Search NASA⌕ Search

SEARCH · Search NASA

Results for “AI agent”

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 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Employing artificial intelligence to steer exascale workflows with colmena

Computational workflows are a common class of application on supercomputers, yet the loosely coupled and heterogeneous nature of workflows often fails to take full advantage of their capabilities. We created Colmena to leverage the massive parallelism of a supercomputer by using Artificial Intelligence (AI) to learn from and adapt a workflow as it executes. Colmena allows scientists to define how their application should respond to events (e.g., task completion) as a series of cooperative agents. In this paper, we describe the design of Colmena, the challenges we overcame while deploying applications on exascale systems, and the science workflows we have enhanced through interweaving AI. The scaling challenges we discuss include developing steering strategies that maximize node utilization, introducing data fabrics that reduce communication overhead of data-intensive tasks, and implementing workflow tasks that cache costly operations between invocations. These innovations coupled with a variety of application patterns accessible through our agent-based steering model have enabled science advances in chemistry, biophysics, and materials science using different types of AI. In conclusion, our vision is that Colmena will spur creative solutions that harness AI across many domains of scientific computing.

Workflows↗
DOE OSTI2024

Towards a High Fidelity Training Environment for Autonomous Cyber Defense Agents

Cyber defenders are overwhelmed by the frequency and scale of attacks against their networks. This problem will only be exacerbated as attackers leverage AI to automate their workflows. Autonomous cyber defense capabilities could aid defenders by automating operations and adapting dynamically to novel threats. However, existing training environments fall short in areas such as generalization, explainability, scalability, and transferability, making it intractable to train agents that will be effective in real networks. In this paper we take an important step towards creating autonomous cyber defense agents — we present a high fidelity training environment called Cyberwheel that includes both simulation and emulation capabilities. Cyberwheel simplifies customization of the training network and easily allows redefining the agent’s reward function, observation space, and action space to support rapid experimentation of novel approaches to agent design. It also provides visibility into agent behaviors necessary for agent evaluation and sufficient documentation / examples to lower the barrier to entry. As an example use case of Cyberwheel, we present initial results training an autonomous agent to deploy cyber deception strategies in simulation.

Oesch, T↗
DOE OSTI2026

Wolf

The Workflow Orchestration Language Framework (WOLF) is an agentic framework grounded in natural language with an architecture inspired by reinforcement learning (RL)—designed to orchestrate, scale, and accelerate complex workflows. The concept of WOLF was born out of the very successful ASC Tri-lab Multi-Agent Design Assistant (MADA) project, but extends beyond its domain-specific design agents to provide a more general and extensible architecture. WOLF capitalizes on the lessons learned from MADA and is fully aligned with Sutton’s The Bitter Lesson—that the most enduring progress in AI comes from general-purpose methods that scale with computation, rather than narrow techniques built on domain-specific human knowledge. In this spirit, WOLF enables agents to autonomously learn workflows, capture strategies as reusable playbooks, and build a growing corpus of interpretable, auditable “wisdom artifacts.” These artifacts, expressed in natural language, bridge human and machine understanding while preserving adaptability and scalability as computational power continues to expand.

Boureima, Ismaeal↗
DOE OSTI2025

Secure API-Driven Research Automation to Accelerate Scientific Discovery

The Secure Scientific Service Mesh (S3M) provides API-driven infrastructure to accelerate scientific discovery through automated research workflows. By integrating near real-time streaming capabilities, intelligent workflow orchestration, and fine-grained authorization within a service mesh architecture, S3M enables secure and flexible programmatic access to high performance computing (HPC) resources. This framework allows intelligent agents and experimental facilities to dynamically provision resources and execute complex workflows, accelerating experimental lifecycles, and enabling AI-augmented autonomous science. S3M establishes a modern foundation for scientific computing infrastructure that significantly reduces traditional barriers between researchers, computational resources, and experimental facilities.

Skluzacek, Tyler [ORNL] (ORCID:0000000322424931)↗
DOE OSTI2025

CHEMREASONER: Heuristic Search over a Large Language Model’s Knowledge Space using Quantum-Chemical Feedback

The discovery of new catalysts is essential for the design of new and more efficient chemical processes in order to transition to a sustainable future. We introduce an AI-guided computational screening framework unifying linguistic reasoning with quantum-chemistry based feedback from 3D atomistic representations. Our approach formulates catalyst discovery as an uncertain environment where an agent actively searches for highly effective catalysts via the iterative combination of large language model (LLM)-derived hypotheses and atomistic graph neural network (GNN)-derived feedback. Identified catalysts in intermediate search steps undergo structural evaluation based on spatial orientation, reaction pathways, and stability. Scoring functions based on adsorption energies and barriers steer the exploration in the LLM's knowledge space toward energetically favorable, high-efficiency catalysts. We introduce planning methods that automatically guide the exploration without human input, providing competitive performance against expert-enumerated chemical descriptor-based implementations. By integrating language-guided reasoning with computational chemistry feedback, our work pioneers AI-accelerated, trustworthy catalyst discovery.

artificial intelligence↗
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↗
DOE OSTI2026

AI-Ready Semantic Infrastructure for CEBAF: From CED to PALS Knowledge Graphs

JLab and PNNL are jointly developing an AI-ready data ecosystem that exposes the Continuous Electron Beam Acceleration Facility’s (CEBAF’s) operational configuration, lattice description, and control-system channels to agentic optimization frameworks through a standards-based semantic layer. The effort integrates the existing facility-specific CEBAF Element Database (CED) with extensions of the emerging facility-agnostic Particle Accelerator Lattice Standard (PALS) to produce a knowledge graph (KG) containing coherent, machine-interpretable views of devices, signals, and regions. With this KG, CEBAF’s setpoints, readbacks, and device hierarchies become queryable using a uniform declarative graph query language (e.g., Neo4j Cypher), providing intents and inspectable semantics suitable for agentic control. The resulting graph-backed interfaces will allow autonomous agents to retrieve authoritative machine configurations, reason over device- and signal-level relationships, and execute tuning and diagnostic workflows without bespoke CEBAF-specific logic, thereby delivering a scalable pathway from operational data to trustworthy agentic accelerator tuning frameworks.

Zhang, He [Thomas Jefferson National Accelerator F↗
DOE OSTI2026

Development and Implementation of a New AI-Based Tool to Support Fast Reactor Software Model Generation and Validation

This report summarizes FY26 work to develop Maggie, an artificial intelligence-based assistant designed to support software model generation and validation activities for fast reactor analysis codes. The project established a modular, code-agnostic software architecture that separates reusable agent capabilities from code-specific knowledge and tools, with initial implementation focused on the FRP-supported fast reactor safety analysis code SAS4A/SASSYS1 (SAS). A curated SAS-specific knowledge base was assembled from the code manual, training materials, historical analysis reports, and representative input files, and was integrated through retrieval-augmented generation to ground Maggie’s responses in authoritative sources. Maggie was deployed on the internal Argonne network, where it demonstrated practical user-facing capability as a chatbot for answering natural language questions about SAS and retrieving relevant technical information. Demonstration cases also showed that Maggie can generate useful snippets of SAS input for selected modeling tasks, while highlighting current limitations in reliability and consistency for more complex input generation tasks. Overall, the FY26 effort established the technical foundation for an AI-assisted capability intended to improve the efficiency, consistency, and accessibility of fast reactor software model development at Argonne and, with further improvements, to support eventual use by the broader fast reactor community, including industry users of FRP-supported analysis tools.

Thomas, Rachel [Argonne National Laboratory (ANL),↗
DOE OSTI2025

Tactical Analysis for Calculating Contextual Risk at Boundaries: Summary of Laboratory Directed Research & Development Effort

The Tactical Analysis for Calculating Contextual Risk at Boundaries (TACCRAB) tool is an innovative digital twin (DT) platform and automated risk algorithm designed to transform operational decision-making in structured screening environments, with an initial focus on Southern Border Land Ports of Entry (POEs). The invention provides integration points for advanced artificial intelligence, predictive modeling, and real-time data analysis to produce a comprehensive risk management tool that enables proactive, data-informed security strategies. The core inventive features of TACCRAB center on its unique risk algorithm, which dynamically calculates contextual risk by synthesizing historical data, near real-time streaming data from the checkpoints themselves, and AI-generated predictions. Unlike traditional risk assessment methods, TACCRAB utilizes a DT to provide comprehensive operational insights, allowing stakeholders to visualize, simulate, and optimize checkpoint configurations with unprecedented speed and contextual awareness. TACCRAB's key innovation lies in its ability to combine multiple complex inputs - including technology detection probabilities, resource availability, screening pathway characteristics, and threat actor behavioral patterns - into a unified risk calculation and update these inputs based on changing operational and environmental conditions. By leveraging a DT that continuously updates and learns from linked data, TACCRAB can suggest adaptive mitigation strategies that minimize risk while maintaining operational efficiency. Particularly novel is the platform's approach to decision support, which goes beyond static risk assessment. The DT provides dynamic metrics such as wait times, resource allocation effectiveness, and potential emerging threat scenarios, enabling users to view sophisticated, relevant what-if simulations and optimize checkpoint operations in near real-time. The system's architecture allows for generalized application across different screening environments, such as secure facilities, ports of entry, and soft targets, making it a versatile tool for security and operational management. The invention distinguishes itself through its comprehensive integration of predictive modeling, AI-driven pattern discovery, and user-friendly interface design. By combining these elements, TACCRAB transforms complex risk data into actionable insights, supporting decision-makers at various organizational levels - from booth agents making split-second screening decisions to checkpoint managers optimizing the day's resource allocation to strategic planners managing long-term investments.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
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)]↗
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↗
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↗
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↗