Search NASA⌕ Search

SEARCH · Search NASA

Results for “agent safety”

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 OSTI2026

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)↗
DOE OSTI2025

Three‐trophic level food webs support the safety of a biocontrol agent 3 years after release

Biological control (biocontrol) is a powerful tool for managing invasive alien species and assisting the restoration of native ecosystems. Rigorous post‐release monitoring of biocontrol agents is critical to evaluate the success of biocontrol programs; however, this is still rarely implemented. Here, we combined the use of species interaction networks with a Before‐After Control‐Impact design to evaluate the target and non‐target, direct and indirect effects of the Australian gall wasp Trichilogaster acaciaelongifoliae , released to control the invasive plant Acacia longifolia in Portugal. We compared the structure of plant‐galling insect‐parasitoid food webs before and 3 years after the release of the biocontrol agent. Exhaustive sampling did not detect any non‐target effects, either direct (on non‐target plants) or indirect (on other galling insects via shared plants). Additionally, no significant changes were detected in network structure that could be related to the establishment of the biocontrol agent. This study shows that monitoring biocontrol at the community level is possible and that, when carefully planned, biocontrol poses minimal risk of non‐target effects.

López‐Núñez, Francisco A. [Centre for Functional E↗
DOE OSTI2024

The safety of magnetic resonance imaging contrast agents

Gadolinium-based contrast agents are increasingly used in clinical practice. While these pharmaceuticals are verified causal agents in nephrogenic systemic fibrosis, there is a growing body of literature supporting their role as causal agents in symptoms associated with gadolinium exposure after intravenous use and encephalopathy following intrathecal administration. Gadolinium-based contrast agents are multidentate organic ligands that strongly bind the metal ion to reduce the toxicity of the metal. The notion that cationic gadolinium dissociates from these chelates and causes the disease is prevalent among patients and providers. We hypothesize that non-ligand-bound (soluble) gadolinium will be exceedingly low in patients. Soluble, ionic gadolinium is not likely to be the initial step in mediating any disease. The Kidney Institute of New Mexico was the first to identify gadolinium-rich nanoparticles in skin and kidney tissues from magnetic resonance imaging contrast agents in rodents. In 2023, they found similar nanoparticles in the kidney cells of humans with normal renal function, likely from contrast agents. We suspect these nanoparticles are the mediators of chronic toxicity from magnetic resonance imaging contrast agents. This article explores associations between gadolinium contrast and adverse health outcomes supported by clinical reports and rodent models.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

Optimal CO 2 storage management considering safety constraints in multi-stakeholder multi-site GCS projects: A Markov game perspective

Geological carbon storage (GCS) projects could involve a diverse array of stakeholders or players from public, private, and regulatory sectors, each with different objectives and responsibilities. Given the complexity, scale, and long-term nature of GCS operations, determining whether individual stakeholders can independently optimize their interests — or whether collaborative coalition agreements are needed — remains a central question for effective GCS project planning and management. To access large, high-quality storage resources, future GCS deployment may increasingly occur in geologically connected sites, where shared geological features such as pressure space and reservoir pore capacity can lead to competitive behavior among stakeholders. In this work, we propose a paradigm based on Markov games to quantitatively investigate how different coalition structures affect the goals of stakeholders. We frame this multi-stakeholder multi-site problem as a multi-agent reinforcement learning problem with safety constraints. Our approach enables agents to learn optimal strategies while complying with safety regulations. We present an example where multiple operators are injecting CO 2 into their respective project areas in a geologically connected basin. To address the high computational cost of repeated simulations of high fidelity models, a previously developed surrogate model based on the Embed-to-Control (E2C) framework is employed. Our results demonstrate the effectiveness of the proposed framework in addressing optimal management of CO 2 storage when multiple stakeholders with different objectives and goals are involved.

58 GEOSCIENCES↗
DOE OSTI2026

A Physics-Informed Reinforcement Learning Framework for Economic-Thermal Co-Optimization of Crypto Mining Data Centers: Preprint

The rapid expansion of cryptocurrency mining has created a new class of high-density data centers characterized by extreme thermal flux and high sensitivity to volatile economic markets. Traditional thermal management strategies, typically reliant on rule-based control, maintain static setpoints that fail to account for fluctuating electricity prices and cryptocurrency values - factors critical to mining profitability. To address this, we present a physics-informed reinforcement learning (PIRL) framework for economic-thermal co-optimization in crypto mining data centers. This framework consists of a proximal policy optimization (PPO) agent, a virtual testbed powered by high-fidelity physics-based models, and an interactive frontend dashboard. The PPO agent is trained using the virtual testbed and strict hardware safety limits. This physics-informed approach allows the agent to learn a stochastic policy that dynamically balances mining revenue against operational costs by co-optimizing HVAC cooling setpoints and IT computational hashrate. The simulation results demonstrate that the integrated framework achieved an 8.62% increase in net operational profit compared to traditional baseline strategies while strictly adhering to safety-critical temperature constraints (coolant supply temperature < 32 degrees C). This work provides a scalable template for the deployment of reinforcement learning in mission critical facilities where economic volatility and physical safety must be managed simultaneously.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2026

Optimization and stabilization of Fermilab Booster using hybrid Bayesian/RL framework

PIPII project will raise Fermilab Booster intensity and ramp rate. Beam losses will limit average power and are hard to simulate. Presently, Booster uses operator-guided empirical tuning. This task is challenging due to high dimensionality, multiple objectives, critical safety constraints, and drifts. We developed a synergistic suite of Bayesian optimization (BO) and reinforcement learning (RL) tools to optimize and stabilize beam losses. First, active learning was used to build a rough model. Data was collected parasitically using two novel safety constraint types – nonlinear input space restrictions (based on optics model), and uncertainty constraints (to stop bad steps/beam aborts). We then applied online multi-objective BO with scalarized objectives and fitting to improve/rebalance losses, increasing safety margins by 25%. Using BO model as a safety veto, we tried several on/off-policy RL agents for long term stabilization; SAC had best performance. We found that adding contextual (state) information further improved performance, eventually integrating key knobs like linac phase and temperature into the parameter space. Long term testing is ongoing to enable operational use.

Kuklev, Nikita [Fermilab]↗
DOE OSTI2026

REFSafE: A RAG-Enabled Framework for Predictive Risk Analysis and Automated Safety Report Generation in Mission-Critical Environments

Operational safety in mission-critical environments requires AI systems that are accurate, interpretable, and resistant to hallucination. We present an agentic Retrieval-Augmented Generation (RAG) framework, REFSafe, for grounded hazard analysis and automated safety report generation. The system integrates Large Language Models (LLMs) with structured operational data, historical incident repositories, policy documents, and external authoritative sources. Through iterative agentic reasoning, the framework retrieves, verifies, and synthesizes evidence prior to generation, enforcing citation-backed outputs with explicit source attribution (documents, links, and prior events) to ensure traceability and trust. To mitigate hallucinations and unsupported claims, all risk assessments and forecasts are constrained to retrieved evidence, with confidence signals derived from retrieval relevance and source consistency. A transparent pipeline enables subject matter experts (SMEs) to validate predictions, and provide structured feedback, forming a continuous performance calibration loop. Preliminary deployment demonstrates improved reliability in hazard detection and safety/vulnerability report generation. This work advances trustworthy, evidence-grounded AI for predictive safety intelligence in mission-critical operations.

Das, Sanjay [ORNL] (ORCID:0009000542591915)↗
DOE OSTI2025

ADEPT: A Pedagogical Framework for Integrating Agentic AI with Deterministic Scientific Workflows

The integration of Large Language Models (LLMs) into scientific research promises to accelerate discovery, yet a significant gap remains between the dynamic reasoning of Artificial Intelligence (AI) agents and the static, deterministic nature of canonical scientific workflows. This paper introduces ADEPT (Agentic Discovery and Exploration Platform for Tools), a reference architecture and pedagogical framework explicitly designed to bridge this gap. ADEPT's primary mission is to provide a transparent, "glass-box" environment where researchers and engineers can learn to effectively wrap established scientific software (e.g., BLAST, Nextflow pipelines) and compose it into reliable, agent-driven workflows. We describe its modular, multi-server architecture, which leverages the Model Context Protocol (MCP) for tool serving, LangGraph for robust agentic orchestration, and a secure nsjail-based sandbox for safe code execution. By prioritizing architectural clarity, safety, and modularity, ADEPT serves as an extensible blueprint for building trustworthy AI-augmented systems and fosters the collaborative development necessary to responsibly employ agentic AI for science. We provide practical examples of how to adapt and extend this framework, highlighting its utility in workforce development and AI-readiness capabilities across research and development projects.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

A multi-scale cognitive interaction model of instrument operations at the Linac Coherent Light Source

The Linac Coherent Light Source (LCLS) is the world’s first x-ray free electron laser. It is a scientific user facility operated by the SLAC National Accelerator Laboratory, at Stanford, for the U.S. Department of Energy. As beam time at LCLS is extremely valuable and limited, experimental efficiency—getting the most high quality data in the least time—is critical. Our overall project employs cognitive engineering methodologies with the goal of improving experimental efficiency and increasing scientific productivity at LCLS by refining experimental interfaces and workflows, simplifying tasks, reducing errors, and improving operator safety and stress. Here, in this study, we describe a multi-agent, multi-scale computational cognitive interaction model of instrument operations at LCLS. Our model simulates the aspects of human cognition at multiple cognitive and temporal scales, ranging from seconds to hours, and among agents playing multiple roles, including instrument operator, real time data analyst, and experiment manager. The model can roughly predict impacts stemming from proposed changes to operational interfaces and workflows. Example results demonstrate the model’s potential in guiding modifications to improve operational efficiency. We discuss the implications of our effort for cognitive engineering in complex experimental settings and outline future directions for research. The model is open source, and the videos of the supplementary material provide extensive detail.

47 OTHER INSTRUMENTATION↗
DOE OSTI2026

LDRD FY25 Program Overview

As Lawrence Livermore National Laboratory’s (LLNL’s) Laboratory Directed Research and Development (LDRD) program enters its fifth decade of leading-edge research and development, its impact and importance have never been stronger. The program continues to advance strategic investments in pioneering science, technology, and engineering, ensuring LLNL will be ready to deliver on our mission as it evolves over the coming decades. Investing in LDRD research, and the people who perform this critical work, gives LLNL the ability to sustain our role as a leader in the Department of Energy and National Nuclear Security Administration enterprise. The LDRD program enables high-risk, high-payoff research that anticipates emerging threats and future mission needs. By nurturing the ingenuity of the Lab’s greatest asset, its people, LDRD funding advances not only our research but also grows and nurtures our workforce: engaging future innovators with student mentoring, challenging postdoctoral researchers to apply their skills to support national security, and strengthening the leadership skills of early career staff. This annual report documents how LDRD investments advance LLNL’s science, technology, and engineering across our mission space. To assess LDRD’s impact we track both short and long-term metrics such as peer-reviewed publications, number of students, or professional fellows. In addition to reviewing these metrics, I encourage you to delve deeper into the breadth of science and technology that illustrate the strategic value of this research portfolio. For instance, a recent exploratory research project used advanced manufacturing to construct miniaturized three-dimensional ion traps for a quantum computer with reduced quantum error rates to enable applications that address national security missions and support basic science. Another project has delved into studying detonation by examining deflagration to enhance the safety and security of the nuclear weapons stockpile. LDRD researchers are also deploying AI agents on two of the world’s most powerful supercomputers to automate and accelerate inertial confinement fusion experiments. Other teams are delivering more accurate optical constants to enable improved validation for aluminum to advance atomic and molecular physics models. LDRD-driven discoveries of how metals deform under extreme conditions strengthen our ability to model and design materials for demanding national security environments. National security challenges are increasingly complex and continuously evolving. LDRD focuses our most innovative science and technology on these challenges, ensuring the Laboratory is developing creative, forward-leaning solutions for our nation and the world. The following pages feature highlights of published scientific advances, patents, and honors that stem from LDRD investments. As you read this report, I hope you will understand how these investments position the Laboratory, and our partners, to meet the demands of the decades ahead.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Antimicrobial Peptides Can Facilitate Whole Blood Safety from Bacteria: A Proof of Concept

With continuous improvements to blood donor deferrals and the availability of sensitive tests for donation screening for infectious agents, bacterial contamination of whole blood (WB) and blood components stored for transfusion is a rare event. Nonetheless, it still occurs and remains a transfusion-associated risk in terms of septic transfusion reactions (STRs) and transfusion-transmitted bacterial infections with morbidity and mortality outcomes. One of the risk mitigation strategies for bacterial contamination is to implement treatment with currently available proactive pathogen reduction technologies (PRTs) for these transfusion products. Here, as a proof of concept, we tested two recently developed unique cationic antimicrobial peptides (AMPs; D-CONGA and D-CONGA-Q7) for WB safety from bacterial contamination. In this study, WB was inoculated with Escherichia coli and Staphylococcus epidermidis and treated with the two peptides to evaluate their bactericidal efficacy. The results demonstrated that D-CONGA and D-CONGA-Q7 exhibit potent inhibitory activity against the bacteria with a minimal inhibitory concentration (MIC) range of 4–8 and 1–8 μM, respectively, depending on the bacterial species tested. Time-kill kinetics further confirmed that the peptides exhibit bactericidal efficacy at 8 μM by achieving a 5-log 10 reduction (99.999%) of the bacterial load in WB with a time-dependent killing profile. Furthermore, even at 20 μM, the AMPs did not negatively impact hemolysis or hemostatic properties. We have further demonstrated using a cationic exchange resin that the cationic AMPs can be separated and removed from WB after the peptide treatments. During 35-day WB storage at 2–8 °C, 4 μM D-CONGA-Q7 one-time treatment prevented S. epidermidis growth and preserved WB quality and integrity. Overall, the results described here provide the first proof of concept that certain AMPs, such as D-CONGA and D-CONGA-Q7, can facilitate WB safety from bacteria during storage.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Incentivizing Cooperative Merging Control: Insights from Multi-Agent Deep Reinforcement Learning

Cooperative driving automation enables connected and automated vehicles (CAVs) to devise cooperative merging control, introducing great potentials to alleviate traffic congestion, reduce energy consumption, and enhance safety for highway on-ramp operations. Although numerous CAV cooperative merging algorithms have been developed to improve energy and traffic performance, the agreement-seeking among CAV users and their local benefits have been understudied. This can lead to rejections of cooperative merging plans and jeopardizing CAV performance, as a cooperation may entail certain CAVs to sacrifice their local benefits to achieve a system optimum. To address this issue, the study first leverages multi-agent deep reinforcement learning (MADRL) factoring both local reward and regional reward to demonstrate the discrepancies between CAV users’ local benefits and system optimum. Next, the existence of a correlated equilibrium is proved to characterize the convergence of MADRL training. This further facilitates the incorporation of incentives (computed based on reward discrepancies) to compensate for CAV users’ local benefits and facilitate system-optimal agreements in cooperative merging operations.

Zhou, Anye [ORNL] (ORCID:0000000301455579)↗
DOE OSTI2025

Developing aqueous solubilizing agents as an alternative to solvent extraction

Here, advancing separations science is important for the entire field of chemistry. One partitioning technique that would benefit from improvement is solvent extraction. Despite its effective and widespread use, the method suffers from some problems: generation of flammable organic waste, lengthy process times, and safety concerns associated with contacting organic solvents with acidic aqueous solutions. We developed an alternative separation method inspired by solvent extraction that side-steps those issues. Toward this end, we identified that the functionality of an extractant (an agent used in solvent extraction to pull analytes from the aqueous phase into the organic phase) would change if it was modified for water solubility. In this alternative scenario, the extractant transforms into an “aqueous solubilizing agent.” We discovered that adding this aqueous solubilizing agent alongside a precipitating agent caused the contaminants to precipitate, but not the analyte. This separation concept was demonstrated within the bounds of one of the most difficult partitioning problems, separating minor actinides (Am 3+ ) from lanthanides (Ln 3+ ). We discovered that the (HSO 3 Ph) 4 BTP (aq) aqueous solubilizing agent prevented Am 3+ (aq) from precipitating with Ln 3+ (aq) when f-element precipitating agents (NaF (aq) or HF (aq) ) were added. This separation boasts impressive Am 3+ (aq) recovery yield (90 ± 2 %), near quantitative Ln 3+ (aq) removal, and high separation factors [>3000, Am 3+ (aq) vs. Nd 3+ (aq) ]. It seems likely – given the large number of candidate extractants that could be modified for aqueous solubility and the numerous combinations of existing solubilizing and precipitating agents – that this alternative approach could be used broadly in place of solvent extraction and solve other important separation problems.

(HSO3Ph)4BTP(aq)↗
DOE OSTI2026

Development and Implementation of a New AI-Based Tool to Support Fast Reactor Software Model Generation and Validation

This report summarizes FY26 work to develop Maggie, an artificial intelligence-based assistant designed to support software model generation and validation activities for fast reactor analysis codes. The project established a modular, code-agnostic software architecture that separates reusable agent capabilities from code-specific knowledge and tools, with initial implementation focused on the FRP-supported fast reactor safety analysis code SAS4A/SASSYS1 (SAS). A curated SAS-specific knowledge base was assembled from the code manual, training materials, historical analysis reports, and representative input files, and was integrated through retrieval-augmented generation to ground Maggie’s responses in authoritative sources. Maggie was deployed on the internal Argonne network, where it demonstrated practical user-facing capability as a chatbot for answering natural language questions about SAS and retrieving relevant technical information. Demonstration cases also showed that Maggie can generate useful snippets of SAS input for selected modeling tasks, while highlighting current limitations in reliability and consistency for more complex input generation tasks. Overall, the FY26 effort established the technical foundation for an AI-assisted capability intended to improve the efficiency, consistency, and accessibility of fast reactor software model development at Argonne and, with further improvements, to support eventual use by the broader fast reactor community, including industry users of FRP-supported analysis tools.

Thomas, Rachel [Argonne National Laboratory (ANL),↗
DOE OSTI2025

OR-AGENT framework – Architecting electrified heavy-duty drayage applications

The widespread adoption of zero-emission vehicles in heavy-duty (HD) commercial freight transportation faces considerable technoeconomic challenges. For heavy-duty trucks, ensuring high uptime, cost parity with diesel, and safety standards is especially critical as these vehicles operate over long distances with heavy loads, where any downtime or off-nominal behaviors significantly impacts logistics, productivity, and the total cost of ownership. Unlike traditional diesel refueling, BEV charging infrastructure must be co-optimized with vehicle deployment, operational demands, and grid capacity to ensure cost-effective and reliable freight operations. However, the lack of a standardized ownership and service model has led to a fragmented approach—where commercial vehicle operators may invest in, own, and maintain both vehicle/batteries and charging/energy infrastructure. This disconnect may exclude energy service providers from the equation, forcing fleet operators to explore ‘behind-the-fence’ energy solutions that increase capital investment, operational downtime, overhead costs, and, in some cases, net carbon emissions. To address these issues, this study introduces OR-AGENT (Optimal Regional Architecture Generation for Efficient National Transport), a comprehensive modeling framework that integrates powertrain architectures, charging infrastructures, and energy backbone systems into a cohesive strategy. In this paper, OR-AGENT is applied to develop an interconnected systems architecture for energy efficiency and resiliency enhancement of heavy-duty drayage vehicles at the Port of Savannah, GA. This framework showcases an interconnected systems approach to electrifying heavy-duty drayage vehicles at the Port of Savannah, GA. The study assessed BEVs with 400–1200 kWh battery capacities, accounting for seasonal variations in weather and freight routing. A diverse charging mix (150 kW–1250 kW) was evaluated alongside grid capacity constraints, cost, and carbon intensity analysis, leading to the development of a strategic microgrid/Distributed Energy Resources (DER) deployment architecture to ensure a reliable and sustainable transition. However, the findings also highlight the need for alternative zero-emission solutions for remaining trips, such as larger batteries, electrified roadways, hydrogen powertrains, or net-zero emission fuels. In conclusion, the findings are incorporated into a Total Cost of Ownership (TCO) model to identify optimal architectures for an interconnected electrified ecosystem.

Commercial vehicles↗
DOE OSTI2026

Agentic artificial intelligence for multistage physics experiments at a large-scale user facility particle accelerator

We present a language-model-driven agentic artificial intelligence (AI) system to autonomously execute multistage physics experiments on a production synchrotron light source. Implemented at the Advanced Light Source particle accelerator, the system translates natural language user prompts into structured execution plans that combine archive data retrieval, control-system channel resolution, automated script generation, controlled machine interaction, and analysis. In a representative machine physics task, we show that preparation time was reduced by 2 orders of magnitude relative to manual scripting even for a system expert, while operator-standard safety constraints were strictly upheld. Core architectural features, plan-first orchestration, bounded tool access, and dynamic capability selection, enable transparent, auditable execution with fully reproducible artifacts. These results establish a blueprint for the safe integration of agentic AI into accelerator experiments and demanding machine physics studies, as well as routine operations, with direct portability across accelerators worldwide and, more broadly, to other large-scale scientific infrastructures.

Accelerator/storage ring control systems↗
DOE OSTI2025

High-Density, Low-Hysteresis Storage Using Hydrated Salts in Surface-Functionalized Hydrogels (Final Technical Report)

Nearly 70 years ago, Glauber’s salt was identified as a leading phase change material (PCM) in terms of its heat storage density (~2x paraffin), thermal conductivity (~1W/m·K), safety, availability and cost (~$\$$100/ton). However, the complex issues of supercooling and incongruent melting due to phase separation have prevented realization of the promise. The addition of thickeners and nucleating agents such as borax solve these issues but only over few cycles. This work aims to (a) resolve long-standing challenges with Glauber’s salt as a thermal storage material through a unique materials approach, (b) to characterize the new material’s properties that are relevant to performance and (c) to explore its incorporation into commercial water heaters. The materials concept involves encapsulating the salt in custom-designed, large-mesh hydrogels that enable breakthrough advances. Specifically, (1) the choice of mesh size and polymer chemistry control diffusion of salt/water and help to eliminate phase segregation. With the hydrogel itself occupying <10% volume, there is little loss in storage density compared to another encapsulation. (2) Specific nucleation centers that covalently tether to the hydrogel trigger heterogeneous nucleation, eliminating supercooling-associated hysteresis losses. The fact that they are spatially tethered, prevents the loss in performance over multiple freeze/thaw cycles (>100). We report extensive characterization of the hydrogel complex in terms of its storage density, freezing/melting temperature, cycling losses, rheological properties, aging and thermal conductivity. The novel material developed in this work is a significant advancement over the state-of-art. Finally, we investigate its potential as a thermal storage material for commercial/residential water heating and identify scenarios in which its deployment is advantageous.

25 ENERGY STORAGE↗
DOE OSTI2026

GridCoPilot for Thermal Events: An LLM-Based Platform for Power Grid Reliability Analysis

Large Language Models show promise for translating natural language into database queries, but deploying such systems in safety-critical domains requires high reliability. We present an application of GridCoPilot to thermal event analysis (heatwaves and coldwaves) that affect power grid reliability. Our approach uses a LangChain SQL Agent to translate natural language queries into auditable SQL statements, with deterministic visualization routines that parse the structured query results. We introduce structural framing as a design principle, we integrate a NERC-region-level event library with county-level meteorology and decompose the combined data into three relational tables (event metadata, county-level event details, and a county-to-NERC subregion mapping), using prompt-guided joins to direct the model toward correct multi-table queries. For two core analytical patterns (identifying worst events by region and by region-year), the system achieved 100% SQL accuracy across all 16 NERC subregions and both event types (64 queries total). These results validate the approach for target use cases, though performance on diverse natural language formulations requires further investigation. We discuss design trade-offs, failure modes including JSON output truncation, and pathways for extending this approach to other hazard domains.

24 POWER TRANSMISSION AND DISTRIBUTION↗