Toward a Multi-Agent System Architecture for Insight & Cybersecurity in Cyber-Physical Networks (Presentation).
Abstract not provided.
Stout, William M.S.↗
SEARCH · Engineering Papers
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.
Collected notes from the Benchmarks and Metrics Workshop
In recent years there has been a proliferation of proposals in the artificial intelligence (AI) literature for integrated agent architectures. Each architecture offers an approach to the general problem of constructing an integrated agent. Unfortunately, the ways in which one architecture might be considered better than another are not always clear. There has been a growing realization that many of the positive and negative aspects of an architecture become apparent only when experimental evaluation is performed and that to progress as a discipline, we must develop rigorous experimental methods. In addition to the intrinsic intellectual interest of experimentation, rigorous performance evaluation of systems is also a crucial practical concern to our research sponsors. DARPA, NASA, and AFOSR (among others) are actively searching for better ways of experimentally evaluating alternative approaches to building intelligent agents. One tool for experimental evaluation involves testing systems on benchmark tasks in order to assess their relative performance. As part of a joint DARPA and NASA funded project, NASA-Ames and Teleos Research are carrying out a research effort to establish a set of benchmark tasks and evaluation metrics by which the performance of agent architectures may be determined. As part of this project, we held a workshop on Benchmarks and Metrics at the NASA Ames Research Center on June 25, 1990. The objective of the workshop was to foster early discussion on this important topic. We did not achieve a consensus, nor did we expect to. Collected here is some of the information that was exchanged at the workshop. Given here is an outline of the workshop, a list of the participants, notes taken on the white-board during open discussions, position papers/notes from some participants, and copies of slides used in the presentations.
Drummond, Mark E.↗
AutoLabs: cognitive multi-agent systems with self-correction for autonomous chemical experimentation
The automation of chemical research through self-driving laboratories (SDLs) promises to accelerate scientific discovery, yet the reliability and granular performance of the underlying AI agents remain critical, under-examined challenges. In this work, we introduce AutoLabs, a self-correcting, multi-agent architecture designed to autonomously translate natural-language instructions into executable protocols for a high-throughput liquid handler. The system engages users in dialogue, decomposes experimental goals into discrete tasks for specialized agents, performs tool-assisted stoichiometric calculations, and iteratively self-corrects its output before generating a hardware-ready file. We present a comprehensive evaluation framework featuring five benchmark experiments of increasing complexity, from simple sample preparation to multi-plate timed syntheses. Through a systematic ablation study of 20 agent configurations, we assess the impact of reasoning capacity, architectural design (single- vs. multi-agent), tool use, and self-correction mechanisms. Our results demonstrate that agent reasoning capacity is the most critical factor for success, reducing quantitative errors in chemical amounts (nRMSE) by over 85% in complex tasks. When combined with a multi-agent architecture and iterative self-correction, AutoLabs approaches expert-authored reference procedures on the benchmark (F1-score > 0.89) on challenging multi-plate syntheses. These findings establish a clear blueprint for developing robust and trustworthy AI partners for autonomous laboratories, highlighting the synergistic effects of modular design, advanced reasoning, and self-correction to ensure both performance and reliability in high-stakes scientific applications. Code: https://github.com/pnnl/autolabs
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
Implementation and Evaluation of IEC 61850-based Distributed Control System for Microgrid Applications
This paper presents a resilient, modular and scalable distributed control architecture for microgrid systems which uses distributed agents controlling individual loads, network switches, generators or storage devices to provide intelligent power management and efficient microgrid operation. The communication between the distributed agents is realized by implementing IEC 61850 data models and GOOSE messages. The data models include state representation, measurements at various points, and dispatch requests for reliable operation of microgrid control system. System resiliency is enhanced through implementing distributed agent architecture with no single point of failure.
24 POWER TRANSMISSION AND DISTRIBUTION↗
An Evolvable Multi-Agent Approach to Satellite Telecommunication Systems
This paper presents a model of a satellite communication system using evolving multi-agent architecture.
Evolvable Multi-Agent Satellite Telecommunication ↗
Reusable Autonomy
Currently, spacecraft ground systems have a well defined and somewhat standard architecture and operations concept. Based on domain analysis studies of various control centers conducted over the years it is clear that ground systems have core capabilities and functionality that are common across all ground systems. This observation alone supports the realization of reuse. Additionally, spacecraft ground systems are increasing in their ability to do things autonomously. They are being engineered using advanced expert systems technology to provide automated support for operators. A clearer understanding of the possible roles of agent technology is advancing the prospects of greater autonomy for these systems. Many of their functional and management tasks are or could be supported by applied agent technology, the dynamics of the ground system's infrastructure could be monitored by agents, there are intelligent agent-based approaches to user-interfaces, etc. The premise of this paper is that the concepts associated with software reuse, applicable in consideration of classically-engineered ground systems, can be updated to address their application in highly agent-based realizations of future ground systems. As a somewhat simplified example consider the following situation, involving human agents in a ground system context. Let Group A of controllers be working on Mission X. They are responsible for the command, control and health and safety of the Mission X spacecraft. Let us suppose that mission X successfully completes it mission and is turned off. Group A could be dispersed or perhaps move to another Mission Y. In this case there would be reuse of the human agents from Mission X to Mission Y. The Group A agents perform their well-understood functions in a somewhat but related context. There will be a learning or familiarization process that the group A agents go through to make the new context, determined by the new Mission Y, understood. This simplified scenario highlights some of the major issues that need to be addressed when considering the situation where Group A is composed of software-based agents (not their human counterparts) and they migrate from one mission support system to another. This paper will address: - definition of an agent architecture appropriate to support reuse; - identification of non-mission-specific agent capabilities required; - appropriate knowledge representation schemes for mission-specific knowledge; - agent interface with mission-specific knowledge (a type of Learning); development of a fully-operational group of cooperative software agents for ground system support; architecture and operation of a repository of reusable agents that could be the source of intelligent components for realizing an autonomous (or nearly autonomous) agent-based ground system, and an agent-based approach to repository management and operation (an intelligent interface for human use of the repository in a ground-system development activity).
Truszkowski, Walt↗
Architecture for Adaptive Intelligent Systems
We identify a class of niches to be occupied by 'adaptive intelligent systems (AISs)'. In contrast with niches occupied by typical AI agents, AIS niches present situations that vary dynamically along several key dimensions: different combinations of required tasks, different configurations of available resources, contextual conditions ranging from benign to stressful, and different performance criteria. We present a small class hierarchy of AIS niches that exhibit these dimensions of variability and describe a particular AIS niche, ICU (intensive care unit) patient monitoring, which we use for illustration throughout the paper. We have designed and implemented an agent architecture that supports all of different kinds of adaptation by exploiting a single underlying theoretical concept: An agent dynamically constructs explicit control plans to guide its choices among situation-triggered behaviors. We illustrate the architecture and its support for adaptation with examples from Guardian, an experimental agent for ICU monitoring.
ACTIVE CONTROL↗
Space/ground systems as cooperating agents
Within NASA and the European Space Agency (ESA) it is agreed that autonomy is an important goal for the design of future spacecraft and that this requires on-board artificial intelligence. NASA emphasizes deep space and planetary rover missions, while ESA considers on-board autonomy as an enabling technology for missions that must cope with imperfect communications. ESA's attention is on the space/ground system. A major issue is the optimal distribution of intelligent functions within the space/ground system. This paper describes the multi-agent architecture for space/ground systems (MAASGS) which would enable this issue to be investigated. A MAASGS agent may model a complete spacecraft, a spacecraft subsystem or payload, a ground segment, a spacecraft control system, a human operator, or an environment. The MAASGS architecture has evolved through a series of prototypes. The paper recommends that the MAASGS architecture should be implemented in the operational Dutch Utilization Center.
Grant, T. J.↗
Advantages of Brahms for Specifying and Implementing a Multiagent Human-Robotic Exploration System
We have developed a model-based, distributed architecture that integrates diverse components in a system designed for lunar and planetary surface operations: an astronaut's space suit, cameras, all-terrain vehicles, robotic assistant, crew in a local habitat, and mission support team. Software processes ('agents') implemented in the Brahms language, run on multiple, mobile platforms. These mobile agents interpret and transform available data to help people and robotic systems coordinate their actions to make operations more safe and efficient. The Brahms-based mobile agent architecture (MAA) uses a novel combination of agent types so the software agents may understand and facilitate communications between people and between system components. A state-of-the-art spoken dialogue interface is integrated with Brahms models, supporting a speech-driven field observation record and rover command system. An important aspect of the methodology involves first simulating the entire system in Brahms, then configuring the agents into a runtime system Thus, Brahms provides a language, engine, and system builder's toolkit for specifying and implementing multiagent systems.
Clancey, William J.↗
The Impact of Autonomous Systems Technology on JPL Mission Software
This paper discusses the following topics: (1) Autonomy for Future Missions- Mars Outposts, Titan Aerobot, and Europa Cryobot / Hydrobot; (2) Emergence of Autonomy- Remote Agent Architecture, Closing Loops Onboard, and New Millennium Flight Experiment; and (3) Software Engineering Challenges- Influence of Remote Agent, Scalable Autonomy, Autonomy Software Validation, Analytic Verification Technology, and Autonomy and Software Software Engineering.
Doyle, Richard J.↗
Lessons Learned from Autonomous Sciencecraft Experiment
An Autonomous Science Agent has been flying onboard the Earth Observing One Spacecraft since 2003. This software enables the spacecraft to autonomously detect and responds to science events occurring on the Earth such as volcanoes, flooding, and snow melt. The package includes AI-based software systems that perform science data analysis, deliberative planning, and run-time robust execution. This software is in routine use to fly the EO-l mission. In this paper we briefly review the agent architecture and discuss lessons learned from this multi-year flight effort pertinent to deployment of software agents to critical applications.
Autonomous Sciencecraft Experiment (ASE)↗
CATS-based Agents That Err
This report describes preliminary research on intelligent agents that make errors. Such agents are crucial to the development of novel agent-based techniques for assessing system safety. The agents extend an agent architecture derived from the Crew Activity Tracking System that has been used as the basis for air traffic controller agents. The report first reviews several error taxonomies. Next, it presents an overview of the air traffic controller agents, then details several mechanisms for causing the agents to err in realistic ways. The report presents a performance assessment of the error-generating agents, and identifies directions for further research. The research was supported by the System-Wide Accident Prevention element of the FAA/NASA Aviation Safety Program.
Callantine, Todd J.↗
Topology-Dependent Performance of Free-Space Photonic Quantum Networks Under Noise
Photonic quantum communication enables secure and high-fidelity information transfer beyond classical limits, with direct relevance to emerging quantum networks operating in free-space environments. While physical-layer models of depolarizing noise, Gamma–Gamma turbulence statistics, entanglement swapping, and decoy-state QKD security bounds are individually well established, prior work typically treats these components in isolation or under fixed network assumptions. In this work, we develop a unified topology-aware analytical framework that simultaneously integrates free-space optical link budgets, turbulence-induced visibility degradation, depolarizing qubit noise, multi-hop entanglement cascade dynamics, teleportation fidelity thresholds, CHSH nonlocality certification, and asymptotic decoy-state secret key rate bounds across star, mesh, and ring graph structures. Rather than introducing new physical channel models, we demonstrate that identical physical links exhibit fundamentally different end-to-end performance once embedded within different network topologies. Mesh architectures minimize visibility cascade through hop-count reduction but incur quadratic hardware scaling. Star topologies minimize link count but concentrate noise and synchronization overhead at the hub. Ring configurations offer linear hardware scaling with multiplicative fidelity degradation. The results establish topology as a first-order design parameter in near-term free-space quantum networks operating without full quantum repeater infrastructures. While motivated by distributed multi-agent architectures, the framework applies broadly to terrestrial, airborne, and satellite-assisted photonic quantum communication systems.
QKD↗
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↗
Surrogate Modelling of 3rd Integer Resonant Extraction at Fermilab Delivery Ring
We present an ongoing work in which a surrogate model is being developed to reproduce the response dynamics of the third-integer resonant extraction process in the Delivery Ring (DR) at Fermilab. This effort is in pursuit of smoothly extracting circulating beam to the Mu2e Experiment s production target, wherein the goal is to extract a uniform slice of the circulating $1e12$ protons in the DR over 25,000 turns (43~ms). The DR contains 3 harmonic sextupoles which excite a third-integer resonance as well as three fast, tune-ramping quadrupole magnets which drive the horizontal tune towards the $29/3$ resonance. In our initial work the surrogate model trains on a semi-analytical simulation provided in the same format as live data. Using Reinforcement Learning (and other potential ML methods), the trained surrogate acts as the environment in which a simple ML control agent could learn to dynamically adjust the quadrupole ramp at 430 break points within the 43 microsecond spill window. The control agent will be hosted on a dedicated Arria 10 FPGA, introducing its own requirements on control agent architecture. In this work we report the accuracy and fidelity of surrogate models in comparison to the response dynamics of the physics simulator.
Narayanan, Aakaash [Fermilab] (ORCID:0000000157944↗
A framework for building real-time expert systems
The Space Station Freedom is an example of complex systems that require both traditional and artificial intelligence (AI) real-time methodologies. It was mandated that Ada should be used for all new software development projects. The station also requires distributed processing. Catastrophic failures on the station can cause the transmission system to malfunction for a long period of time, during which ground-based expert systems cannot provide any assistance to the crisis situation on the station. This is even more critical for other NASA projects that would have longer transmission delays (e.g., the lunar base, Mars missions, etc.). To address these issues, a distributed agent architecture (DAA) is proposed that can support a variety of paradigms based on both traditional real-time computing and AI. The proposed testbed for DAA is an autonomous power expert (APEX) which is a real-time monitoring and diagnosis expert system for the electrical power distribution system of the space station.
Lee, S. Daniel↗
A streamlined software environment for situated skills
This paper documents a powerful set of software tools used for developing situated skills. These situated skills form the reactive level of a three-tiered intelligent agent architecture. The architecture is designed to allow these skills to be manipulated by a task level engine which is monitoring the current situation and selecting skills necessary for the current task. The idea is to coordinate the dynamic activations and deactivations of these situated skills in order to configure the reactive layer for the task at hand. The heart of the skills environment is a data flow mechanism which pipelines the currently active skills for execution. A front end graphical interface serves as a debugging facility during skill development and testing. We are able to integrate skills developed in different languages into the skills environment. The power of the skills environment lies in the amount of time it saves for the programmer to develop code for the reactive layer of a robot.
Yu, Sophia T.↗
Metrics of a Paradigm for Intelligent Control
We present metrics for quantifying organizational structures of complex control systems intended for controlling long-lived robotic or other autonomous applications commonly found in space applications. Such advanced control systems are often called integration platforms or agent architectures. Reported metrics span concerns about time, resources, software engineering, and complexities in the world.
Hexmoor, Henry↗