Beyond Leaderboards: Tokenomics of Agentic Small Language Model Ensembles
Explore the source record for details and available documents.
97 MATHEMATICS AND COMPUTING↗
SEARCH · Search NASA
Results for “agentic AI”
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.
Summary of Technical Interchange Meetings (TIMs) Designed to Enable Earth Independent Medical Operations (EIMO)
The Exploration Medical Capability Element (ExMC) in NASA’s Human Research Program hosted a series of TIMs in 2023-2024 designed to stimulate discussion around specific topics with the goal of enabling EIMO. In context of the thematic constituent elements of EIMO, namely pre-mission planning, acute/emergent/prolonged medical decision making, supply/resource management and task load management, subject matter experts from industry, academia and government (NASA and other Agencies) provided valuable and actionable guidance and recommendations. Earth-based medical experts will remain indispensable for pre-mission planning, however, management of acute/emergent medical contingencies will require a gradual transition of medical care and decision making from terrestrial to space-based assets to enable support of astronaut health and performance and reduce overall mission risk. Key to achieving these enhancements is providing an integrated data system platform capable of utilizing multiple data streams in concert with a variety of on-board databases and passive monitoring of video and wearable sensors to enable a multi-modal, agentic AI-based clinical decision support system (CDSS) to support crew medical officer (CMO) medical decision-making. The EIMO series of TIMs (I-V) have proven to be instructive and portend a significant paradigm shift will be necessary to maintain crew health and performance on exploration class missions. Importantly, since the expected paradigm shift will be significantly different from the methods of operation that have been employed for the majority of missions from the inception of human spaceflight to date, any proposed methods must be deployed in the setting of ongoing operations early and be “tested, reviewed and practiced” while reliable back-up is available to facilitate an Enterprise-wide level of comfort and acceptance. Serious constraints on data transmission coupled with a large and expanding universe of on-board medical informatics data streams will necessitate implementation of a CDSS to supplant the current reliance on support provided by ground-based SMEs. Establishment of trust in the system by CMO/crew and the ground-based medical support team will be essential. Co-development of a CDSS with industry partners will assure that state of the art tools can be employed, and industry efficiencies can be leveraged. Training regimens, materials and tools must evolve to be responsive (just-in-time training) and facilitate autonomous execution of procedures. Proficiency metrics should be established and be based on validated competencies or milestones as opposed to a prescribed number of training hours. Training should be prioritized for broad, translatable skills that have universal application across a variety of medical conditions. Repetition was deemed to be the key to achieving proficiency and emphasis should lie in procedural training which is known to extinguish more rapidly than diagnostic skills. Advanced tools, e.g., extended reality, can provide more realistic and effective training. Use of advanced probabilistic risk assessment tools will be essential to optimize the medical system capability while carefully balancing risk relative to mass/power/volume limitations. Importance of factoring use-life of medical supplies and maintaining awareness of redundancy and opportunity to re-purpose under off nominal situations was emphasized. Consideration of adopting optimized performance standards vs. “good-enough” performance thresholds is warranted. The use of legacy systems as opposed to creating new systems may be preferable. Managing task load and associated cognitive load will be essential to maintain operational safety and behavioral health. ExMC aspires to create a shared EIMO paradigm and strategic vision for advancing medical system design through novel technologies, training, protocols, and support capabilities, built upon the spirit of successful strategies and innovations over the past six decades of space medicine operations.
Jay Lemery↗
Beyond Leaderboards: Tokenomics of Agentic Small Language Model Ensembles
Explore the source record for details and available documents.
97 MATHEMATICS AND COMPUTING↗
Surrogates for Valve-Controlled Pipe Flow: Accelerating Nuclear Reactor Design
Neural surrogate models are developed to replace expensive steady-state RANS CFD simulations for valve-controlled pipe flow in nuclear reactor design. Using parametric CFD data generated with MOOSE Pronghorn across a range of valve geometry and flow conditions, three approaches are compared: a POD-based reduced-order model, a structured UNet on a cylindrical grid, and unstructured models (DeepONet and BiStride MeshGraphNet) on nondimensionalized point clouds. POD achieves the highest accuracy (99%) with fast inference but requires storing all solution snapshots, while the DeepONet and BSMS-GNN both achieve ~89% accuracy at sub-second inference, with the BSMS-GNN offering superior geometric generalizability. These surrogates enable rapid ranking of candidate valve designs and can warm-start CFD solvers to accelerate convergence, supporting agentic design iteration on the Prometheus platform.
42 - ENGINEERING↗
SIVA: A Conversational and Declarative Scientific Visualization Tool
Explore the source record for details and available documents.
97 MATHEMATICS AND COMPUTING↗
Approach for Autonomous Control of Unmanned Aerial Vehicle Using Intelligent Agents for Knowledge Creation
This paper describes the development of a planned approach for Autonomous operation of an Unmanned Aerial Vehicle (UAV). A Hybrid approach will seek to provide Knowledge Generation through the application of Artificial Intelligence (AI) and Intelligent Agents (IA) for UAV control. The applications of several different types of AI techniques for flight are explored during this research effort. The research concentration is directed to the application of different AI methods within the UAV arena. By evaluating AI and biological system approaches. which include Expert Systems, Neural Networks. Intelligent Agents, Fuzzy Logic, and Complex Adaptive Systems, a new insight may be gained into the benefits of AI and CAS techniques applied to achieving true autonomous operation of these systems. Although flight systems were explored, the benefits should apply to many Unmanned Vehicles such as: Rovers. Ocean Explorers, Robots, and autonomous operation systems. A portion of the flight system is broken down into control agents that represent the intelligent agent approach used in AI. After the completion of a successful approach, a framework for applying an intelligent agent is presented. The initial results from simulation of a security agent for communication are presented.
Dufrene, Warren R., Jr.↗
Approach for Autonomous Control of Unmanned Aerial Vehicle Using Intelligent Agents for Knowledge Creation
This paper describes the development of a planned approach for Autonomous operation of an Unmanned Aerial Vehicle (UAV). A Hybrid approach will seek to provide Knowledge Generation thru the application of Artificial Intelligence (AI) and Intelligent Agents (IA) for UAV control. The application of many different types of AI techniques for flight will be explored during this research effort. The research concentration will be directed to the application of different AI methods within the UAV arena. By evaluating AI approaches, which will include Expert Systems, Neural Networks, Intelligent Agents, Fuzzy Logic, and Complex Adaptive Systems, a new insight may be gained into the benefits of AI techniques applied to achieving true autonomous operation of these systems thus providing new intellectual merit to this research field. The major area of discussion will be limited to the UAV. The systems of interest include small aircraft, insects, and miniature aircraft. Although flight systems will be explored, the benefits should apply to many Unmanned Vehicles such as: Rovers, Ocean Explorers, Robots, and autonomous operation systems. The flight system will be broken down into control agents that will represent the intelligent agent approach used in AI. After the completion of a successful approach, a framework of applying a Security Overseer will be added in an attempt to address errors, emergencies, failures, damage, or over dynamic environment. The chosen control problem was the landing phase of UAV operation. The initial results from simulation in FlightGear are presented.
Dufrene, Warren R., Jr.↗
Generative AI for Power Grid Operations
Generative artificial intelligence (AI) has captured into the mainstream, demonstrating capabilities that once belonged solely to the realm of human cognition. From defeating world champions in complex games to generating human-quality text and images, Generative AI has proven its potential to revolutionize countless industries. The electric power grid is no exception. Generative AI's ability to process vast amounts of data rapidly, assist decision support and identify patterns could significantly enhance power grid operations. For example, Generative AI could improve state estimation where measurements are not available or integrate renewable energy sources more efficiently with probabilistic forecasting. The key contributions of this whitepaper are outlined below: (1) Comprehensive overview of Generative AI's applications in power grid operations: It highlights the opportunities in areas such as forecasting, state estimation, and demonstrating the potential for enhancing efficiency, reliability, and resilience. (2) Expanding Generative AI's impact through synergies with emerging technologies: The paper introduce NREL developed eGridGPT and explores how AI orchestration, multi-agent systems, and Digital Twins can collaborate to optimize grid operations, addressing the complexities of a decarbonized and electrified future. (3) In-depth analysis of challenges in implementing Generative AI: This includes considerations like data availability and quality, model validation, certification, and ethical concerns, ensuring responsible AI deployment. (4) Emphasizing human-AI collaboration: The whitepaper underscores the importance of trustworthy, transparency, and explainability in AI systems to promote seamless interaction between human operators and AI, ultimately improving decision-making. (5) Exploring future research and development: It identifies critical areas for further advancement to fully realize Generative AI's potential in power grid operations. This whitepaper serves as a valuable resource for researchers, practitioners, and policymakers looking to harness Generative AI for a more reliable, stable, and cost-effective power grid.
24 POWER TRANSMISSION AND DISTRIBUTION↗
Formal Modeling of Multi-Agent Systems using the Pi-Calculus and Epistemic Logic
Multi-agent systems have become important recently in computer science, especially in artificial intelligence (AI). We allow a broad sense of agent, but require at least that an agent has some measure of autonomy and interacts with other agents via some kind of agent communication language. We are concerned in this paper with formal modeling of multi-agent systems, with emphasis on communication. We propose for this purpose to use the pi-calculus, an extension of the process algebra CCS. Although the literature on the pi-calculus refers to agents, the term is used there in the sense of a process in general. It is our contention, however, that viewing agents in the AI sense as agents in the pi-calculus sense affords significant formal insight. One formalism that has been applied to agents in the AI sense is epistemic logic, the logic of knowledge. The success of epistemic logic in computer science in general has come in large part from its ability to handle concepts of knowledge that apply to groups. We maintain that the pi-calculus affords a natural yet rigorous means by which groups that are significant to epistemic logic may be identified, encapsulated, structured into hierarchies, and restructured in a principled way. This paper is organized as follows: Section 2 introduces the pi-calculus; Section 3 takes a scenario from the classical paper on agent-oriented programming [Sh93] and translates it into a very simple subset of the n-calculus; Section 4 then shows how more sophisticated features of the pi-calculus may bc brought into play; Section 5 discusses how the pi-calculus may be used to define groups for epistemic logic; and Section 6 is the conclusion.
Rorie, Toinette↗
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↗
Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis
Operational safety in high-stakes domains such as industrial process control, autonomous, and safety-critical systems demand reliable hazard identification. While large language models (LLMs) have shown promise in automating safety analysis tasks, single-turn, monolithic inference is brittle: it lacks the self-correction, deliberation, and contextual refinement that safety engineers apply iteratively. In this paper, we introduce HAZDIAL, a framework that investigates whether structured agentic dialogue (multi-agent, multi-turn interactions) improves the quality of NLP-based hazard identification over single-pass baselines. We systematically compare two dialogue modalities: adversarial debate and constructive discussion, and propose an genetic algorithm-based agentic interaction optimization. We evaluate all configurations against a curated golden dataset using standard classification metrics (accuracy, precision, recall, F1) and a novel dialogue metrics. This work advances the intersection of dialogue systems, multi-agent reasoning, and AI safety, providing empirical evidence for dialogue-driven hazard analysis.
Das, Sanjay [ORNL] (ORCID:0009000542591915)↗
Design principles for lifelong learning AI accelerators
Lifelong learning-an agent's ability to learn throughout its lifetime-is a hallmark of biological learning systems and a central challenge for artificial intelligence (AI). The development of lifelong learning algorithms could lead to a range of novel AI applications, but this will also require the development of appropriate hardware accelerators, particularly if the models are to be deployed on edge platforms, which have strict size, weight and power constraints. Here we explore the design of lifelong learning AI accelerators that are intended for deployment in untethered environments. We identify key desirable capabilities for lifelong learning accelerators and highlight metrics to evaluate such accelerators. We then discuss current edge AI accelerators and explore the future design of lifelong learning accelerators, considering the role that different emerging technologies could play. The Perspective explores the future design of lifelong learning artificial intelligence (AI) accelerators that are intended for deployment in untethered environments, identifying key desirable capabilities for such edge AI accelerators and guidance on metrics to evaluate them.
42 ENGINEERING↗
Serious Gaming for Building a Basis of Certification via Trust and Trustworthiness of Autonomous Systems
Autonomous systems governed by a variety of adaptive and nondeterministic algorithms are being planned for inclusion into safety-critical environments, such as unmanned aircraft and space systems in both civilian and military applications. However, until autonomous systems are proven and perceived to be capable and resilient in the face of unanticipated conditions, humans will be reluctant or unable to delegate authority, remaining in control aided by machine-based information and decision support. Proving capability, or trustworthiness, is a necessary component of certification. Perceived capability is a component of trust. Trustworthiness is an attribute of a cyber-physical system that requires context-driven metrics to prove and certify. Trust is an attribute of the agents participating in the system and is gained over time and multiple interactions through trustworthy behavior and transparency. Historically, artificial intelligence and machine learning systems provide answers without explanation - without a rationale or insight into the machine “thinking”. In order to function as trusted teammates, machines must be able to explain their decisions and actions. This transparency is a product of both content and communication. NASA’s Autonomy Teaming & TRAjectories for Complex Trusted Operational Reliability (ATTRACTOR) project seeks to build a basis for certification of autonomous systems via establishing metrics for trustworthiness and trust in multi-agent team interactions, using AI (Artificial Intelligence) explainability and persistent modeling and simulation, in the context of mission planning and execution, with analyzable trajectories. Inspired by Massively Multiplayer Online Role Playing Games (MMORPG) and Serious Gaming, the proposed ATTRACTOR modeling and simulation environment is similar to online gaming environments in which player (aka agent) participants interact with each other, affect their environment, and expect the simulation to persist and change regardless of any individual agent’s active participation. This persistent simulation environment will accommodate individual agents, groups of self-organizing agents, and large-scale infrastructure behavior. The effects of the emerging adaptation and coevolution can be observed and measured to building a basis of measurable trustworthiness and trust, toward certification of safety-critical autonomous systems.
Allen, B. Danette↗
Generative diffusion model surrogates for mechanistic agent-based biological models
Mechanistic, multicellular, agent-based models are commonly used to investigate tissue, organ, and organism-scale biology at single-cell resolution. The Cellular-Potts Model (CPM) is a powerful and popular framework for developing and interrogating these models. CPMs become computationally expensive at large space- and time- scales making application and investigation of developed models difficult. Surrogate models may allow for the accelerated evaluation of CPMs of complex biological systems. However, the stochastic nature of these models means each set of parameters may give rise to different model configurations, complicating surrogate model development. In this work, we leverage denoising diffusion probabilistic models (DDPMs) to train a generative AI surrogate of a CPM used to investigate in vitro vasculogenesis. We describe the use of an image classifier to learn the characteristics that define unique areas of a 2-dimensional parameter space. We then apply this classifier to aid in surrogate model selection and verification. Our CPM model surrogate generates model configurations 20,000 timesteps ahead of a reference configuration and demonstrates approximately a 22x reduction in computational time as compared to native code execution. Our work represents a step towards the implementation of DDPMs to develop digital twins of stochastic biological systems.
97 MATHEMATICS AND COMPUTING↗
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.↗
Effect of the Angiotensin I Converting Enzyme Inhibitor, MK-421, on Experimentally Induced Drinking
MK-421, the ethyl ester maleate salt of N-(S)-1-(ethoxycarbonyl)-3-phenyl-propyl- Ala-L-Pro, is an angiotensin I converting enzyme inhibitor. An initial objective was to determine whether MK-421, administered at 0, 2.5, 5.0, 10.0, 20.0 and 40.0 mg/kg, ip to 96 female rats 15 min prior to administration of the beta-adrenergic agonist, isoproterenol (25 microgram/kg, ip), would inhibit the drinking induced by isoproterenol during 2 h after its administration. The water intake induced by isoproterenol was inhibited significantly by 2.5 mg MK-421/kg. When a similar experiment was performed using Angiotensin I (AI) (200 microgram/kg, ip) as the dipsogenic agent, MK-421 (5 mg/kg, ip), administered 15 min prior to AI, inhibited significantly both the dipsogenic and the diuretic effect of AI. However, administration of angiotensin II (AII, 200 microgram/kg, ip) 15 min after MK-421 (5mg/kg) was accompanied by a water intake that did not differ from AII alone. The drink induced by ip administration of 1.0 m NaCl solution (1% of body wt, ip) was not inhibited by administration of MK-421 (5 mg/kg) 15 min prior to allowing access to water while the drink induced by a 24 h dehydration was partially inhibited. Thus, the drinks induced by administraition of either isoproterenol or AI are dependent on formation of AII. That induced by dehydration is partially dependent, while that induced by hypertonic siilinc is independent of the formation of AII.
Fregley, Melvin J.↗
The Techsat-21 autonomous space science agent
In this paper we discuss how these AI technologies are synergistically integrated in a hybrid multi-layer control architecture to enable a virtual spacecraft science agent.
autonomy software agents onboard decision-making↗
A distributed agent architecture for real-time knowledge-based systems: Real-time expert systems project, phase 1
We propose a distributed agent architecture (DAA) that can support a variety of paradigms based on both traditional real-time computing and artificial intelligence. DAA consists of distributed agents that are classified into two categories: reactive and cognitive. Reactive agents can be implemented directly in Ada to meet hard real-time requirements and be deployed on on-board embedded processors. A traditional real-time computing methodology under consideration is the rate monotonic theory that can guarantee schedulability based on analytical methods. AI techniques under consideration for reactive agents are approximate or anytime reasoning that can be implemented using Bayesian belief networks as in Guardian. Cognitive agents are traditional expert systems that can be implemented in ART-Ada to meet soft real-time requirements. During the initial design of cognitive agents, it is critical to consider the migration path that would allow initial deployment on ground-based workstations with eventual deployment on on-board processors. ART-Ada technology enables this migration while Lisp-based technologies make it difficult if not impossible. In addition to reactive and cognitive agents, a meta-level agent would be needed to coordinate multiple agents and to provide meta-level control.
Lee, S. Daniel↗