Search NASA⌕ Search

SEARCH · Search NASA

Results for “agentic”

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Towards Agentic AI on Particle Accelerators

As particle accelerators grow in complexity, traditional control methods face increasing challenges in achieving optimal performance. This paper envisions a paradigm shift: a decentralized multi-agent framework for accelerator control, powered by Large Language Models (LLMs) and distributed among autonomous agents. We present a proposition of a self-improving decentralized system where intelligent agents handle high-level tasks and communication and each agent is specialized control individual accelerator components. This approach raises some questions: What are the future applications of AI in particle accelerators? How can we implement an autonomous complex system such as a particle accelerator where agents gradually improve through experience and human feedback? What are the implications of integrating a human-in-the-loop component for labeling operational data and providing expert guidance? We show two examples, where we demonstrate viability of such architecture.

43 PARTICLE ACCELERATORS↗
DOE OSTI2026

Agentic Diagrammatica: Towards Autonomous Symbolic Computation in High Energy Physics

We present Diagrammatica, a symbolic computation extension to the HEPTAPOD agentic framework, which enables LLM agents to plan and execute multi-step theoretical calculations. Symbolic computation poses a distinctive reliability challenge for LLM agents, as correctness is governed by implicit mathematical conventions that are not encoded in a form that can be easily checked in the computational backend. We identify two complementary remedies, tool-constrained computation and targeted knowledge grounding, and pursue the first as the primary architecture. Concretely, we concentrate the agent's action distribution onto tool calls with convention-fixing semantics, in which the agent specifies a compact, human-auditable diagram specification and a trusted backend performs the symbolic or numerical manipulations exactly. The toolkit provides two complementary calculation paths consuming a shared diagram specification: Naive Dimensional Analysis (NDA) for order-of-magnitude rate estimates and Exact Diagrammatic Analysis (EDA) for tree-level symbolic calculations via automatic FeynCalc code generation, both supplemented by automatic Feynman diagram enumeration and a navigable theory knowledge base. The architecture is validated on two benchmarks: (1) an exhaustive catalog of all tree-level, single-vertex $1\to 2$ partial decay widths across scalar, fermion, and vector parents, with complete massless and threshold limits and Standard Model validation; and (2) an NDA sensitivity study of the muon decay multiplicity $μ^+ \to ν_μ\barν_e + n(e^+e^-) + e^-$, determining the maximum observable $n$ at current and planned muon experiments.

Menzo, Tony [Alabama U.; Fermilab] (ORCID:00000002↗
DOE OSTI2026

Agentic traffic intelligence: Augmented human-in-the-loop scenario generation for microscopic traffic simulation

Traditional microscopic traffic simulation generation often relies on static datasets and manual design, limiting its ability to simulate complex conditions easily. This paper presents a novel framework, Agentic Traffic Intelligence, which combines human approval large language models (LLMs), the Real-Twin tool, and multi-agent systems to perform realistic microscopic traffic simulation scenario generation. The proposed framework incorporates human-in-the-loop (HIL) control, retrieval-augmented generation (RAG), and multi-agent control mechanisms. HIL mechanisms are used to guide multiple LLMs focused on attributes for microscopic simulation generation and to improve the interpretability and transparency of LLM execution for users. RAG enhances context extraction by dynamically integrating external knowledge sources for traffic scenario generation foundations. A multi-agent architecture with supervisory control coordinates the interaction of simulation components, including traffic simulators, control logic, and calibration tools. This enables the synthesis of simulation-ready scenarios that reflect dynamic demand profiles and behavior controls. Furthermore, the framework fuses multisource traffic data with unstructured context and supports iterative refinement through interactive user feedback. Validated through microscopic simulation using Simulation of Urban Mobility, the generated scenarios demonstrate high-fidelity network generation with inflow and turn movement and behavioral calibration, offering a robust and efficient tool for stress-testing and optimizing urban mobility systems.

Hierarchical multi-agent control↗
DOE OSTI2025

Multi-scale, Multi-disciplinary, and Multi-agent Explainable AI with Koopman-Undergirded Learning, Prediction, and Analysis (M3EA KULPA) (Project Closeout Report)

The goal of this project was to develop and use domain-aware machine learning formulations, based on the Koopman Operator (KO), for modelling multi-scale, multi-disciplinary (e.g., multi-physics), and/or multi-agent systems. The project developed these formulations for the following cases: • Systems with dynamics at two separate time scales, • Systems with a bi-level hierarchical control structure, • Systems with bi-level hierarchical control and dynamics at two separate time scales (the lower level controls operating at the faster time scale), and • Systems with n separate but interacting agents/disciplines (with/without control, respectively); the controls for each agent could include bi-level hierarchical control and dynamics at two separate time scales as described above. The project then defined a set of dynamical systems consisting of different nonlinear oscillators that could be used to test these different formulations and then subsequently learned the KO models for those systems. With the KO models, we were able to do the following: • Quantify system stability, including both long-term and transient behavior, • Quantify the effects of feedbacks between the different time scales and agents/disciplines in terms of those feedbacks’ effects on system stability, • Replace a standard Proportional-Integral (PI) control in the hierarchical control structure with a KO-based Linear-Quadratic Regular (LQR), a form of optimal control, • Calculate optimal supervisory control policies a) with and without time scale separated dynamics at the lower level control levels and b) with both PI and KO-based LQR lower level control policies, and • Calculate dynamic Nash equilibria for multi-agent systems where each agent makes its own control decisions.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Enhancing Autonomous Control of Microreactors Using Multi-Agent Reinforcement Learning

In order for microreactors to be economically competitive, operation costs will need to be minimized through some degree of autonomous control. Previous work has demonstrated the effectiveness of reinforcement learning (RL) for load-following control in a drum-controlled microreactor. This study extends that work by exploring the potential of RL to independently control each of the reactor’s drums. We compare a single-agent RL approach with a multi-agent RL (MARL) framework, testing them for generalization across different load-following power profiles and control timescales, and for robustness in cases of randomly disabled control drums. Since the point kinetics simulation environment used in this study cannot resolve spatial effects, we assume that in the absence of spatially localized disturbances, optimal drum movements should be symmetrical. We demonstrate that single-agent RL is able to achieve accurate performance only when symmetric actions are ignored; otherwise, it fails to train a useful controller. Meanwhile, the MARL framework performs symmetric actions by design and trains a robust, accurate agent, as evidenced by mean absolute errors in power matching of 0.41% for the training power profile, 0.68% for a profile with half the drums disabled, and 0.21% for a profile on a realistic load-following time horizon.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2026

Desorption Electrospray Ionization–Mass Spectrometry Imaging Provides Spatiochemical Information on Potential Biocontrol Agents against Phytophthora capsici Infection in Tomato Plants

Biological control agents can offer an eco-friendly and more sustainable alternative to conventional chemical pesticides, providing protection against destructive pathogens, such as Phytophthora capsici, while reducing potential environmental harm associated with synthetic pesticide use in agricultural systems. This work evaluates the biocontrol effectiveness of Bacillus vallismortis, Bacillus amyloliquefaciens, Bacillus thuringiensis, and Bacillus subtilis, against the widespread plant pathogen Phytophthora capsici. Our studies showed that Bacillus thuringiensis and Bacillus subtilis promote plant growth and provide protection against Phytophthora capsici in both in vitro and in vivo greenhouse studies, while Bacillus vallismortis and Bacillus amyloliquefaciens were effective in vitro but not in vivo. Specifically, Bacillus thuringiensis was observed to both hinder the growth of Phytophthora capsici and enhance plant resilience to this pathogen, with B. thuringiensis-treated, pathogen-exposed plants displaying a 94.4% increase in root length and a 74.0% increase in shoot height compared to plants with only oomycete exposure. To probe the molecular interactions between the biocontrol agent and pathogen, a dual culture of Bacillus thuringiensis and Phytophthora capsici was analyzed in situ using a desorption electrospray ionization–mass spectrometry imaging (DESI-MSI) workflow. This approach interrogated the spatially oriented biochemical interactions that may serve as the molecular foundation for the effectiveness of these biological control agents in crop protection, identifying seven unique phenotypic regions within the dual culture. Herein, we demonstrate the benefits of biological control agent application in tomato cultivation and showcase the strengths of desorption electrospray ionization–mass spectrometry imaging when applied to the spatially resolved molecular characterization of agriculturally relevant microorganisms.

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

Data Assimilation for Robust UQ Within Agent-Based Simulation on HPC Systems

Agent-based simulation provides a powerful tool for in silico system modeling. However, these simulations do not provide built-in methods for uncertainty quantification (UQ). Within these types of models a typical approach to UQ is to run multiple realizations of the model then compute aggregate statistics. This approach is limited due to the compute time required for a solution. When faced with an emerging biothreat, public health decisions need to be made quickly and solutions for integrating near real-time data with analytic tools are needed. We propose an integrated Bayesian UQ framework for agent-based models based on sequential Monte Carlo sampling. Given streaming or static data about the evolution of an emerging pathogen this Bayesian framework provides a distribution over the parameters governing the spread of a disease through a population. These estimates of the spread of a disease may be provided to public health agencies seeking to abate the spread. By coupling agent-based simulations with Bayesian modeling in a data assimilation, our proposed framework provides a powerful tool for modeling dynamical systems in silico. We propose a method which reduces model error and provides a range of realistic possible outcomes. Moreover, our method addresses two primary limitations of ABMs: the lack of UQ and an inability to assimilate data. Our proposed framework combines the flexibility of an agent-based model with UQ provided by the Bayesian paradigm in a workflow which scales well to HPC systems. We provide algorithmic details and results on a simulated outbreak with both static and streaming data.

Spannaus, Adam [ORNL] (ORCID:0000000225213657)↗
DOE OSTI2025

Foveal vision reduces neural resources in agent-based game learning

Efficient processing of information is crucial for the optimization of neural resources in both biological and artificial visual systems. In this paper, we study the efficiency that may be obtained via the use of a fovea. Using biologically-motivated agents, we study visual information processing, learning, and decision making in a controlled artificial environment, namely the Atari Pong video game. We compare the resources necessary to play Pong between agents with and without a fovea. Our study shows that a fovea can significantly reduce the neural resources, in the form of number of neurons, number of synapses, and number of computations, while at the same time maintaining performance at playing Pong. To our knowledge, this is the first study in which an agent must simultaneously optimize its visual system, along with its decision making and action generation capabilities. That is, the visual system is integral to a complete agent.

60 APPLIED LIFE SCIENCES↗
NASA NTRS1975

Development of high temperature resistant graphite fiber coupling agents

Surface treatments were investigated as potential coupling agents to improve the elevated temperature shear strength retention of polyimide/graphite and polyphenylquinoxaline/graphite composites. The potential coupling agents were evaluated by fiber strand tensile tests, fiber and composite weight losses at 533 and 588K, and by interlaminar shear strength retention at 533 and 588K. The two surface treatments selected for more extensive evaluation were a coating of Ventromer T-1, a complex organometallic reaction product of titanium tetrachloride and trimethyl borate, and a polyphenylquinoxaline (PPQ) sizing which was pyrolyzed in nitrogen to form a carbonaceous layer on the fiber. Pyrolyzed polyphenylquinoxaline is a satisfactory coupling agent for polyimide/Thornel 300 graphite fiber composites. During 1000 hours aging at 588K such composites lose a little over half their transverse tensile strength, and suffer a slight loss in flexural modulus. No degradation of flexural strength or interlaminar shear strength occured during 1000 hours aging at 588K. None of the coupling agents examined had a markedly beneficial effect with polyphenylquinoxaline composites.

Griffin, R. N.↗
NASA NTRS1977

Spacecraft disinfectant/cleansing agent development

The sanitation agent container, which was selected in a trade off study, employs two chambers, a rigid outer container and an inner flexible bladder. The bladder contains the sanitation agent formulation and its release is controlled by a manually operated valve. The outer container holds a high pressure vapor. There is no void in the bladder which makes the package operation independent of orientation and therefore usable in zero gravity. Foam is developed by a low boiling point fluid or dissolved in the product. When the product is dispensed at atmospheric presure, the evolved gas or vapor whips up a goam in the valve. The sanitation agents were initially formulated with freons which produces an excellent foam. However freon is incompatible with the life support system and was replaced with carbon dioxide dissolved at high pressure. The CO2 system may limit high temperature exposure to prevent leakage or package distortion. The sanitation agents have been shown to be effective in cleaning soils from personnel and material.

Abbate, M.↗
NASA NTRS1994

Agent oriented programming

The goal of our research is a methodology for creating robust software in distributed and dynamic environments. The approach taken is to endow software objects with explicit information about one another, to have them interact through a commitment mechanism, and to equip them with a speech-acty communication language. System-level applications include software interoperation and compositionality. A government application of specific interest is an infrastructure for coordination among multiple planners. Daily activity applications include personal software assistants, such as programmable email, scheduling, and new group agents. Research topics include definition of mental state of agents, design of agent languages as well as interpreters for those languages, and mechanisms for coordination within agent societies such as artificial social laws and conventions.

Shoham, Yoav↗
NASA NTRS1998

Research and Development for an Operational Information Ecology: The User-System Interface Agent Project

The User System Interface Agent (USIA) is a special type of software agent which acts as the "middle man" between a human user and an information processing environment. USIA consists of a group of cooperating agents which are responsible for assisting users in obtaining information processing services intuitively and efficiently. Some of the main features of USIA include: (1) multiple interaction modes and (2) user-specific and stereotype modeling and adaptation. This prototype system provides us with a development platform towards the realization of an operational information ecology. In the first phase of this project we focus on the design and implementation of prototype system of the User-System Interface Agent (USIA). The second face of USIA allows user interaction via a restricted query language as well as through a taxonomy of windows. In third phase the USIA system architecture was revised.

Srivastava, Sadanand↗
NASA NTRS2000

Emergent Aerospace Designs Using Negotiating Autonomous Agents

This paper presents a distributed design methodology where designs emerge as a result of the negotiations between different stake holders in the process, such as cost, performance, reliability, etc. The proposed methodology uses autonomous agents to represent design decision makers. Each agent influences specific design parameters in order to maximize their utility. Since the design parameters depend on the aggregate demand of all the agents in the system, design agents need to negotiate with others in the market economy in order to reach an acceptable utility value. This paper addresses several interesting research issues related to distributed design architectures. First, we present a flexible framework which facilitates decomposition of the design problem. Second, we present overview of a market mechanism for generating acceptable design configurations. Finally, we integrate learning mechanisms in the design process to reduce the computational overhead.

Deshmukh, Abhijit↗
NASA NTRS2000

Multi-Agent Diagnosis and Control of an Air Revitalization System for Life Support in Space

An architecture of interoperating agents has been developed to provide control and fault management for advanced life support systems in space. In this adjustable autonomy architecture, software agents coordinate with human agents and provide support in novel fault management situations. This architecture combines the Livingstone model-based mode identification and reconfiguration (MIR) system with the 3T architecture for autonomous flexible command and control. The MIR software agent performs model-based state identification and diagnosis. MIR identifies novel recovery configurations and the set of commands required for the recovery. The AZT procedural executive and the human operator use the diagnoses and recovery recommendations, and provide command sequencing. User interface extensions have been developed to support human monitoring of both AZT and MIR data and activities. This architecture has been demonstrated performing control and fault management for an oxygen production system for air revitalization in space. The software operates in a dynamic simulation testbed.

Malin, Jane T.↗
NASA NTRS1998

Collaborative Information Agents on the World Wide Web

In this paper, we present DIAMS, a system of distributed, collaborative information agents which help users access, collect, organize, and exchange information on the World Wide Web. Personal agents provide their owners dynamic displays of well organized information collections, as well as friendly information management utilities. Personal agents exchange information with one another. They also work with other types of information agents such as matchmakers and knowledge experts to facilitate collaboration and communication.

Chen, James R.↗
NASA NTRS2001

Designing Agent Collectives For Systems With Markovian Dynamics

The "Collective Intelligence" (COIN) framework concerns the design of collectives of agents so that as those agents strive to maximize their individual utility functions, their interaction causes a provided "world" utility function concerning the entire collective to be also maximized. Here we show how to extend that framework to scenarios having Markovian dynamics when no re-evolution of the system from counter-factual initial conditions (an often expensive calculation) is permitted. Our approach transforms the (time-extended) argument of each agent's utility function before evaluating that function. This transformation has benefits in scenarios not involving Markovian dynamics, in particular scenarios where not all of the arguments of an agent's utility function are observable. We investigate this transformation in simulations involving both linear and quadratic (nonlinear) dynamics. In addition, we find that a certain subset of these transformations, which result in utilities that have low "opacity (analogous to having high signal to noise) but are not "factored" (analogous to not being incentive compatible), reliably improve performance over that arising with factored utilities. We also present a Taylor Series method for the fully general nonlinear case.

Wolpert, David H.↗
NASA NTRS2002

The Design of Collectives of Agents to Control Non-Markovian Systems

The 'Collective Intelligence' (COIN) framework concerns the design of collectives of reinforcement-learning agents such that their interaction causes a provided 'world' utility function concerning the entire collective to be maximized. Previously, we applied that framework to scenarios involving Markovian dynamics where no re-evolution of the system from counter-factual initial conditions (an often expensive calculation) is permitted. This approach sets the individual utility function of each agent to be both aligned with the world utility, and at the same time, easy for the associated agents to optimize. Here we extend that approach to systems involving non-Markovian dynamics. In computer simulations, we compare our techniques with each other and with conventional-'team games'. We show whereas in team games performance often degrades badly with time, it steadily improves when our techniques are used. We also investigate situations where the system's dimensionality is effectively reduced. We show that this leads to difficulties in the agents' ability to learn. The implication is that 'learning' is a property only of high-enough dimensional systems.

Lawson, John W.↗
NASA NTRS2001

Design and Control of Large Collections of Learning Agents

The intelligent control of multiple autonomous agents is an important yet difficult task. Previous methods used to address this problem have proved to be either too brittle, too hard to use, or not scalable to large systems. The 'Collective Intelligence' project at NASA/Ames provides an elegant, machine-learning approach to address these problems. This approach mathematically defines some essential properties that a reward system should have to promote coordinated behavior among reinforcement learners. This work has focused on creating additional key properties and algorithms within the mathematics of the Collective Intelligence framework. One of the additions will allow agents to learn more quickly, in a more coordinated manner. The other will let agents learn with less knowledge of their environment. These additions will allow the framework to be applied more easily, to a much larger domain of multi-agent problems.

Agogino, Adrian↗