Search NASA⌕ Search

SEARCH · Search NASA

Results for “agent architectures”

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 163 records · Page 9
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

El Agente: An autonomous agent for quantum chemistry

Computational chemistry tools are widely used to study the behavior of chemical phenomena. Yet, the complexity of these tools can make them inaccessible to non-specialists and challenging even for experts. In this work, we introduce El Agente Q, an LLM-based multi-agent system that dynamically generates and executes quantum chemistry workflows from natural language user prompts. The system is built on a novel cognitive architecture featuring a hierarchical memory framework that enables flexible task decomposition, adaptive tool selection, post-analysis, and autonomous file handling and submission. El Agente Q is benchmarked on six university-level course exercises and two case studies, demonstrating robust problem-solving performance (averaging >87% task success) and adaptive error handling through in situ debugging. It also supports longer-term, multi-step task execution for more complex workflows, while maintaining transparency through detailed action trace logs. Together, these capabilities lay the foundation for increasingly autonomous and accessible quantum chemistry.

agentic systems↗
DOE OSTI2026

ToPolyAgent: AI agents for coarse-grained bead-spring topological polymer simulations

We introduce ToPolyAgent, a multi-agent AI framework for performing coarse-grained molecular dynamics (MD) simulations of topological polymers through natural language instructions. By integrating large language models (LLMs) with domain-specific computational tools, ToPolyAgent supports both interactive and autonomous simulation workflows across diverse polymer architectures, including linear, ring, brush, and star polymers, as well as dendrimers. The system consists of four LLM-powered agents: a Config Agent for generating initial polymer–solvent configurations, a Simulation Agent for executing LAMMPS-based MD simulations and conformational analyses, a Report Agent for compiling markdown reports, and a Workflow Agent for streamlined autonomous operations. Interactive mode incorporates user feedback loops for iterative refinements, while autonomous mode enables end-to-end task execution from detailed prompts. We demonstrate ToPolyAgent's versatility through case studies involving diverse polymer architectures under varying solvent conditions, thermostats, and simulation lengths. Furthermore, we highlight its potential as a research assistant by directing it to investigate the effect of interaction parameters on the linear polymer conformation, and the influence of grafting density on the persistence length of the brush polymer. By coupling natural language interfaces with rigorous simulation tools, ToPolyAgent lowers barriers to complex computational workflows and advances AI-driven materials discovery in polymer science. It lays the foundation for autonomous and extensible multi-agent scientific research ecosystems.

Ding, Lijie [Oak Ridge National Laboratory (ORNL),↗
NASA NTRS1989

A development framework for distributed artificial intelligence

The authors describe distributed artificial intelligence (DAI) applications in which multiple organizations of agents solve multiple domain problems. They then describe work in progress on a DAI system development environment, called SOCIAL, which consists of three primary language-based components. The Knowledge Object Language defines models of knowledge representation and reasoning. The metaCourier language supplies the underlying functionality for interprocess communication and control access across heterogeneous computing environments. The metaAgents language defines models for agent organization coordination, control, and resource management. Application agents and agent organizations will be constructed by combining metaAgents and metaCourier building blocks with task-specific functionality such as diagnostic or planning reasoning. This architecture hides implementation details of communications, control, and integration in distributed processing environments, enabling application developers to concentrate on the design and functionality of the intelligent agents and agent networks themselves.

Adler, Richard M.↗
NASA NTRSDate not supplied

A Distributed Simulation-to-Flight Framework to Support Investigating Trust/Trustworthiness in Multi-Agent Systems

As autonomous systems continue to grow both in use and complexity, the necessity for robust and extensible simulation-to-flight frameworks is paramount for establishing an effective architecture for autonomous systems. Hardware test flights are time-consuming and cost prohibitive during early system design and development. Simulation environments can be useful tools to accelerate algorithm development and testing. However, transitions from simulation to flight (sim-to-flight) can be challenging, unless systems are designed with this transition in mind and with the necessary capabilities built into the architecture and framework. One of the objectives of Autonomy Teaming and TRAjectories for Complex Trusted Operational Reliability (ATTRACTOR) was to design and develop a distributed mixed-reality simulation environment to begin establishing a basis for certification of autonomous systems via research into trust and trustworthiness. ATTRACTOR’s objective was to construct computational concepts of trustworthiness and justifiable trust in multi-agent autonomous teams, to inform future certification of safety-critical and time-critical autonomous systems in aviation. In this paper, we present an autonomous systems architecture and development framework paired with a persistent distributed modeling and simulation (ModSim) environment for test and evaluation of autonomous systems. They were designed under ATTRACTOR in order to measure and establish trustworthiness and trust in single-and multi-agent human-machine systems whether these machines are fixed-wing general aviation, rotary-wing Unmanned Aerial Vehicles (UAVs), ground rovers, or even spacecraft. The Autonomous Entity Operational Network (AEON) framework enables autonomous system development with an easily extensible collection of libraries and plug-n-play nodes facilitated by the Data Distribution Service (DDS) communication protocol standard. The Baseline Environment for Autonomous Modeling (BEAM) simulation environment is a distributed mixed-reality Unity™-based environment built around the same DDS communication paradigm allowing for easy integration with AEON-based autonomous applications, enabling sim-to-flight with minimal configuration changes. Using AEON and BEAM, source code that runs in simulation ports directly to hardware and has successfully flown in the National Airspace System (NAS) at NASA LaRC many times over the lifetime of ATTRACTOR.

Benjamin N Kelley↗
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↗
NASA NTRS1990

Prototyping a large-scale distributed system for the Great Observatories era - NASA Astrophysics Data System (ADS)

The NASA Astrophysics Data System (ADS) is a distributed information system intended to support research in the Great Observatories era, to simplify access to data, and to enable simultaneous analyses of multispectral data sets. Here, the user agent and interface, its functions, and system components are examined, and the system architecture and infrastructure is addressed. The present status of the system and related future activities are examined.

Shames, Peter↗
NASA NTRS2004

An Architecture for Controlling Multiple Robots

The Control Architecture for Multirobot Outpost (CAMPOUT) is a distributed-control architecture for coordinating the activities of multiple robots. In the CAMPOUT, multiple-agent activities and sensor-based controls are derived as group compositions and involve coordination of more basic controllers denoted, for present purposes, as behaviors. The CAMPOUT provides basic mechanistic concepts for representation and execution of distributed group activities. One considers a network of nodes that comprise behaviors (self-contained controllers) augmented with hyper-links, which are used to exchange information between the nodes to achieve coordinated activities. Group behavior is guided by a scripted plan, which encodes a conditional sequence of single-agent activities. Thus, higher-level functionality is composed by coordination of more basic behaviors under the downward task decomposition of a multi-agent planner

Aghazarian, Hrand↗
NASA NTRS1991

Future applications of artificial intelligence to Mission Control Centers

Future applications of artificial intelligence to Mission Control Centers are presented in the form of the viewgraphs. The following subject areas are covered: basic objectives of the NASA-wide AI program; inhouse research program; constraint-based scheduling; learning and performance improvement for scheduling; GEMPLAN multi-agent planner; planning, scheduling, and control; Bayesian learning; efficient learning algorithms; ICARUS (an integrated architecture for learning); design knowledge acquisition and retention; computer-integrated documentation; and some speculation on future applications.

Friedland, Peter↗
DOE OSTI2025

Agentic AI vs ML-Based Autotuning: A Comparative Study for Loop Reordering Optimization

High Performance Computing (HPC) applications rely heavily on code optimizations to achieve good performance on modern CPU and GPU architectures. Traditional Machine Learning auto-tuning approaches have demonstrated success in exploring high-dimensional spaces, but they often require expensive compile-run evaluations and lack adaptability for large HPC applications. The recent advances in Large Language Models (LLMs) and Agentic AI systems raise intriguing questions about the potential of these approaches to address specific optimization methodologies. This work aims to answer an essential question for the HPC community: “How Agentic AI Systems Compare to Traditional ML Autotuning Techniques?” To address this question, we present a comparative analysis between a traditional ML-based optimization approach and an Agentic AI system, evaluating their respective capabilities and limitations for loop-level optimization. In addition, we introduced a new Agentic AI system named LoopGen-AI using three different Large Language Models: GPT-4.1, Claude 4.0, and Gemini 2.5. A key finding is that LoopGen-AI achieves competitive per-formance with only a few program runs, the reasoning logs from the agents revealed that their decisions rely heavily on the combination of semantic understanding of the target kernel with dynamic feedback from the environment, highlighting a promising new dimension in performance tuning. In contrast, ML-based autotuners focus on statistical exploration, and require orders of magnitude more runs to reach peak performance. Additionally, our analysis shows that prompt engineering, particularly using Persona + Context Manager patterns, significantly impacts the effectiveness of Agentic AI. Our results indicate that while Agentic AI systems are not yet a complete replacement for ML-based autotuners, it can effectively complement traditional methods.

Rosas, Miguel Romero↗
NASA NTRS2000

Autonomy Architectures for a Constellation of Spacecraft

Until the past few years, missions typically involved fairly large expensive spacecraft. Such missions have primarily favored using older proven technologies over more recently developed ones, and humans controlled spacecraft by manually generating detailed command sequences with low-level tools and then transmitting the sequences for subsequent execution on a spacecraft controller. This approach toward controlling a spacecraft has worked spectacularly on previous missions, but it has limitations deriving from communications restrictions - scheduling time to communicate with a particular spacecraft involves competing with other projects due to the limited number of deep space network antennae. This implies that a spacecraft can spend a long time just waiting whenever a command sequence fails. This is one reason why the New Millennium program has an objective to migrate parts of mission control tasks onboard a spacecraft to reduce wait time by making spacecraft more robust. The migrated software is called a "remote agent" and has 4 components: a mission manager to generate the high level goals, a planner/scheduler to turn goals into activities while reasoning about future expected situations, an executive/diagnostics engine to initiate and maintain activities while interpreting sensed events by reasoning about past and present situations, and a conventional real-time subsystem to interface with the spacecraft to implement an activity's primitive actions. In addition to needing remote planning and execution for isolated spacecraft, a trend toward multiple-spacecraft missions points to the need for remote distributed planning and execution. The past few years have seen missions with growing numbers of probes. Pathfinder has its rover (Sojourner), Cassini has its lander (Huygens), and the New Millenium Deep Space 3 (DS3) proposal involves a constellation of 3 spacecraft for interferometric mapping. This trend is expected to continue to progressively larger fleets. For example, one mission proposed to succeed DS3 would have 18 spacecraft flying in formation in order to detect earth-sized planets orbiting other stars. A proposed magnetospheric constellation would involve 5 to 500 spacecraft in Earth orbit to measure global phenomena within the magnetosphere. This work describes and compares three autonomy architectures for a system that continuously plans to control a fleet of spacecraft using collective mission goals instead of goals or command sequences for each spacecraft. A fleet of self-commanding spacecraft would autonomously coordinate itself to satisfy high level science and engineering goals in a changing partially-understood environment making feasible the operation of tens or even a hundred spacecraft (such as for interferometry or plasma physics missions). The easiest way to adapt autonomous spacecraft research to controlling constellations involves treating the constellation as a single spacecraft. Here one spacecraft directly controls the others as if they were connected. The controlling "master" spacecraft performs all autonomy reasoning, and the slaves only have real-time subsystems to execute the master's commands and transmit local telemetry/observations. The executive/diagnostics module starts actions and the master's real-time subsystem controls the action either locally or remotely through a slave. While the master/slave approach benefits from conceptual simplicity, it relies on an assumption that the master spacecraft's executive can continuously monitor the slaves' real-time subsystems, and this relies on high-bandwidth highly-reliable communications. Since unintended results occur fairly rarely, one way to relax the bandwidth requirements involves only monitoring unexpected events in spacecraft. Unfortunately, this disables the ability to monitor for unexpected events between spacecraft and leads to a host of coordination problems among the slaves. Also, failures in the communications system can result in losing slaves. The other two architectures improve robustness while reducing communications by progressively distributing more of the other three remote agent components across the constellation. In a teamwork architecture, all spacecraft have executives and real-time subsystems - only the leader has the planner/scheduler and mission manager. Finally, distributing all remote agent components leads to a peer-to-peer approach toward constellation control.

Barrett, Anthony↗
NASA NTRS1989

Integrating planning, execution, and learning

To achieve the goal of building an autonomous agent, the usually disjoint capabilities of planning, execution, and learning must be used together. An architecture, called MAX, within which cognitive capabilities can be purposefully and intelligently integrated is described. The architecture supports the codification of capabilities as explicit knowledge that can be reasoned about. In addition, specific problem solving, learning, and integration knowledge is developed.

Kuokka, Daniel R.↗
NASA NTRS2019

Collaborative Seamless Manager for Airspace Resources and Traffic

In today's NAS, airlines conduct pre-departure flight planning with limited information about traffic congestion. Then, as events evolve (pre-departure, on the surface, or inflight) and are impacted by congestion, limited options for changing flight plans are offered to the airlines, and, in some cases, flight plans are changed by air traffic managers on behalf of the airlines. For the airlines, this produces flight plan uncertainty and possible disruption to their business plans. The Collaborative Seamless Manager of Airspace Resources and Traffic (CSMART) is a tool being developed for the 2045 Next Gen System that will enhance the airlines' ability to flight plan, both pre-departure and during flight. CSMART achieves this, using the UTM architecture approach, by connecting via the internet airlines with other airlines and airlines with FAA agents. Flight plans, including digital, discrete planned trajectories with tolerances, are passed through the connection. Planned trajectories are used to create probabilistic predictions of when and where congestion will occur. Pre-departure, airline agents will use the predictions to collaboratively and seamlessly create flight plans that avoid congestion or go through it, depending on business objectives. In cases, where demand exceeds capacity and priorities need to be set, airline agents will have the ability to negotiate with each other to set them. Moreover, if flights are impacted by congestion during flight, CSMART will allow airlines more real-time decision making options for changing flight plans. This seminar presents the general CSMART concept and tool and research needed to develop it.

Windhorst, Robert D.↗
DOE OSTI2026

From natural language to control signals: a conceptual framework for semantic channel finding in complex experimental infrastructure

Modern experimental platforms such as particle accelerators, fusion devices, telescopes, and industrial process control systems expose tens to hundreds of thousands of control and diagnostic channels, accumulated over decades of hardware evolution. Operators and AI systems alike depend on informal expert knowledge, inconsistent naming conventions, and scattered documentation to locate the signals required for monitoring, troubleshooting, and automated control, creating a persistent bottleneck for reliability, scalability, and emerging language-model-driven interfaces. We formalize semantic channel finding, the task of mapping natural-language intent to concrete control-system signals, as a general problem in complex experimental infrastructure, and introduce a four-paradigm conceptual framework to guide architecture selection based on facility-specific data regimes. The paradigms span (i) direct in-context lookup over small, curated channel dictionaries, (ii) constrained hierarchical navigation through structured trees, (iii) interactive agent exploration using iterative reasoning and tool-based database queries, and (iv) ontology-grounded semantic search that decouples channel meaning from facility-specific naming conventions. We demonstrate the practical feasibility of each paradigm through proof-of-concept implementations at four operational facilities spanning two orders of magnitude in scale: from compact free-electron lasers to large synchrotron light sources, operating under diverse control-system architectures ranging from clean hierarchical naming schemes to legacy environments with decades of heterogeneous conventions. Where evaluated against expert-curated operational queries, these instantiations achieve 90%–97% accuracy, validating the framework’s applicability across real-world deployment scenarios. To accelerate adoption across the broader scientific and industrial control-system community, we release open-source, plug-and-play implementations of all three interactive paradigms-direct lookup, hierarchical navigation, and middle-layer exploration-within the Osprey framework, together with tools for channel database generation, interactive testing, and minimal-configuration deployment. This work establishes semantic channel finding as a foundational capability for human-centric and agentic AI interfaces at large-scale facilities, providing both a systematic framework for architecture design and practical resources to enable adoption without building custom infrastructure from scratch.

channel finding↗
NASA NTRS2013

The Regolith Biters: A Divide-And-Conquer Architecture for Sample-Return Missions

The collective interaction of simple systems can be leveraged to attain complex goals. Based on this principle, we envision space system architectures where the core functional components are decoupled, autonomous, and cooperative. We aim to pursue this vision in the context of small-body sample-return missions. After all, no experimental study sheds more light into our understanding of the origin and evolution of the Solar System than the analysis of samples from asteroids and comets. We also believe that their study is important from a strategic perspective: meteorite impacts pose a direct and credible threat to life on Earth, and the development of contingency small-body deflection missions presupposes some knowledge of the target body. The current architectural paradigm for sample-return missions is centered around a design where spacecraft and sampling device are merged into a single, complex system. We argue that this monolithic approach couples the navigation and sample-collection problems, making both more difficult. In contrast, we propose a decoupled system based on the coordinated interaction between a spacecraft and a collective of small, simple devices - the Regolith Biters (RBs). A spacecraft carrying a number of RBs would travel to the vicinity of a small body. From a favorable vantage point, and while remaining within a safe distance in a non-colliding trajectory, it would release the RBs towards the target body. Upon encountering the body, they would bite the regolith (thus retaining a sample), and eject back to orbit. The spacecraft, being endowed with appropriate navigation and tracking capabilities, would rendezvous with and collect those RBs within its reach, and bring them back to Earth. Separating the navigation and sampling concerns removes the need for proximity operations with the small body-the stage in current architectures that carries the most challenges and risks. Eliminating the need for proximity operations brings back to the discussion the exploration of exciting prospects, like highly active comets, fast-rotating bodies, and binary systems. Distributing the sampling problem among a collective of agents provides the opportunity to sample multiple regions in a single mission. It also provides robustness to various environmental conditions, and may enable the distributed, in situ characterization of the body. In the search for reliability, current architectures rely on complexity: an elaborate system should succeed at once. We rely on numbers: a given agent may fail at any stage, but success is attained by the collective.

Asteroids↗
NASA NTRS2004

Facilitating the Specification Capture and Transformation Process in the Development of Multi-Agent Systems

To support the development of flexible and reusable MAS, we have built a framework designated MAS-CF. MAS-CF is a component framework that implements a layered architecture based on contextual composition. Interaction rules, controlled by architecture mechanisms, ensure very low coupling, making possible the sharing of distributed services in a transparent, dynamic and independent way. These properties propitiate large-scale reuse, since organizational abstractions can be reused and propagated to all instances created from a framework. The objective is to reduce complexity and development time of multi-agent systems through the reuse of generic organizational abstractions.

Filho, Aluzio Haendehen↗
NASA NTRS1996

An Open Computing Infrastructure that Facilitates Integrated Product and Process Development from a Decision-Based Perspective

Computer applications for design have evolved rapidly over the past several decades, and significant payoffs are being achieved by organizations through reductions in design cycle times. These applications are overwhelmed by the requirements imposed during complex, open engineering systems design. Organizations are faced with a number of different methodologies, numerous legacy disciplinary tools, and a very large amount of data. Yet they are also faced with few interdisciplinary tools for design collaboration or methods for achieving the revolutionary product designs required to maintain a competitive advantage in the future. These organizations are looking for a software infrastructure that integrates current corporate design practices with newer simulation and solution techniques. Such an infrastructure must be robust to changes in both corporate needs and enabling technologies. In addition, this infrastructure must be user-friendly, modular and scalable. This need is the motivation for the research described in this dissertation. The research is focused on the development of an open computing infrastructure that facilitates product and process design. In addition, this research explicitly deals with human interactions during design through a model that focuses on the role of a designer as that of decision-maker. The research perspective here is taken from that of design as a discipline with a focus on Decision-Based Design, Theory of Languages, Information Science, and Integration Technology. Given this background, a Model of IPPD is developed and implemented along the lines of a traditional experimental procedure: with the steps of establishing context, formalizing a theory, building an apparatus, conducting an experiment, reviewing results, and providing recommendations. Based on this Model, Design Processes and Specification can be explored in a structured and implementable architecture. An architecture for exploring design called DREAMS (Developing Robust Engineering Analysis Models and Specifications) has been developed which supports the activities of both meta-design and actual design execution. This is accomplished through a systematic process which is comprised of the stages of Formulation, Translation, and Evaluation. During this process, elements from a Design Specification are integrated into Design Processes. In addition, a software infrastructure was developed and is called IMAGE (Intelligent Multidisciplinary Aircraft Generation Environment). This represents a virtual apparatus in the Design Experiment conducted in this research. IMAGE is an innovative architecture because it explicitly supports design-related activities. This is accomplished through a GUI driven and Agent-based implementation of DREAMS. A HSCT design has been adopted from the Framework for Interdisciplinary Design Optimization (FIDO) and is implemented in IMAGE. This problem shows how Design Processes and Specification interact in a design system. In addition, the problem utilizes two different solution models concurrently: optimal and satisfying. The satisfying model allows for more design flexibility and allows a designer to maintain design freedom. As a result of following this experimental procedure, this infrastructure is an open system that it is robust to changes in both corporate needs and computer technologies. The development of this infrastructure leads to a number of significant intellectual contributions: 1) A new approach to implementing IPPD with the aid of a computer; 2) A formal Design Experiment; 3) A combined Process and Specification architecture that is language-based; 4) An infrastructure for exploring design; 5) An integration strategy for implementing computer resources; and 6) A seamless modeling language. The need for these contributions is emphasized by the demand by industry and government agencies for the development of these technologies.

Hale, Mark A.↗
NASA NTRS2020

Detection and Mitigation of Transient Instabilities in Multi-Agent Systems and Swarms

We first introduce the novel concept of transient instabilities in multi-agent systems and swarms, i.e., a small disturbance leads to increasing-amplitude oscillations throughout the swarm, which results in a large number of inter-agent collisions. This instability is dominant in the transient phase of the system and it does not appear in the steady-state behavior of the system, as each agent uses Lyapunov-stable feedback control laws. We present a rigorous definition of transient instability in swarms, and discuss its key properties. We also present a sufficient condition to check if a swarm will be transient stable. We study the behaviour of different control laws under this condition. We also show how transient instability phenomenon could impact the dynamics of deployable structures. Next, we present a novel control architecture that augments the baseline formation maintenance controller to mitigate transient instabilities. At its heart, the proposed architecture consists of a projection operator based estimator disguised as a reference model that generates collision-free trajectories for the agents to follow. We present numerical simulation results to demonstrate the effectiveness of our proposed approaches.

Quadrelli, Marco B.↗