → ensemble/MC-dropout uncertainty selects the most informative → DFT labels them in parallel inside one allocation → dataset grows → HydraGNN retrains → repeat. DFT backend is a single YAML toggle (dft.backend: vasp | qe). LLM-generated seed structures are supported (no curated POSCAR library needed). Config uses ${VAR}, ${VAR:-default}, ${VAR:?msg} shell-style substitution for cross-user/cross-site portability. LLM BACKENDS Ollama (local, default), vLLM (HPC multi-GPU serving), OpenAI, Anthropic, HuggingFace Transformers+Accelerate. Selected at runtime via flag or env var with no code changes. HPC PORTABILITY Same Python entry points run on Frontier (ROCm 7.2), Aurora (oneAPI), and Perlmutter (CUDA 12). DFT and ML stacks are never co-loaded in the same shell; they couple through the scheduler and filesystem. Advanced multi-node launchers (serve, discovery-chat, single-relaxation, active-learning, QE warm-start) are provided for all three platforms. CODABENCH COMPETITION BUNDLE A self-contained benchmark: 159 atomistic test structures across 11 material classes, 5 tasks (formation energy, forces, ML relaxation, AI-DFT relaxation, phase stability ranking), public/private leaderboard split (30/70), and four ready-to-run baselines: MACE-MP-0, HydraGNN, UMA, AllScAIP.

Lupo Pasini, Massimiliano [Oak Ridge National Labo↗
DOE OSTI2026

Knowledge Graph of RB-Tnseq Data from Fitness Browser (KP-DP1)

Motivation: Predicting microbial gene fitness across environmental conditions remains a central challenge for predictive phenomics and autonomous experimentation. Fitness assays generate large volumes of genotype–phenotype measurements difficult to integrate with experimental metadata and biological function in a form that supports mechanistic reasoning. Knowledge graphs offer a semantic framework for unifying modalities and enabling context-aware inference. Results: We build GIMME (Graph Inference for Microbial Metabolism Exploration), a semantically grounded knowledge graph that unifies gene fitness measurements spanning 10 Pseudomonas species with experimental metadata and biological context. Media are decomposed into chemical components and experiments carry structured links to natural-language descriptions. The resulting graph supports two inference modes: (1) symbolic graph traversal to surface candidate gene–environment and gene–chemical associations, and (2) learned inference using heterogeneous graph neural networks that propagate information across neighborhoods. We formulate link regression over (gene, media, experiment) triplets, combining learned gene embeddings with pretrained LLM sourced text embeddings of node descriptions to predict gene fitness. We then augment a baseline MLP with an auxiliary message-passing encoder (GraphSAGE/GAT) that propagates information over gene–protein–function and media–chemical subgraphs, and fuse the two pathways with a gated residual connection. This approach produces strong agreement with held-out fitness measurements (GraphSAGE Pearson r 0.74) while also highlighting inference challenges in extreme-fitness regimes. We aggregate GAT edge-attention weights by relation type and layer to estimate which biological and environmental relations most influence fitness predictions. Conclusion: This work explores using knowledge graphs as “context graphs” for microbial phenotype prediction. They provide a rich substrate which enables explainable retrieval of supporting evidence, and provides a natural bridge to autonomous workflows that prioritize the next experiment.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

Hybrid Quantum–Classical Graph Transformers for Efficient Sentiment Analysis

Quantum Machine Learning (QML) offers a promising paradigm that leverages quantum computing principles to develop efficient and expressive models for learning from complex and structured data. Recent advances in natural language processing (NLP) and artificial intelligence (AI) have demonstrated capabilities in understanding, generating, and reasoning over linguistic and multimodal information. In this work, we present the Quantum Graph Transformer (QGT), a hybrid quantum–classical architecture that extends graph transformer capabilities through quantum self-attention. The QGT models variable-length sentences as token graphs, where both the embedding encoding and the self-attention mechanisms are implemented using parameterized quantum circuits (PQCs), enabling efficient contextual learning with significantly fewer trainable parameters. We train QGT using both fully connected and 𝑘 -nearest-neighbor graph structures and evaluate it on five benchmark sentiment-classification datasets. Experimental results show that QGT consistently achieves higher or comparable accuracy to existing quantum NLP models and outperforms a Classical Graph Transformer (CGT) baseline with identical architecture, achieving 29.4 × fewer parameters while requiring 3–5 × fewer samples to reach comparable performance. These findings highlight the potential of graph-based quantum models as scalable and data-efficient architectures for natural language understanding.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
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↗
NASA NTRS2011

Sky Event Reporting Metadata (VOEvent) Version 2.0

VOEvent [20] defines the content and meaning of a standard information packet for representing, transmitting, publishing and archiving information about a transient celestial event, with the implication that timely follow-up is of interest. The objective is to motivate the observation of targets-of-opportunity, to drive robotic telescopes, to trigger archive searches, and to alert the community. VOEvent is focused on the reporting of photon events, but events mediated by disparate phenomena such as neutrinos, gravitational waves, and solar or atmospheric particle bursts may also be reported. Structured data is used, rather than natural language, so that automated systems can effectively interpret VOEvent packets. Each packet may contain zero or more of the "who, what, where, when & how" of a detected event, but in addition, may contain a hypothesis (a "why") regarding the nature of the underlying physical cause of the event.

Seaman, Rob↗
DOE OSTI2026

Agentic framework for programmatic crystal structure generation using a fine-tuned worker–supervisor large language model

Platinum group metals (PGMs) underpin many catalytic technologies but face severe supply constraints, motivating the search for alternative materials and computational methods to accelerate discovery. While atomistic simulation tools such as Pymatgen and ASE have streamlined structure manipulation, they require detailed inputs, limiting accessibility for experimentalists and slowing early-stage exploration. Here, in this study, we present an AI-driven agentic framework that orchestrates worker–supervisor large language models (LLMs). The worker translates natural-language prompts of varying abstraction into valid crystallographic structures using a compact LLM fine-tuned with low-rank adaptation on a curated text–code–CIF dataset, emphasizing energy-efficient training. Benchmarking against the baseline CodeGen-350M-mono model shows that fine-tuning reduces hallucination rates from 100% to as low as 5% and improves structural match accuracy to up to 82% for fully specified inputs. Accuracy declines with decreasing prompt detail but remains nontrivial even when only stoichiometry and space group are provided, underscoring the LLM’s capacity for crystallographic inference. The supervisor Claude LLM evaluates the outputs and triggers iterative refinement through the worker’s built-in structure manipulation capabilities (e.g., supercell scaling, strain, vacancy, and substitution operations). We further demonstrate use cases for technologically relevant catalysts, including IrO 2 , pyrochlore Pb 2 Ir 2 O 7 , Ni 2 FeO 4 , and Ni 3 Mo, where the framework generates physically consistent structures that can be refined via geometry optimization. This work introduces a low-energy, language-driven pathway for integrating human and machine intelligence in materials design, paving the way for AI-assisted synthesis planning and high-throughput screening of complex oxides.

AI agent↗
DOE OSTI2026

Hierarchical Multi-agent Large Language Model Reasoning for Autonomous Heterogeneous Catalyst Discovery

Artificial intelligence is reshaping scientific exploration, but most methods automate procedural tasks without engaging in scientific reasoning, limiting autonomy in discovery. We demonstrate that hierarchical agentic large language model reasoning can efficiently drive simulation and scientific exploration. Across two chemical applications, CO adsorption on Cu surface transition metal adatoms and on M–N–C catalysts, reasoning-guided exploration reduces required atomistic simulations by up to 90% relative to heuristic or random selection. Comparisons across single-agent, multi-agent, and stochastic baselines show that hierarchical strategies yield more coherent and information-efficient search trajectories. Reasoning traces reveal chemically grounded decisions that cannot be explained by semantic bias or stochastic sampling. We realize these agentic reasoning strategies in Materials Agents for Simulation and Theory in Electronic-structure Reasoning (MASTER), a multimodal system that translates natural language into density functional theory workflows. Altogether, multi-agent collaboration accelerates heterogeneous catalyst discovery and marks a step toward more autonomous, reasoning-guided scientific exploration.

30 DIRECT ENERGY CONVERSION↗
NASA NTRS1985

Phase structure rewrite systems in information retrieval

Operational level automatic indexing requires an efficient means of normalizing natural language phrases. Subject switching requires an efficient means of translating one set of authorized terms to another. A phrase structure rewrite system called a Lexical Dictionary is explained that performs these functions. Background, operational use, other applications and ongoing research are explained.

Klingbiel, P. H.↗
NASA NTRS2009

A Verification-Driven Approach to Traceability and Documentation for Auto-Generated Mathematical Software

Model-based development and automated code generation are increasingly used for production code in safety-critical applications, but since code generators are typically not qualified, the generated code must still be fully tested, reviewed, and certified. This is particularly arduous for mathematical and control engineering software which requires reviewers to trace subtle details of textbook formulas and algorithms to the code, and to match requirements (e.g., physical units or coordinate frames) not represented explicitly in models or code. Both tasks are complicated by the often opaque nature of auto-generated code. We address these problems by developing a verification-driven approach to traceability and documentation. We apply the AUTOCERT verification system to identify and then verify mathematical concepts in the code, based on a mathematical domain theory, and then use these verified traceability links between concepts, code, and verification conditions to construct a natural language report that provides a high-level structured argument explaining why and how the code uses the assumptions and complies with the requirements. We have applied our approach to generate review documents for several sub-systems of NASA s Project Constellation.

Denney, Ewen W.↗
NASA NTRSDate not supplied

Authoring, Analyzing, and Monitoring Requirements for a Lift-Plus-Cruise Aircraft

Requirements specification and analysis is widely applied to ensure the correctness of industrial systems in safety critical domains. Requirements are often initially written in natural language, which is highly ambiguous, and as a second step transformed into a language with rigorous semantics for formal analysis. In this paper, we report on our experience in requirements creation and analysis, as well as run-time monitor generation using the Formal Requirement Elicitation Tool (FRET), on an industrial case study for a Lift-Plus-Cruise concept aircraft. We study the creation of requirements directly in the structured language of FRET without a prior definition of the same requirements in natural language. We focus on requirements describing state machines and discuss the challenges that we faced, in terms of creating requirements and generating monitors. We demonstrate how realizability, i.e., checking whether a requirements specification can be implemented, is crucial for understanding temporal interdependencies among requirements. Our study is the first complete attempt at using FRET to create industrial, realizable requirements and generate run-time monitors. Insight from lessons learned was materialized into new features in the FRET and JKind analysis frameworks.

Requirements engineering↗
NASA NTRSDate not supplied

Authoring, Analyzing, and Monitoring Requirements for a Lift-Plus-Cruise Aircraft

Requirements specification and analysis is widely applied to ensure the correctness of industrial systems in safety critical domains. Requirements are often initially written in natural language, which is highly ambiguous, and as a second step transformed into a language with rigorous semantics for formal analysis. [Question/problem] In this paper, we report on our experience in requirements creation and analysis, as well as run-time monitor generation using the Formal Requirement Elicitation Tool (FRET), on an industrial case study for a Lift-Plus-Cruise concept aircraft. [Principal ideas/results] We study the creation of requirements directly in the structured language of FRET without a prior definition of the same requirements in natural language. We focus on requirements describing state machines and discuss the challenges that we faced, in terms of creating requirements and generating monitors. We demonstrate how realizability, i.e., checking whether a requirements specification can be implemented, is crucial for understanding temporal interdependencies among requirements. [Contribution] Our study is the first complete attempt at using FRET to create industrial, realizable requirements and generate run-time monitors. Insight from lessons learned was materialized into new features in the FRET and JKind analysis frameworks.

Requirements engineering↗
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↗
NASA NTRS2005

Semantic Analysis of Email Using Domain Ontologies and WordNet

The problem of capturing and accessing knowledge in paper form has been supplanted by a problem of providing structure to vast amounts of electronic information. Systems that can construct semantic links for natural language documents like email messages automatically will be a crucial element of semantic email tools. We have designed an information extraction process that can leverage the knowledge already contained in an existing semantic web, recognizing references in email to existing nodes in a network of ontology instances by using linguistic knowledge and knowledge of the structure of the semantic web. We developed a heuristic score that uses several forms of evidence to detect references in email to existing nodes in the Semanticorganizer repository's network. While these scores cannot directly support automated probabilistic inference, they can be used to rank nodes by relevance and link those deemed most relevant to email messages.

Berrios, Daniel C.↗