Search NASA⌕ Search

SEARCH · Search NASA

Results for “Agentic AI”

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 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Using AI to Reproduce Neutrino Cross Section Analysis - Prototyping the Neutrino Discovery Platform

The Neutrino Discovery Platform (NDP) aims to accelerate DUNE-era science by making the neutrino program's existing datasets analyzable through fast, reproducible, and auditable workflows. We report a working version of two of its layers, data curation and agentic orchestration, built and tested end to end on MINERvA open data. The guiding lesson throughout is that a cross section is a measurement, and not just a plotted shape, only if it carries a defensible systematic-uncertainty budget, a trustworthy unfolding, and a reproducible record. Using a single medium-energy playlist pair from the MINERvA open-data release (about $2.05\times10^{17}$ protons on target of data), we first reproduced the shapes of two published charged-current inclusive $\nu_\mu$ measurements through a complete extraction ladder: selection, background subtraction, D'Agostini unfolding, efficiency correction, and flux normalization. These shape-level reproductions ran and tracked the published results, but they lacked the systematic-uncertainty machinery that defines a MINERvA cross section. To supply it, we vendored and built the MINERvA Analysis Toolkit and developed a many-universe systematic-uncertainty tool that produces a portable covariance artifact, a parallel event-loop runner, and a per-run auditability harness. Validated against a published covariance release, the toolchain reproduces the released statistical, flux, and muon-energy-scale terms and shows that they account for roughly 63\% of the total variance, with the remainder unreleased. Using this same infrastructure, we then performed a measurement of our own design, the hadronic recoil-energy distribution of low-energy ($E_\nu<2.5$~GeV) charged-current inclusive events, and found data/simulation shape agreement of $\chi^2/\mathrm{ndf}=1.26$. Together these results show that the platform supports original physics and not only reproductions.

Breaux, Auto [Tulane U. (main)]↗
NASA NTRS2005

Apex Reference Manual 3.0 Beta

Apex is a toolkit for constructing software that behaves intelligently and responsively in demanding task environments. Reflecting its origin at NASA where Apex continues to be developed, current applications include: a) Providing autonomous mission management and tactical control capabilities for unmanned aerial vehicles including an autonomous surveillance helicopter and a simulation prototype of an unmanned fixed-wing aircraft to be used for wildfire mapping; b) Simulating human air traffic controllers, pilots and astronauts to help predict how people might respond to changes in equipment or procedures; and c) Predicting the precise duration and sequence of routine human behaviors based on a human-computer interaction engineering technique called CPM-GOMS. Among Apex s components are a set of implemented reasoning services, such as those for reactive planning and temporal pattern recognition; a software architecture that embeds and integrates these services and allows additional reasoning elements to be added as extensions; a formal language for specifying agent knowledge; a simulation environment to facilitate prototyping and analysis; and Sherpa, a set of tools for visualizing autonomy logic and runtime behavior. In combination, these are meant to provide a flexible and usable framework for creating, testing, and deploying intelligent agent software. Overall, our goal in developing Apex is to lower economic barriers to developing intelligent software agents. New ideas about how to extend or modify the system are evaluated in terms of their impact in reducing the time, expertise, and inventiveness required to build and maintain applications. For example, potential enhancements to the AI reasoning capabilities in the system are reviewed not only for usefulness and distinctiveness, but also for their impact on the readability and general usability of Apex s behavior representation language (PDL) and on the transparency of resulting behavior. A second central part of our approach is to iteratively refine Apex based on lessons learned from as diverse a set of applications as possible. Many applications have been developed by users outside the core development team including engineers, researchers, and students. Usability is thus a central concern for every aspect of Apex visible to a user, including PDL, Sherpa, the Apex installation process, APIs, and user documentation. Apex users vary in their areas of expertise and in their familiarity with autonomy technology. Focusing on usability, a development philosophy summarized by the project motto "Usable Autonomy," has been important part of enabling diverse users to employ Apex successfully and to provide feedback needed to guide iterative, user-centered refinement.

Freed, Michael A.↗
NASA NTRS1991

SPIKE: AI scheduling techniques for Hubble Space Telescope

AI (Artificial Intelligence) scheduling techniques for HST are presented in the form of the viewgraphs. The following subject areas are covered: domain; HST constraint timescales; HTS scheduling; SPIKE overview; SPIKE architecture; constraint representation and reasoning; use of suitability functions by scheduling agent; SPIKE screen example; advantages of suitability function framework; limiting search and constraint propagation; scheduling search; stochastic search; repair methods; implementation; and status.

Johnston, Mark D.↗
DOE OSTI2024

Federated Deep Reinforcement Learning for Decentralized VVO of BTM DERs

The future of grid control requires a hybrid approach combining centralized and decentralized methods to fully utilize the potential of smart edge devices with artificial intelligence (AI) capabilities. This paper aims to develop and evaluate a federated deep reinforcement learning (FDRL) framework for decentralized adaptive volt-var optimization (VVO) of behind-the-meter (BTM) distributed energy resources (DERs). First, this paper models a single deep reinforcement learning (DRL) agent using the Markov Decision Process (MDP) framework for decentralized adaptive VVO of BTM DERs. Two DRL algorithms, soft actor-critic (SAC) and twin-delayed deep deterministic policy gradient (TD3), are compared for their effectiveness in optimizing VVO. Results show that TD3 outperforms SAC, achieving a 71.3% improvement in mean reward. Finally, the DRL agent is deployed within the FDRL framework, using the Flower platform, to enhance learning, provide adaptive control, and ensure data privacy for BTM DERs.

Ravi, Abhijith↗
DOE OSTI2026

SetGo: Metadata Readiness for Scientific AI Datasets

Scientific datasets intended for AI use require both computational readiness for model training and metadata readiness for discovery, sharing, and reuse. The Readiness Engine for Data Integration (REDI) addresses computational readiness, but no corresponding tool evaluates whether a dataset’s metadata are sufficiently complete, governed, and standards-compliant for publication and agent-based consumption. Existing FAIR assessors operate only on published repository records, and no single system covers FAIR compliance, licensing, provenance, governance, reproducibility, and catalog readiness together. We present SetGo, an open-source Python toolkit that assesses and repairs metadata readiness across these six dimensions before a dataset is published or archived. Applied to four scientific corpora, SetGo surfaces deficiencies that general-purpose tools do not detect: ERA5 climate metadata scores 4% on ACDD 1.3 compliance; materials datasets fail OPTIMADE species-definition requirements; and PDB-derived proteomics data carries licensing terms incompatible with standard SPDX identifiers. Guided enrichment raises overall FAIR scores from 52–57% to 81–91%, and a single setgo publish command pushes to Hugging Face Hub, CKAN, or OpenMetadata with ML Commons Croissant 1.0 metadata sidecars. To support interactive and automated workflows, SetGo integrates with coding agents powered by large language models (LLMs) through a /setgo skill that enables natural-language execution of the full assess–enrich–publish loop, with user involvement limited to supplying missing metadata values.

Wilkinson, Sean [ORNL] (ORCID:0000000214437479)↗
DOE OSTI2026

Towards AI-assisted neutrino flavor theory design

Particle physics theories, such as those which explain neutrino flavor mixing, arise from a vast landscape of model-building possibilities. A model’s construction typically relies on the intuition of theorists. It also requires considerable effort to identify appropriate symmetry groups, assign field representations, and extract predictions for comparison with experimental data. We develop Autonomous Model Builder (AMBer), a framework in which a reinforcement learning agent interacts with a streamlined physics software pipeline to search these spaces efficiently. AMBer selects symmetry groups, particle content, and group representation assignments to construct models while minimizing the number of free parameters introduced. We validate our approach in well-studied regions of theory space and extend the exploration to a previously unexamined symmetry group. While demonstrated in the context of neutrino flavor theories, this approach of reinforcement learning with physics software feedback may be extended to other theoretical model-building problems in the future.

Baretz, Jason Benjamin↗
DOE OSTI2026

TETA Autoresearch [SWR-26-089]

TETA Autoresearch is a template repository based on github.com/karpathy/autoresearch for AI-assisted research science in the TETA group in the Center for Integrated Mobility Sciences (CIMS) center at the National Laboratory of the Rockies. This software is a template for running autonomous research experiments that iteratively improve an ML model for a single optimization objective. Two execution modes share one harness: LLM mode - an agent (e.g. Claude Code) edits a scaffold train.py one change at a time, tagging each experiment, logging reasoning, and pushing results. Defined by program.md. Optimizer mode - an Optuna-backed driver (TPE / CMA-ES / Random) iterates over a domain-defined search space. Defined by optimizers/. RouteE (vehicle energy prediction) is the reference domain under domains/routee/. Adding a new domain is mechanical - see EXTENDING.md.

Reinicke, Nicholas [National Laboratory of the Roc↗
NASA NTRS1991

Spectroscopy and multivariate analyses applications related to solid rocket nozzle bondline

Chemical composition and molecular orientation define the properties of materials. Information related to chemical composition and molecular configuration is obtained by various forms of spectroscopy. Software algorithms developed for multivariate analyses, expert systems, and Artificial Intelligence (AI) are used to conduct repetitive operations. The techniques are believed to be of particular significance toward achieving TQM objectives. The objective was to obtain information related to the quality of the bondline in the solid rocket motor, SRM, nozzle. Hysol 934 NA, a room temperature curing epoxide resin, is used as the bonding agent. A good bond requires that the adhesive be placed on a properly prepared metal surface, the adhesives Part A and B be mixed in appropriate ratio from material within shelf life specifications. Spectroscopic data was obtained for surfaces prepared according to specifications, contaminated metal surfaces, samples of the epoxide adhesive at times that represent shelf aging from 3 months to 2 years, several mix ratio of A to B, and curing material. Temperature was found to be a significant factor. The study concentrated on pot life and mix ratio.

Arendale, W. F.↗
NASA NTRS2003

Automated Data Processing as an AI Planning Problem

NASA s vision for Earth Science is to build a "sensor web"; an adaptive array of heterogeneous satellites and other sensors that will track important events, such as storms, and provide real-time information about the state of the Earth to a wide variety of customers. Achieving his vision will require automation not only in the scheduling of the observations but also in the processing af tee resulting data. Ta address this need, we have developed a planner-based agent to automatically generate and execute data-flow programs to produce the requested data products. Data processing domains are substantially different from other planning domains that have been explored, and this has led us to substantially different choices in terms of representation and algorithms. We discuss some of these differences and discuss the approach we have adopted.

Golden, Keith↗
NASA NTRS2012

Implementing Artificial Intelligence Behaviors in a Virtual World

In this paper, we will present a look at the current state of the art in human-computer interface technologies, including intelligent interactive agents, natural speech interaction and gestural based interfaces. We describe our use of these technologies to implement a cost effective, immersive experience on a public region in Second Life. We provision our Artificial Agents as a German Shepherd Dog avatar with an external rules engine controlling the behavior and movement. To interact with the avatar, we implemented a natural language and gesture system allowing the human avatars to use speech and physical gestures rather than interacting via a keyboard and mouse. The result is a system that allows multiple humans to interact naturally with AI avatars by playing games such as fetch with a flying disk and even practicing obedience exercises using voice and gesture, a natural seeming day in the park.

Krisler, Brian↗
DOE OSTI2025

Destabilizing a Social Network Model via Intrinsic Feedback Vulnerabilities

Social influence plays a significant role in shaping individual sentiments and actions, particularly in a world of ubiquitous digital interconnection. The rapid development of generative artificial intelligence (AI) has given rise to well-founded concerns regarding the potential implementation of radicalization techniques in social media. Motivated by these developments, we present a case study investigating the effects of small but intentional perturbations on a simple social network. We employ Taylor's classic model of social influence and tools from robust control theory (most notably the Dynamical Structure Function (DSF)), to identify perturbations that qualitatively alter the system's behavior while remaining as unobtrusive as possible. We examine two such scenarios: perturbations to an existing link and perturbations that introduce a new link to the network. In each case, we identify destabilizing perturbations of minimal norm and simulate their effects. Remarkably, we find that small but targeted alterations to network structure may lead to the radicalization of all agents, exhibiting the potential for large-scale shifts in collective behavior to be triggered by comparatively minuscule adjustments in social influence. Given that this method of identifying perturbations that are innocuous yet destabilizing applies to any suitable dynamical system, our findings emphasize a need for similar analyses to be carried out on real systems (e.g., real social networks), to identify the places where such dynamics may already exist.

Rogers, Lane [ORNL]↗
DOE OSTI2024

Characterizing Interaction Uncertainty in Human-Machine Teams

With the increasing use and adoption of artificial intelligence (AI), the reliability of modern data systems will be driven by a tighter teaming between human experts and intelligent machine teammates. As in the case of human-human teams, the success of human-machine teams will also rely on clear communication about mutual goals and actions. In this paper, we combine related literature from cognitive psychology, human-machine teaming, uncertainty in data analysis, and multi-agent systems to propose a new form of uncertainty: interaction uncertainty for characterizing bidirectional communication in human-machine teams. We map the causes and effects of interaction uncertainty and outline potential ways to mitigate uncertainty for mutual trust in a high-consequence real-world scenario.

uncertainty, data analytics, interaction, trust, h↗
NASA NTRSDate not supplied

Tradeoffs When Considering Deep Reinforcement Learning for Contingency Management in Advanced Air Mobility

Air transportation is undergoing a rapid evolution globally with the introduction of Advanced Air Mobility (AAM) and with it comes novel challenges and opportunities for transforming aviation. As AAM operations introduce increasing heterogeneity in vehicle capabilities and density, increased levels of automation are likely necessary to achieve operational safety and efficiency goals. This paper focuses on one example where increased automation has been suggested. Autonomous operations will need contingency management systems that can monitor evolving risk across a span of interrelated (or interdependent) hazards and, if necessary, execute appropriate control interventions via supervised or automated decision making. Accommodating this complex environment may require automated functions (autonomy) that apply artificial intelligence (AI) techniques that can adapt and respond to a quickly changing environment. This paper explores the use of Deep Reinforcement Learning (DRL) which has shown promising performance in complex and high-dimensional environments where the objective can be constructed as a sequential decision-making problem. An extension of a prior formulation of the contingency management problem as a Markov Decision Process (MDP) is presented and uses a DRL framework to train agents that mitigate hazards present in the simulation environment. A comparison of these learning-based agents and classical techniques is presented in terms of their performance, verification difficulties, and development process.

machine learningautonomous systems; flight simulat↗
NASA NTRSDate not supplied

Tradeoffs When Considering Deep Reinforcement Learning for Contingency Management in Advanced Air Mobility

Air transportation is undergoing a rapid evolution globally with the introduction of Advanced Air Mobility (AAM) and with it comes novel challenges and opportunities for transforming aviation. As AAM operations introduce increasing heterogeneity in vehicle capabilities and density, increased levels of automation are likely necessary to achieve operational safety and efficiency goals. This paper focuses on one example where increased automation has been suggested. Autonomous operations will need contingency management systems that can monitor evolving risk across a span of interrelated (or interdependent) hazards and, if necessary, execute appropriate control interventions via supervised or automated decision making. Accommodating this complex environment may require automated functions (autonomy) that apply artificial intelligence (AI) techniques that can adapt and respond to a quickly changing environment. This paper explores the use of Deep Reinforcement Learning (DRL) which has shown promising performance in complex and high-dimensional environments where the objective can be constructed as a sequential decision-making problem. An extension of a prior formulation of the contingency management problem as a Markov Decision Process (MDP) is presented and uses a DRL framework to train agents that mitigate hazards present in the simulation environment. A comparison of these learning-based agents and classical techniques is presented in terms of their performance, verification difficulties, and development process.

machine learning↗
DOE OSTI2025

Antiviral discovery using sparse datasets by integrating experiments, molecular simulations, and machine learning

Computational methods have demonstrated success in identifying virucidal agents, effectively contributing to the discovery of novel virucidal molecules. In this study, we developed a machine learning (ML) model, trained on a small dataset, to predict inhibitors of human enterovirus 71 (EV71), a pathological agent that causes severe disease in children and immunocompromised adults. Despite the dataset’s limitation, comprising of only 36 compounds tested, our ML framework demonstrated significant predictive capability. Notably, experimental validation revealed that five out of the eight compounds predicted by our model from the Chinese cosmetic material list exhibited virucidal activity. The inhibitor effects displayed by the main active compounds were further confirmed by molecular dynamics simulation. This underscores the potential of our AI-driven approach to bypass data constraints in identifying active molecules against viral pathogens.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2026

REDI – Readiness Engine for Data Integration

The Readiness Engine for Data Integration (REDI) is an open-source framework for automating, standardizing, and assessing the process of preparing scientific data for AI training. REDI implements a five-stage pipeline (ingest, preprocess, transform, structure, output) with per-stage provenance instrumentation via Flowcept, domain-aware transformation logic (PII anonymization, regridding, graph encoding, and more), and built-in readiness assessment and validation modes. REDI has been evaluated across climate, proteomics, materials science, and nuclear fusion datasets, demonstrating near-ideal parallel scaling to 100 nodes on OLCF's Frontier system. REDI is deployable as an agent-callable skill in coding environments such as Claude Code and OpenAI Codex, and is complemented by SetGo for FAIR compliance and catalog publication.

Brewer, Wesley [Oak Ridge National Laboratory (ORN↗
DOE OSTI2026

From Rules to Reasoning: A Survey of Large Language Model-Based Approaches to Scientific Hypothesis and Idea Generation

Scientific hypothesis generation represents a fundamental challenge in contemporary research due to exponentially expanding literature volumes and increasing disciplinary specialization. Large language models (LLMs) have emerged as transformative tools for automated scientific discovery, moving beyond traditional rule-based and literature-mining approaches. Four paradigmatic approaches define current LLM-driven hypothesis generation: direct prompting and fine-tuning methods, knowledge-enhanced frameworks integrating retrieval-augmented generation (RAG), multi-agent collaborative systems simulating research teams, and reasoning-focused approaches implementing cognitive architectures. Domain-specific applications demonstrate statistical equivalence to human expert performance in social psychology, experimental validation in biomedical research, and near-expert quality in astronomy. Evaluation methodologies encompass human expert assessment, LLM-as-judge frameworks, and comprehensive benchmarking systems. Technical challenges include hallucination management, knowledge integration limitations, and balancing novelty with feasibility. Future directions emphasize hybrid neural-symbolic architectures and sophisticated human-AI collaboration models for responsible scientific discovery acceleration.

AI-driven discovery↗
DOE OSTI2026

A Scoping Review of Mixed Initiative Visual Analytics in the Automation Renaissance

Artificial agents are increasingly integrated into data analysis workflows, carrying out tasks that were primarily done by humans. Our research explores how the introduction of automation recalibrates the dynamic between humans and automating technology. To explore this question, we conducted a scoping review encompassing twenty years of mixed-initiative visual analytic systems. To describe and contrast the relationship between humans and automation, we developed an integrated taxonomy to delineate the objectives of these mixed-initiative visual analytics tools, how much automation they support, and the assumed roles of humans. Here, we describe our qualitative approach of integrating existing theoretical frameworks with new codes we developed. Our analysis shows that the visualization research literature lacks consensus on the definition of mixed-initiative systems and explores a limited potential of the collaborative interaction landscape between people and automation. Our research provides a scaffold to advance the discussion of human-AI collaboration during visual data analysis. Our integrated taxonomy is available in the form of a web application on https://smonadjemi.github.io/miva.

Monadjemi, Shayan [ORNL] (ORCID:0000000293855969)↗