Search NASA⌕ Search

SEARCH · Search NASA

Results for “agentic systems”

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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Model-based Hierarchical Reinforcement Learning for Improved Physical Security Design: A Prototype

Prior work in FY24 developed an adversarial AI agent aid in path analysis of physical protection systems. This agent, trained using a model-based reinforcement learning algorithm, was able to successfully learn the most vulnerable path in facilities. It was able to extend the current state of practice for physical protection design by exhibiting dynamic behavior based on current environmental conditions. Whereas PathTrace largely performs a static, graph-based analysis, the AI agent was able to make decisions based on relative position in the facility, current conditions (was the adversarial agnet discovered?), and proximity to secondary targets. The agent demonstrated some novel capabilities, but had limitations that need to be resolved before it can be used for production purposes. For example, the adversarial agent generalizes poorly and takes a relatively long time to train. Nonetheless, there is still considerable promise for developing the adversarial agent further in order to explore even richer, more dynamic behaviors (e.g., adversary motivations, environmental debris, and more). This work considers a complementary idea; development of a planning agent. The planning agent is envisioned as an auto-complete-like tool that can help accelerate security system design by human experts. The agent would respect existing barriers and sensors placed by a human expert while offering cost-effective suggestions (i.e., implicitly balancing effectiveness with cost) to improve the design. The goal is for this agent to be part of an expert’s toolbox, not to totally upend the current state-of-practice, or to displace human experts. The ultimate goal would be concurrent training of both the adversarial and planning agent together, to learn entirely through self-play. This would represent an entirely new way of performing system deign. We selected a hierarchical, model-based reinforcement learning algorithm to serve as the planning agent. This is an extension of concepts used in the prior FY24 adversarial agent work. There, we had a single agent acting an environment. Here, we have two different sub-agents (policies), working together, to form a complete agent. There is a manager policy, which can select abstract goals on slower time scales, and a worker, which performs primitive actions to reach goals selected by the manager. It is worth noting that this class of algorithm is challenging to work with. From our understanding, our work is one of the first successful uses of model-based reinforcement learning (MBRL) in nuclear energy1 , and likely the first hierarchical model-based reinforcement learning application in nuclear energy. Further, this work is one of the first known attempts to apply AI to perform a design tasks in nuclear energy. Consequently, there were significant implementation challenges and the bulk of the work was focused on successful implementation and algorithm design. The results presented here are very low technology readiness level as a consequence of the lack of related literature, but still represent a significant step forward in the pursuit of applied AI for design.

42 ENGINEERING↗
DOE OSTI2022

Quantum model learning agent: characterisation of quantum systems through machine learning

Accurate models of real quantum systems are important for investigating their behaviour, yet are difficult to distil empirically. Here, we report an algorithm—the quantum model learning agent (QMLA)—to reverse engineer Hamiltonian descriptions of a target system. We test the performance of QMLA on a number of simulated experiments, demonstrating several mechanisms for the design of candidate Hamiltonian models and simultaneously entertaining numerous hypotheses about the nature of the physical interactions governing the system under study. QMLA is shown to identify the true model in the majority of instances, when provided with limited a priori information, and control of the experimental setup. Our protocol can explore Ising, Heisenberg and Hubbard families of models in parallel, reliably identifying the family which best describes the system dynamics. We demonstrate QMLA operating on large model spaces by incorporating a genetic algorithm to formulate new hypothetical models. The selection of models whose features propagate to the next generation is based upon an objective function inspired by the Elo rating scheme, typically used to rate competitors in games such as chess and football. In all instances, our protocol finds models that exhibit F 1 score ≥ 0.88 when compared with the true model, and it precisely identifies the true model in 72% of cases, whilst exploring a space of over 250 000 potential models. By testing which interactions actually occur in the target system, QMLA is a viable tool for both the exploration of fundamental physics and the characterisation and calibration of quantum devices.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Intelligent System Partitioning for Agent-Based Security Constrained Optimal Power Flow

This project developed scalable, computationally efficient algorithms to solve realistic large-scale power system optimization problems as part of a larger series of competitions run by ARPA-E. These problems are important because the secure and reliable operation of the power grid, especially under increased uncertainty and variability, is growing increasingly challenging. The economic feasibility of the proposed methods developed by our team is quite low, considering it’s a purely software-based solution to operate power grids more efficiently. The technical effectiveness, as evidenced by our performance in the competition, balances heuristics and approximations to provide a tradeoff between speed and accuracy.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

A Real-time Agent Based Optimization and Control Approach for Residential Building Heating Ventilation and Air Conditioning Systems

The prevalence of the loT (Internet of Things) is fostering the development of new control options and decision making that was not previously available. This is creating a wealth of opportunities for real-time control approaches and systems that can optimize for a common goal. This paper presents a smart residential neighborhood with optimization at the residential level utilizing a system of agents. The optimization utilizes information and modeling to optimize variable speed HVAC real-time operation in actual residential buildings. Data is presented showing the performance of the optimization and conclusions are drawn on next steps for development.

Hall, Joni↗
DOE OSTI2026

MOSAIC-CONUS: A Multimodal, Multi-Temporally Paired Dataset for Earth Sciences

Earth embeddings—vector representations of geographic locations indexed in space and time—are emerging as a unifying interface for geospatial AI. However, their quality depends not only on model design, but on how multimodal Earth observation (EO) data are spatially indexed, temporally aligned, and cross-modally associated during pretraining. We introduce MOSAIC-CONUS (Multimodal Observations with Spatially Aligned Imagery, Urban Points of Interest, In-Situ Measurements and Text Captions), a large-scale EO dataset over the contiguous United States, organized around 250,000 stratified point indices that serve as stable spatial keys across seven modalities: active radar, passive optical imagery, lidar-derived elevation, land cover, functional context, hydrometeorological measurements, and textual summaries. Unlike existing EO datasets, MOSAIC-CONUS introduces four contributions not jointly addressed in prior work: 1. an open-source, large-scale multimodal EO corpus structured around point-indexed data designed to support Earth embedding learning; 2. explicit radar-optical pairing tables spanning twelve temporal alignment regimes, formalizing cross-sensor alignment as a controllable variable for analyzing how temporal mismatch across modalities influences learned embeddings quality; 3. a benchmark suite spanning cross-modal retrieval, annual nightlights regression, and basin-held-out streamflow prediction, positioning MOSAIC-CONUS as a benchmark-ready resource for multimodal AI systems; and 4. a language-based embedding layer through co-registered textual summaries, enabling Earth embeddings to function as a queryable interface for agentic AI systems. The dataset and pairing protocols are publicly released.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Ripple-Type Control for Enhancing Resilience of Networked Physical Systems

Distributed control agents have been advocated as an effective means for improving the resiliency of our physical infrastructures under unexpected events. Purely local control has been shown to be insufficient, centralized optimal resource allocation approaches can be slow. In this context, we put forth a hybrid low-communication saturation-driven protocol for the coordination of control agents that are distributed over a physical system and are allowed to communicate with peers over a “hotline” communication network. According to this protocol, agents act on local readings unless their control resources have been depleted, in which case they send a beacon for assistance to peer agents. Our ripple-type scheme triggers communication locally only for the agents with saturated resources and it is proved to converge. Moreover, under a monotonicity assumption on the underlying physical law coupling control outputs to inputs, the devised control is proved to converge to a configuration satisfying safe operational constraints. The assumption is shown to hold for voltage control in electric power systems and pressure control in water distribution networks. Numerical tests corroborate the efficacy of the novel scheme.

distributed control↗
DOE OSTI2021

PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems [SWR-22-07]

NREL's PowerGridworld provides a modular simulation environment for training heterogenous, grid-aware, multi-agent reinforcement learning (RL) policies at scale. The package enables the user to create component gym environments that can be composed into more complex agents. For example, a grid interactive building environment can be created by composing together component environments each encapsulating the building, PV, and battery physics. These multi-component environments can then be combined into multi-agent simulation where each agent's power consumption/injection becomes an input for solving the optimal power flow on a distribution feeder modeled in OpenDSS. Information from OpenDSS, such as bus voltages and line flows, can be included in the agents' observation spaces to enable grid-aware rewards. The default API for the PowerGridworld simulator conforms to RLLib's MultiAgent API and thus enables distributed training using HPC and cloud resources.

Biagioni, David↗
DOE OSTI2026

MADA: Multi-Agent Design Assistant

MADA (Multi-Agent Design Assistant) is a Large Language Model (LLM) powered multi-agent framework that coordinates specialized agents for complex design workflows. The system was designed for HPC workflows with the following agents in mind: 1) A Job Management Agent (JMA) launches and manages ensemble simulations on HPC systems, 2) a Geometry Agent (GA) generates meshes, and 3) an Inverse Design Agent (IDA) proposes new designs informed by simulation outcomes. Our framework reduces cumbersome manual workflow setup, and enables automated design exploration at scale. However, the software also enables users to rapidly create new multi-agent systems. Simply define new agents in a configuration file, giving each their own set of tools (via MCP), and then chat and prompt your new multi-agent system. Is

Gunnarson, BrianS [Lawrence Livermore National Lab↗
DOE OSTI2021

Data-Driven Multi-agent Deep Reinforcement Learning for Distribution System Decentralized Voltage Control with High Penetration of PVs

This paper proposes a novel model-free/data-driven centralized training and decentralized execution multi-agent deep reinforcement learning (MADRL) framework for distribution system voltage control with high penetration of PVs. The proposed MADRL can coordinate both the real and reactive power control of PVs with existing static var compensators and battery storage systems. Unlike the existing DRL-based voltage control methods, our proposed method does not rely on a system model during both the training and execution stages. This is achieved by developing a new interaction scheme between the surrogate modeling of the original system and the multi-agent soft actor critic (MASAC) MADRL algorithm. In particular, the sparse pseudo-Gaussian process with a few-shots of measurements is utilized to construct the surrogate model of the original environment, i.e., power flow model. This is a data-driven process and no model parameters are needed. Furthermore, the MASAC enabled MADRL allows to achieve better scalability by dividing the original system into different voltage control regions with the aid of real and reactive power sensitivities to voltage, where each region is treated as an agent. This also serves as the foundation for the centralized training and decentralized execution, thus significantly reducing the communication requirements as only local measurements are required for control. Comparative results with other alternatives on the IEEE 123-nodes and 342-nodes systems demonstrate the superiority of the proposed method.

14 SOLAR ENERGY↗
DOE OSTI2026

CVEVOLVE

CVEvolve is an agentic AI system for autonomous algorithm discovery for scientific data processing. It creates workflows where large language model agents freely set up and configure development environments and evaluation harnesses, develop and improve data processing algorithms with designed exploration-exploitation balancing mechanisms, log history and findings in a structured database, and run holdout testing to ensure algorithm generalizability. CVEvolve offers a zero-code interface and does not require users to provide structured data and evaluation scripts.

Cherukara, MatthewJoseph [Argonne National Laborat↗
DOE OSTI2025

A2SD: Accelerating Scientific Innovation Through Autonomous Discovery Systems

The 2025 Advancing Autonomous Scientific Discovery (A2SD) workshop convened researchers from academia, national laboratories, and industry to explore the transformative role of autonomy in scientific discovery. The workshop highlighted a convergence of artificial intelligence, robotics, and computational workflows into autonomous systems capable of accelerating the scientific process. Presentations and discussions spanned autonomous experimentation, intelligent workflow orchestration, digital twins, and agent-based systems for managing complex research ecosystems. Key challenges discussed included interoperability across heterogeneous infrastructures, near real-time data management under FAIR principles, reproducibility, and the integration of human oversight. The workshop also emphasized the need for modular software interfaces, federated learning models, and education initiatives to support a next-generation scientific workforce.

Taufer, Michela [University of Tennessee, Knoxvill↗
DOE OSTI2025

From clutter to clarity: Emergent neural operators via questionnaire metrics

Real-world datasets in chemical engineering and bioengineering processes—such as those from catalytic reactors, multiphase flows, polymerization reactors, bioreactors, and clinical trials—can often be unlabeled or disorganized, rendering the training of existing supervised learning models ineffective at learning the underlying dynamics. To salvage these datasets for decision-making, we first seek to obtain clarity from the cluttered data. Here, we present a framework for developing “structural” generative models, discovering emergent equations, and constructing efficient emulators from scrambled datasets by integrating unsupervised organizational learning techniques (Questionnaires) with advanced deep learning architectures (Deep Hidden Physics Models and Deep Operator Networks). Our approach is demonstrated on two illustrative model systems: (a) a 1D advection–diffusion partial differential equation representing a winding underground pipe and (b) an ensemble of Stuart–Landau oscillators, an agent-based system of coupled ordinary differential equations. In both cases, we successfully reconstruct meaningful spatial, temporal, and parameter embeddings from scrambled data, enabling good predictions of system dynamics. As a result, we highlight the framework’s potential for broader applications, enabling data-driven system identification in fields with inherently disorganized or hidden parameter spaces.

42 ENGINEERING↗
DOE OSTI2020

Distributed Detection of Malicious Attacks on Consensus Algorithms with Applications in Power Networks

Consensus-based distributed algorithms are well suited for coordination among agents in a cyber-physical system. These distributed schemes, however, suffer from their vulnerability to cyber attacks that are aimed at manipulating data and control ow. In this article, we present a novel distributed method for detecting the presence of such intrusions for a distributed multi-agent system following ratio consensus. We employ a Max-Min protocol to develop low cost, easy to implement detection strategies where each participating node detects the intrusion independently, eliminating the need for a trusted certifying agent in the network. The effectiveness of the detection method is demonstrated by numerical simulations on a 1000 node network to demonstrate the efficacy and simplicity of implementation.

27 ARPA - Advanced Research Projects Agency-Energy↗
DOE OSTI2020

Using AI Simulations to Dynamically Model Multi-agent Multi-team Energy Systems

The complexity of energy systems is well known as they are complex and intricate systems. As a result, many extant studies have used many simplifications or generalizations that do not accurately reflect the nature of this complex system. In particular, most HVAC systems are modeled as a single unit, or several large units, rather than as a hierarchical composite (e.g., as a floor rather than as a collection of disparate rooms). The net result of this is that the simulations are too generic to perform meaningful analysis, machine learning, or integrated simulation. We propose using a multi-agent multi-team strategic simulations framework called SiMAMT to better define, model, simulate, and learn the HVAC environment. SiMAMT allows us to create distinct models for each type of room, hierarchically aggregate them into units (like floors, or sections), and then into larger sets (like buildings or a campus), and then perform a simulation that interacts with each sub-element individually, the teams of sub-elements collectively, and the entire set in aggregation. Further, and most importantly, we additionally model another ‘team’ within the simulation framework - the users of the systems. Again, each individual is modeled distinctly, aggregated into sub-sets, then collected into large sets. Each user, or agent, is performing on their own but with respect to the larger team goals. This provides a simulation that has a much higher model fidelity and more applicable results that match the real-world.

Franklin, D. Michael↗
DOE OSTI2024

Multi-agent voltage control in distribution systems using GAN-DRL-based approach

Active distribution grids can experience voltage fluctuations and violations due to the high penetration of variable distributed energy resources (DERs). These problems might occur because of the uncertain and variable generation natures of these resources, especially solar photovoltaic resources, during panel shadowing scenarios. Volt-VAR control (VVC) is an efficient method that controls the reactive power set-points of the inverters to regulate the voltage of distribution grids. Although several VVC approaches have been proposed recently, the performance of these approaches degrades significantly if behind-the-meter solar generation data are unobservable/missing. Therefore, it is necessary to impute missing/unobservable PV data accurately to be utilized in VVC approaches. Further, this paper proposes a model-free, data-driven, centrally trained, and decentrally executed multi-agent deep reinforcement learning-based VVC architecture to regulate the voltage of distribution networks. A generative adversarial network (GAN) is incorporated to impute the unobservable PV data accurately, which improves the performance of the proposed control architecture. The proposed multi-agent-soft-actor–critic algorithm (MASAC)-based VVC technique utilizes the actual PV dataset as well as the imputed dataset from the GAN framework to learn the optimal coordinated control policy for controlling the optimal reactive power set-points of PV inverters. The effectiveness of the proposed approach is analyzed on a modified IEEE 34-bus test case with added PV inverters. The results are compared and analyzed with a base case model with no VVC and VVC with a local droop control approach, genetic algorithm optimization, and a centralized soft actor–critic-based approach. Moreover, the performance of the proposed approach is compared with that of a multi-agent VVC framework without using the PV generation data and load information as the system state. The results illustrate that the proposed method with more state input improves the voltage profile and reduces the power loss of the network across various loading and PV generation scenarios.

14 SOLAR ENERGY↗
DOE OSTI2026

Accelerating lattice gauge theory studies with Agentic AI

Lattice gauge theory research, with its computationally intensive simulations and complex multi‑stage workflows, is well positioned to benefit from agentic AI systems. We demonstrate how such tools can support key components of lattice gauge theory research, including novel simulation code development using standard LQCD frameworks, HPC job orchestration, simulation data analysis, and expert‑guided tuning of algorithmic parameters such as Hasenbusch mass preconditioning and multigrid solvers. Our results show that agentic AI can reduce manual effort, improve productivity, and accelerate the research cycle while maintaining essential human oversight.

Ayyar, Venkitesh [Fermilab]↗
DOE OSTI2026

Building MCP-native hierarchical AI scientist ecosystems: a perspective on scaling multi-agent scientific discovery

Large language models (LLMs) are evolving from chatbots with limited tool-using capabilities to agentic AI systems that can perform deep research, assist in proposing hypotheses, help design experiments, automate data analysis, and draft scientific reports. However, there are currently two bottlenecks limiting LLMs' real-world impact on the broader scientific research community beyond academic demonstrations: lack of interoperability (repetitive manual tool-integration is required across scenarios) and the need for scalable coordination (unstructured communication and memory become brittle as the number of agents grows). In this Perspective, we argue that the next phase of agentic scientific discovery requires the development of an ecosystem of protocol-native agents and tools organized through hierarchies inspired by human society, beyond the current paradigm of a single monolithic “AI scientist”. We use Model Context Protocol (MCP) as a concrete example of an emerging interoperability layer for scientific tool and context exchange, and we propose three complementary pathways to increase the scaling capabilities of an MCP-native scientific ecosystem by addressing the composability issues: (1) MCP servers for high-value scientific tools maintained by domain experts, (2) automated transformation of existing code repositories into MCP services, and (3) autonomous invention and evolution of new agents and workflows. Finally, we provide a practical roadmap for scaling AI-driven scientific discovery by expanding tool supply and coordination in MCP-native scientific ecosystems.

97 MATHEMATICS AND COMPUTING↗