SEARCH · Search NASA

Results for “Reasoning 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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 91 records · Page 5

All sources NASA NTRS DOE OSTI

NASA NTRS1991

ECLSS predictive monitoring

On Space Station Freedom (SSF), design iterations have made clear the need to keep the sensor complement small. Along with the unprecendented duration of the mission, it is imperative that decisions regarding placement of sensors be carefully examined and justified during the design phase. In the ECLSS Predictive Monitoring task, we are developing AI-based software to enable design engineers to evaluate alternate sensor configurations. Based on techniques from model-based reasoning and information theory, the software tool makes explicit the quantitative tradeoffs among competing sensor placements, and helps designers explore and justify placement decisions. This work is being applied to the Environmental Control and Life Support System (ECLSS) testbed at MSFC to assist design personnel in placing sensors for test purposes to evaluate baseline configurations and ultimately to select advanced life support system technologies for evolutionary SSF.

Doyle, Richard J.↗

NASA NTRS1994

KATE: From the lab to the firing room

For the past 9 years, the AI group at NASA's Kennedy Space Center (KSC) has been developing a real-time model-based reasoning (MBR) system that can diagnose faults and provide control advisories. The system resulting from this effort is called KATE (Knowledge-based Autonomous Test Engineer). This article describes the transition of KATE from the applied research lab to the firing room (the firing room is the main control and monitoring center for all Shuttle ground support and launch processing). Because the problems that were countered along the way are not unique, we decided to share some of our experiences. This article also includes a brief overview of the latest application of KATE.

Pepe, Charles↗

DOE OSTI2020

Measure Utility, Gain Trust: Practical Advice for XAI Researchers

Research into explanation of machine learning models, i.e. explainable AI (XAI), has seen a sympathetic exponential growth alongside deep artificial neural networks throughout the past decade. For historical reasons explanation and trust have been intertwined. However this focus on trust is too narrow, and has led the research community astray from tried and true empirical methods that lead to more defensible scientific knowledge about people and explanations. To address this, we contribute a practical path forward for researchers in the XAI field. We recommend researchers focus on the utility and impact of their explanations instead of trust. We outline five broad use cases where explanations are useful and, for each, we describe pseudo-experiments that rely on objective empirical measurements and falsifiable hypotheses. We believe that this experimental rigor is necessary to contribute to scientific knowledge in the field of XAI.

Davis, Brittany F.↗

NASA NTRS1993

The coming technological singularity: How to survive in the post-human era

The acceleration of technological progress has been the central feature of this century. I argue in this paper that we are on the edge of change comparable to the rise of human life on Earth. The precise cause of this change is the imminent creation by technology of entities with greater than human intelligence. There are several means by which science may achieve this breakthrough (and this is another reason for having confidence that the event will occur): (1) the development of computers that are 'awake' and superhumanly intelligent (to date, most controversy in the area of AI relates to whether we can create human equivalence in a machine. But if the answer is 'yes, we can', then there is little doubt that beings more intelligent can be constructed shortly thereafter); (2) large computer networks (and their associated users) may 'wake up' as a superhumanly intelligent entity; (3) computer/human interfaces may become so intimate that users may reasonably be considered superhumanly intelligent; and (4) biological science may find ways to improve upon the natural human intellect. The first three possibilities depend in large part on improvements in computer hardware. Progress in computer hardware has followed an amazingly steady curve in the last few decades. Based largely on this trend, I believe that the creation of greater than human intelligence will occur during the next thirty years.

Vinge, Vernor↗

DOE OSTI2024

Dynamic Retrieval Augmented Generation of Ontologies using Artificial Intelligence (DRAGON-AI)

Ontologies are fundamental components of informatics infrastructure in domains such as biomedical, environmental, and food sciences, representing consensus knowledge in an accurate and computable form. However, their construction and maintenance demand substantial resources and necessitate substantial collaboration between domain experts, curators, and ontology experts. We present Dynamic Retrieval Augmented Generation of Ontologies using AI (DRAGON-AI), an ontology generation method employing Large Language Models (LLMs) and Retrieval Augmented Generation (RAG). DRAGON-AI can generate textual and logical ontology components, drawing from existing knowledge in multiple ontologies and unstructured text sources.We assessed performance of DRAGON-AI on de novo term construction across ten diverse ontologies, making use of extensive manual evaluation of results. Our method has high precision for relationship generation, but has slightly lower precision than from logic-based reasoning. Our method is also able to generate definitions deemed acceptable by expert evaluators, but these scored worse than human-authored definitions. Notably, evaluators with the highest level of confidence in a domain were better able to discern flaws in AI-generated definitions. We also demonstrated the ability of DRAGON-AI to incorporate natural language instructions in the form of GitHub issues.These findings suggest DRAGON-AI's potential to substantially aid the manual ontology construction process. However, our results also underscore the importance of having expert curators and ontology editors drive the ontology generation process.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

NASA NTRS1987

An efficient representation of spatial information for expert reasoning in robotic vehicles

The previous generation of robotic vehicles and drones was designed for a specific task, with limited flexibility in executing their mission. This limited flexibility arises because the robotic vehicles do not possess the intelligence and knowledge upon which to make significant tactical decisions. Current development of robotic vehicles is toward increased intelligence and capabilities, adapting to a changing environment and altering mission objectives. The latest techniques in artificial intelligence (AI) are being employed to increase the robotic vehicle's intelligent decision-making capabilities. This document describes the design of the SARA spatial database tool, which is composed of request parser, reasoning, computations, and database modules that collectively manage and derive information useful for robotic vehicles.

Scott, Steven↗

NASA NTRS1988

Benchmarking expert system tools

As part of its evaluation of new technologies, the Artificial Intelligence Section of the Mission Planning and Analysis Div. at NASA-Johnson has made timing tests of several expert system building tools. Among the production systems tested were Automated Reasoning Tool, several versions of OPS5, and CLIPS (C Language Integrated Production System), an expert system builder developed by the AI section. Also included in the test were a Zetalisp version of the benchmark along with four versions of the benchmark written in Knowledge Engineering Environment, an object oriented, frame based expert system tool. The benchmarks used for testing are studied.

Riley, Gary↗

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↗

DOE OSTI2021

Accelerating Scientific Applications With SambaNova Reconfigurable Dataflow Architecture

Here, our exploratory work finds that the SambaNova Reconfigurable Dataflow Architecture (RDA) along with the SambaFlow software stack provides for an attractive system and solution to accelerate AI for science workloads. We have observed the efficacy of using the system with a diverse set of science applications and reasoned their suitability for performance gains over traditional hardware. As the Data-Scale system provides for a very large memory capacity, the system can be used to train models that typically do not fit in a GPU. The architecture also provides for deeper integration with upcoming supercomputers at the Argonne Leadership Computing Facility (ALCF), a US Department of Energy Office of Science user facility, to help advance science insights.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1988

AI and simulation: What can they learn from each other

Simulation and Artificial Intelligence share a fertile common ground both from a practical and from a conceptual point of view. Strengths and weaknesses of both Knowledge Based System and Modeling and Simulation are examined and three types of systems that combine the strengths of both technologies are discussed. These types of systems are a practical starting point, however, the real strengths of both technologies will be exploited only when they are combined in a common knowledge representation paradigm. From an even deeper conceptual point of view, one might even argue that the ability to reason from a set of facts (i.e., Expert System) is less representative of human reasoning than the ability to make a model of the world, change it as required, and derive conclusions about the expected behavior of world entities. This is a fundamental problem in AI, and Modeling Theory can contribute to its solution. The application of Knowledge Engineering technology to a Distributed Processing Network Simulator (DPNS) is discussed.

Colombano, Silvano P.↗

NASA NTRS1985

Expert systems for Space Station automation

The expert systems required for automating key functions of the Manned Space Station (MSS) are explored. It is necessary that the expert systems developed be flexible, degrade gracefully in the case of a failure, and be able to work with incomplete data. The AI systems will have to perform interpretation and diagnosis, design, prediction and induction, and monitoring and control functions. Both quantitative and qualitative reasoning capabilities need improvements, as do automatic verification techniques, explanation and learning capabilities, and the use of metaknowledge, i. e., knowledge about the knowledge contained in the knowledge base. Information retrieval, fault isolation and manufacturing process control demonstrations are needed to validate expert systems for the MSS.

Georgeff, M. P.↗

NASA NTRS1990

Dynamic control of robotic welding - On-going research

Two major challenges exist for the development of dynamic control systems: first, the control system must be resourceful enough to provide problem-solving capabilities in unforeseen circumstances; second, it must be rapid enough to respond to dynamic environments. Most conventional control systems do not have the ability to 'step back' and problem-solve, especially in environments with incomplete and uncertain models and data. Orthogonally, commercially available AI systems usually do not respond at the rates required to support 'real-time' control. Hence, control systems are not available that respond to complex dynamic environments within appropriate time constraints. This paper describes work on an AI-based control system designed to address these challenges. A prototype system has been used, in a simulated environment, to control the robotic welding of aerospace components. This AI-based control system has demonstrated the ability to flexibly control a complex process within required time constraints by incorporating higher level reasoning and the ability to deal with uncertainty. Further work is in progress to expand the system's problem-solving capabilities.

Ruokangas, Corinne C.↗

NASA NTRS1990

Automation of Space Station module power management and distribution system

Viewgraphs on automation of space station module (SSM) power management and distribution (PMAD) system are presented. Topics covered include: reasons for power system automation; SSM/PMAD approach to automation; SSM/PMAD test bed; SSM/PMAD topology; functional partitioning; SSM/PMAD control; rack level autonomy; FRAMES AI system; and future technology needs for power system automation.

Bechtel, Robert↗

NASA NTRS1994

C++ Planning and Resource Reasoning (PARR) shell

This paper describes a generic, C++ version of the Planning and Resource Reasoning (PARR) shell which has been developed to supersede the C-based versions of PARR that are currently used to support AI planning and scheduling applications in flight operations centers at Goddard Space Flight Center. This new object-oriented version of PARR can be more easily customized to build a variety of planning and scheduling applications, and C++ PARR applications can be more easily ported to different environments. Genetic classes, constraints, strategies, and paradigms are described along with two types of PARR interfaces.

Mcintyre, James↗

NASA NTRS1990

CLIPS/Ada: An Ada-based tool for building expert systems

Clips/Ada is a production system language and a development environment. It is functionally equivalent to the CLIPS tool. CLIPS/Ada was developed in order to provide a means of incorporating expert system technology into projects where the use of the Ada language had been mandated. A secondary purpose was to glean information about the Ada language and its compilers. Specifically, whether or not the language and compilers were mature enough to support AI applications. The CLIPS/Ada tool is coded entirely in Ada and is designed to be used by Ada systems that require expert reasoning.

White, W. A.↗

DOE OSTI2026

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↗

DOE OSTI2024

Using Generative AI to implement the discrepancy checker for a Nearly Autonomous Management and Control System for Advanced Reactors

Developments related to generative artificial intelligence (AI) have brought a major breakthrough in AI. These developments are rapidly accelerating developments in different science and engineering applications. Nearly Autonomous Management and Control (NAMAC) system provides recommendations to the operator for maintaining the safety and performance of the reactor. The discrepancy checker (DC) is an important component of the NAMAC) system, whose goal is to determine if the plant is moving towards the expected system state after the control actions are injected. In this work, we explore generative AI methods, particularly, a generative pretrained transformer (GPT) for implementing the DC function in NAMAC. The GPT-based DC aims to alert the operator in situations outside NAMAC’s scope and act as a chatbot the operator can use to retrieve relevant information. This study involves two versions of GPT developed by OpenAI: GPT-3.5 and GPT-4. These GPTs are trained on huge amounts of undisclosed general domain datasets. We explored two methods to adapt GPTs for DC implementation in NAMAC: fine-tuning and retrieval augmented generation. A small knowledge base (information file) that encompasses rules for DC implementation and some general information related to NAMAC has been created to support DC implementation using GPT. In this work, the GPT-based DC implementations have been tested for their reasoning abilities, comprehension, information retrieval, and extraction abilities. It should be noted that this paper only presents a preliminary study to test the feasibility of DC implementation using generative AI technology. Given the potential risks and severe consequences associated with nuclear reactor applications, combined with the black-box nature of AI, extensive offline and online testing and reliability analyses of GPT-based DCs are needed for further developing such capabilities.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2026

Hierarchical Multi-agent Large Language Model Reasoning for Autonomous Heterogeneous Catalyst Discovery

Artificial intelligence is reshaping scientific exploration, but most methods automate procedural tasks without engaging in scientific reasoning, limiting autonomy in discovery. We demonstrate that hierarchical agentic large language model reasoning can efficiently drive simulation and scientific exploration. Across two chemical applications, CO adsorption on Cu surface transition metal adatoms and on M–N–C catalysts, reasoning-guided exploration reduces required atomistic simulations by up to 90% relative to heuristic or random selection. Comparisons across single-agent, multi-agent, and stochastic baselines show that hierarchical strategies yield more coherent and information-efficient search trajectories. Reasoning traces reveal chemically grounded decisions that cannot be explained by semantic bias or stochastic sampling. We realize these agentic reasoning strategies in Materials Agents for Simulation and Theory in Electronic-structure Reasoning (MASTER), a multimodal system that translates natural language into density functional theory workflows. Altogether, multi-agent collaboration accelerates heterogeneous catalyst discovery and marks a step toward more autonomous, reasoning-guided scientific exploration.

30 DIRECT ENERGY CONVERSION↗