Search NASA⌕ Search

SEARCH · Search NASA

Results for “Reasoning”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Operation Optimization using Reinforcement Learning with Integrated Artificial Reasoning Framework

In large and complex systems, operational decision-making requires a systematic analysis with a vast amount of data from both process parameters and component status monitoring. In this paper, we present an integrated artificial reasoning approach for system state transition models that can help operational decision-making with explainable and traceable reasoning. The integrated artificial reasoning framework is a physics-based approach of defining the system structure in a Bayesian network, so we leveraged it in a Markov decision process (MDP) for finding optimal operational solutions. In our proposed framework, the MDP is implemented on a dynamic Bayesian network (DBN), which represents causalities in a system. The multilevel flow modeling was utilized in order to extract these causalities in a more efficient and objective manner. Since multilevel flow modeling is based on the fundamental energy and mass conservation laws, the target system is decomposed into several mass, energy, and information structures, which serve as the basis for a DBN. The MDP consists of the processes of finding a solution for the Bellman equation, which can be derived from the conditional probability equations of the constructed DBN. System operators can capture stochastic system dynamics as multiple subsystem state transitions based on their physical relations and uncertainties coming from the component degradation process or random failures. We analyzed a simplified example system to illustrate finding an optimal operational policy with this approach.

99 GENERAL AND MISCELLANEOUS↗
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↗
DOE OSTI2023

Monte Carlo Thought Search: Large Language Model Querying for Complex Scientific Reasoning in Catalyst Design

Discovering novel catalysts requires complex reasoning involving multiple chemical properties and resultant trade-offs, leading to a combinatorial growth in the search space. While large language models (LLM) have demonstrated novel capabilities for chemistry through complex instruction following capabilities and high quality reasoning, a goal-driven combinatorial search using LLMs has not been explored in detail. In this work, we present a Monte Carlo Tree Search-based approach that improves beyond state-of-the-art chain-of-thought prompting variants to augment scientific reasoning. We introduce two new reasoning datasets: 1) a curation of computational chemistry simulations, and 2) diverse questions written by catalysis researchers for reasoning about novel chemical conversion processes. We improve over the best baseline by 25.8\% and find that our approach can augment scientist's reasoning and discovery process with novel insights.\footnote{All resources will be publicly available upon publication.

Sprueill, Henry W.↗
DOE OSTI2025

Towards philosophical reasoning with agentic LLMs: Socratic method for scientific assistance

As large language models (LLMs) become central tools in science, improving their reasoning capabilities is critical for meaningful and trustworthy applications. We introduce a Socratic agent for scientific reasoning, implemented through a structured system prompt that guides LLMs via classical principles of inquiry. Unlike typical prompt engineering or retrieval-based methods, our approach leverages definition, analogy, hypothesis elimination, and other Socratic techniques to generate more coherent, critical, and domain-aware responses. We evaluate the agent across diverse scientific domains and benchmark it on the abstraction and reasoning corpus challenge dataset, achieving 97.15% under a fixed prompting protocol and without fine-tuning or external tools. Expert evaluation shows improved reasoning depth, clarity, and adaptability over conventional LLM outputs, suggesting that structured prompting rooted in philosophical reasoning can improve the scientific utility of language models.

LLM reasoning↗
DOE OSTI2026

Compositional Reasoning for Hierarchical State Machines

Harel statecharts and its derivatives are popular graphical languages for specifying discrete control systems via hierarchical state machines. Separately, there has been a long line of work on specifying concurrent systems with process calculi which come equipped with an algebraic theory, the ability reason compositionally about various temporal properties, and strong type systems. While these two approaches to modeling systems are tantalizingly similar, the integrated reasoning principles that exist for process calculi have not been demonstrated in hierarchical state machines. A key issue is that operational theories for process calculi do not behave like control systems, and thus, there is virtually no tool support for modeling control systems with such languages. For a control system designer, bringing the integrated, more scalable reasoning from the process calculi to state-machine languages would enable the specification of more complex systems and a more modular systems development process. Our insight is that we can recover many important results from the process calculi in hierarchical state machines with local scope. We employ a structural operational semantics, which is ubiquitous in process and 𝜆-calculi but uncommon in hierarchical statemachine formalizations, to enable inductive reasoning about behavior. Taking inspiration from the structure of process calculi metatheories, we define a calculus of refinement and equivalence that we prove sound with respect to local notion of (bi)simulation. Furthermore, we prove that the calculus preserves the behavioral properties of reactivity, observational determinism, traces, and linear temporal properties. Our results are mechanized in the Rocq proof assistant.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Key Constructs for Reasonable Confidence in System Validation Programs

This paper presents four key constructs developed in preparing IEEE Std P2411TM, Human Factors Engineering Guide for the Validation of System Designs and Integrated Systems Operations at Nuclear Facilities for submission. These constructs reflect judgments that responsible parties make in order to bring validation to closure. Such judgments weigh competing concerns and cost-benefits for stakeholders. Improved processes and methods may support such judgments but cannot alone eliminate uncertainty. Stating and clarifying these constructs aims to reduce uncertainty in the validation process, to better prepare the implementers and reviewers of future validation programs, both in the nuclear industry and beyond. Reasonable Confidence – A proof standard, as used to reach conclusions in a legal case. Legal proof standards are bounded between “preponderance of evidence” and “beyond reasonable doubt”. Reasonable confidence is comparable to an intermediate legal proof standard of “clear and convincing evidence.” Representative Test Set – A collection of scenarios of sufficient variety to represent the anticipated range of operational conditions, events, evolutions, and activities for validating the system(s) under test. Dispositive vs. Diagnostic Criteria – Relevant performance criteria are placed in one of two categories. Dispositive criteria are assessed, without exception, to determine whether a validation test passes or fails overall. Diagnostic criteria are assessed, subject to justified exception, to evaluate the quality or degree of some particular aspect of performance. Repeatability – Consistency in achieving passing results is to be demonstrated for each scenario in the representative test set; thus, the minimum number of formal repetitions for each scenario is two.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2022

Contrasting behaviour under pressure reveals the reasons for pyramidalization in tris(amido)uranium(III) and tris(arylthiolate) uranium(III) molecules

A range of reasons has been suggested for why many low-coordinate complexes across the periodic table exhibit a geometry that is bent, rather a higher symmetry that would best separate the ligands. The dominating reason or reasons are still debated. Here we show that two pyramidal UX3 molecules, in which X is a bulky anionic ligand, show opposite behaviour upon pressurisation in the solid state. UN" 3 (UN3, N" = N(SiMe 3 ) 2 ) increases in pyramidalization between ambient pressure and 4.08 GPa, while U(SAr) 3 (US3, SAr = S-C 6 H 2 - t Bu 3 –2,4,6) undergoes pressure-induced planarization. This capacity for planarization enables the use of X-ray structural and computational analyses to explore the four hypotheses normally put forward for this pyramidalization. The pyramidality of UN3, which increases with pressure, is favoured by increased dipole and reduction in molecular volume, the two factors outweighing the slight increase in metal-ligand agostic interactions that would be formed if it was planar. The ambient pressure pyramidal geometry of US3 is favoured by the induced dipole moment and agostic bond formation but these are weaker drivers than in UN3; the pressure-induced planarization of US3 is promoted by the lower molecular volume of US3 when it is planar compared to when it is pyramidal.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2026

The ballad of LLM agents: philosophical reasoning for chemistry

Large language models (LLMs) show remarkable potential for scientific reasoning but often produce unreliable or scientifically unactionable outputs when faced with multi-step logic, domain grounding, and interpretability challenges, especially in complex fields like chemistry and materials science. Here, we introduce a framework of philosophical reasoning agents, inspired by canonical thinkers such as Socrates, Descartes, Kant, and Hume, to guide LLM behavior via structured prompt engineering. These agents embody distinct reasoning paradigms (dialectical inquiry, deductive logic, rule-based judgment, and empirical validation) and are evaluated across multiple chemistry subdomains, physical, analytical, general, inorganic, and organic chemistry, using the ChemBench benchmark. Our agentic prompting approach yields substantial accuracy gains on open-ended numerical chemistry questions, with gains of +11.5 percentage points for GPT-4o with Hume, +4.5 percentage points for GPT-5 with Kant, and +21.8 percentage points for GPT-5.1 with Socrates at the strict 1% error threshold, relative to the corresponding base models. Beyond accuracy, we observe benchmark-level model–agent performance patterns, suggesting that different prompting styles interact differently with each base model. These findings demonstrate that embedding philosophy-of-science principles into multi-agent frameworks can improve and produce interpretable, adaptive, and domain-aligned scientific LLMs.

Harb, Hassan [Argonne National Laboratory (ANL), A↗
DOE OSTI2021

Artificial Reasoning System for Symptom-Based Conditional Failure Probability Estimation Using Bayesian Network

Advances in nuclear power technologies require enhanced capabilities for operator advice and autonomous control. One of the first tasks in the development of such capabilities is the formulation of symptom-based conditional failure probabilities for structures, systems, and components (SSCs) of interest, for which the primary goal is to aid plant personnel in deducing the probabilistic performance status of the monitored SSCs and in detecting impending faults/failure. The task of conditional failure probability estimation is a bidirectional inference problem and shall be logically tackled by the Bayesian network (BN) approach. As a knowledge-based artificial intelligence tool and a probabilistic graphical model, BN offers the capability of reasoning under uncertainty and graphical representation emulating the physical behavior of the target SSC. This paper provides a systematic overview of the BN technique and the software tools for handling implementation of BN models, along with the associated knowledge representation and reasoning paradigm. Both operational data and expert judgement can be readily incorporated into the knowledge base of a BN model. The challenges with data availability are highlighted, and the general approach to target SSC identification is presented. Our focus is upon failure-prone and risk-important balance of plant assets, especially cases having strong operator involvement. An exemplary case study on the failure of a motor-driven centrifugal pump is also conducted to demonstrate the usefulness and technical feasibility of the proposed artificial reasoning system using an expert system shell.

Zhao, Xingang↗
DOE OSTI2023

Operation Optimization Using Reinforcement Learning with Integrated Artificial Reasoning Framework

In large and complex systems, operational decision-making requires a systematic analysis with a vast amount of data from both process parameters and component status monitoring. In this paper, we present an integrated artificial reasoning approach for system state transition models that can help operational decision-making with explainable and traceable reasoning. The integrated artificial reasoning framework is a physics-based approach of defining the system structure in a Bayesian network, so we leveraged it in a Markov decision process (MDP) for finding optimal operational solutions. In our proposed framework, the MDP is implemented on a dynamic Bayesian network (DBN), which represents causalities in a system. The multilevel flow modeling was utilized in order to extract these causalities in a more efficient and objective manner. Since multilevel flow modeling is based on the fundamental energy and mass conservation laws, the target system is decomposed into several mass, energy, and information structures, which serve as the basis for a DBN. The MDP consists of the processes of finding a solution for the Bellman equation, which can be derived from the conditional probability equations of the constructed DBN. System operators can capture stochastic system dynamics as multiple subsystem state transitions based on their physical relations and uncertainties coming from the component degradation process or random failures. We analyzed a simplified example system to illustrate finding an optimal operational policy with this approach.

Kim, Junyung↗
DOE OSTI2020

Panel Session 132: Risk-Informed Approach for Decision Making in WM, D and D and SNF Management: Reasonable Assurance for Safety

Mr. Larry Camper organized a panel of experts to discuss approaches to better make risk-informed decisions in waste management, decommissioning, and the management of Spent Nuclear Fuel (SNF). The audience heard the perspectives from four panelists that addressed issues ranging from the technical basis used to make risk-informed decisions to for developing cleanup criteria and promulgating regulations and safety standards both domestically and abroad. A summary of each of the presentations given by the panelists is provided herein. This WMS BOD featured panel focused on the Risk-Informed Approach for Decision Making in WM, D and D and SNF Management and the Reasonable Assurance for Safety. The panelists addressed and discussed with the audience different approaches used for decision-making, summarizing ongoing probabilistic vs. deterministic approaches, including IAEA graded approach, and discussed policies/approaches to achieve reasonable assurance for safety rather than using absolute assurance. Panelists with presentations: Risk-Informed Decision Making - More than a Motto? (Paul Black); NRC Staff Perspective on Risk-Informed Approach and Reasonable Safety Assurance in D and D and LLW (Rateb (Boby) Abu Eid); Risk-Informed Decision-Making and Illustrative National Academies Studies (Charles Ferguson); IAEA's Revised Safety Guidance on Remediation (Michelle Roberts); NDA Radioactive Waste Strategy - A Risk Informed Approach (James McKinney)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2021

AI-Guided Reasoning-Based Operator Support System for the Nuclear Power Plant Management

The Decision-making process in the Nuclear Power Plant (NPP) control room faces some challenges: operator incomplete knowledge, insufficient time for responding to the highly dynamic events, and a large number of indicators to monitor. Because of the complexity of the NPP system, it is hard to pre-plan all the failures/mitigative actions. An intelligent operator support system is vital to mitigate these shortcomings. In this paper, an AI declarative approach (Answer Set Programming (ASP)) is employed to represent our knowledge of the nuclear power plant in the form of logic rules. This represented knowledge is structured to form a reasoning-based operator support system. When an incident occurs, this ASP-based reasoning support system is demonstrated to be capable of fault identification (diagnosis), informing the operator of different scenarios and consequences, and generating the control options (decision making).

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2023

Alerga: Alert Aggregation and Reasoning in GOOSE Simulation Pipeline

IEC 61850 specifies the Generic Object Oriented Substation Event (GOOSE) protocol as one option for low latency communication of substation-related events. Due to its strict timing requirements, GOOSE lacks any form of encryption or authentication and has only minimal integrity guarantees. These absences render the protocol vulnerable to a variety of communication anomalies, including adversarial action. In particular, an adversary with access to the substation network can launch man in the middle (MITM) attacks. We propose Alerga, a set of tools to allow operators to mitigate some of the risks of the protocol while retaining its strengths. To that end, we have developed first a GOOSE simulation pipeline including data generation, anomaly detection, alert handling, causal reasoning and data visualization components. The simulator is designed to be modular, allowing operators to swap components to better fit their network capabilities. The volume of alert traffic on a substation network threatens operators with alert fatigue. In order to combat this, we secondly present a novel form of alert aggregation and processing, offering operators a condensed view of any threats to the system. Thirdly, to facilitate the handling of these threats, our causal reasoning system traces the alerts back to their most likely cause, generating an initial hypothesis for operators to investigate.

alert aggregation↗
DOE OSTI2024

Evaluating the Effectiveness of Retrieval-Augmented Large Language Models in Scientific Document Reasoning

Despite the dramatic progress in Large Language Model (LLM) development, LLMs often provide seemingly plausible but not factual information, often referred as hallucinations. Retrieval-augmented LLMs provide a non-parametric approach to solve these issues by retrieving relevant information from external data sources and augment the training process. These models helps to trace evidence from an externally provided knowledge base allowing the model predictions to be better interpreted and verified. In this work, we critically evaluate these models in their ability to perform in scientific document reasoning tasks. To this end, we tuned multiple such model variants with science-focused instructions and evaluated them on a scientific document reasoning benchmark for the usefulness of the retrieved document passages. Our findings suggest that models justify predictions in science tasks with fabricated evidence and leveraging scientific corpus as pretraining data does not alleviate the risk of evidence fabrication.

• Artificial intelligence (AI) / machine learning ↗
DOE OSTI2023

Right band gaps for the right reason at low computational cost with a meta-GGA

In density functional theory, traditional explicit density functionals such as the local density approximation and generalized gradient approximations cannot accurately predict the band gap of solids for a fundamental reason: They lack the exchange-correlation derivative discontinuity. By comparing Kohn-Sham and generalized Kohn-Sham calculations, we here show that the nonempirical meta-generalized-gradient-approximation (meta-GGA) TASK from Aschebrock and Kümmel [Phys. Rev. Res. 1, 033082 (2019)] predicts the right gaps for the right reason, i.e., as a combination of a proper Kohn-Sham gap and a substantial derivative discontinuity contribution. For many materials from small-gap semiconductors to large-gap insulators, the proper band gap is thus obtained. Here we further study a group of metal-halide perovskites for which the band gap is notoriously hard to predict. For these materials, TASK yields band gaps very similar to the nonlocal screened hybrid Heyd-Scuseria-Ernzerhof functional, yet at a fraction of the hybrid functional’s computational cost. We discuss the influence of correlation functionals, and open questions in the comparison of calculated band gaps with experimental ones.

36 MATERIALS SCIENCE↗
DOE OSTI2024

GraphAide: Advanced Graph-Assisted Query and Reasoning System

Curating knowledge from multiple siloed sources that contain both structured and unstructured data is a major challenge in many real-world applications. Pattern matching and querying represent fundamental tasks in modern data analytics that leverage this curated knowledge. The development of such applications necessitates overcoming several research challenges, including data extraction, named entity recognition, data modeling, and designing query interfaces. Moreover, the explainability of these functionalities is critical for their broader adoption. The emergence of Large Language Models (LLMs) has accelerated the development lifecycle of new capabilities. Nonetheless, there is an ongoing need for domain-specific tools tailored to user activities. The creation of digital assistants has gained considerable traction in recent years, with LLMs offering a promising avenue to develop such assistants utilizing domain-specific knowledge and assumptions. In this context, we introduce an advanced query and reasoning system, GraphAide, which constructs a knowledge graph (KG) from diverse sources and allows to query and reason over the resulting KG. GraphAide harnesses both the KG and LLMs to rapidly develop domain-specific digital assistants. It integrates design patterns from retrieval augmented generation (RAG) and the semantic web to create an agentic LLM application. GraphAide underscores the potential for streamlined and efficient development of specialized digital assistants, thereby enhancing their applicability across various domains.

Purohit, Sumit [BATTELLE (PACIFIC NW LAB)] (ORCID:↗
DOE OSTI2026

A roadmap toward scaling, reasoning and self-evolving foundation models for nuclear and particle physics

Foundation models have revolutionized artificial intelligence, with Large Language Models demonstrating unprecedented capabilities in multimodal understanding, reasoning and tool use. Nuclear and particle physics stands at a critical juncture where similar transformative potential awaits realization. The field generates exabytes of experimental data, exascale simulations, and decades of theoretical insights — yet these remain largely disconnected from modern Artifical Intelligence (AI) capabilities, with most physics AI applications confined to narrow, task-specific models that suffer from domain shifting when applied to real experimental data. We present a roadmap for FM4NPP (Foundation Model for Nuclear and Particle Physics), systematically scaling from current proof-of-concept models to trillion-parameter architectures capable of autonomous discovery. Our approach advances three critical frontiers: unified data infrastructure integrating detector data, scientific knowledge and computational tools across global facilities; multi-facility foundation models enabling cross-experiment knowledge transfer and accelerated discovery; and agentic AI capabilities for reasoning and autonomous tool use. The resulting self-evolving FM4NPP will transform physics research by converting time-intensive data analysis, theory derivation and computational bottlenecks into rapid AI–human collaborative discovery. This paradigm shift promises to fundamentally accelerate scientific progress in nuclear and particle physics, enabling researchers to focus on high-level insights while AI handles routine analysis and explores vast parameter spaces beyond human capacity.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗