Search NASA⌕ Search

SEARCH · Search NASA

Results for “Agent”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Multi-Agent Hierarchical Deep Reinforcement Learning for HVAC Control With Flexible DERs

As electricity consumption in commercial and residential buildings continues to rise, reducing energy costs presents an increasing challenge. Heating, ventilating, and air-conditioning (HVAC) systems, which typically account for 40%-50% of a building's energy use, are prime targets for energy savings. Intelligent control of HVAC temperature through the exploitation of HVAC load flexibility brings significant potential to reduce energy consumption and electricity expenses. The nonlinear models of HVAC systems challenge traditional control methods, while the uncertainty introduced by HVAC load flexibility complicates distributed energy resource (DER) management using conventional optimal dispatch techniques. In response to these challenges, we propose a hierarchical multi-agent deep reinforcement learning (DRL) approach. The lower-level agents focus on balancing comfort and energy conservation, while the upper-level DRL agents optimize the use of DERs to reduce peak demand based on the control outcomes of the HVAC by the lower-level agents. Here, in the upper-level agents, we incorporate a multi-agent structure based on ensemble learning, which acts based on historical and current data without relying on precise load forecasting to address the delayed rewarding issue in DRL. This allows for the effective reduction of energy costs. The proposed method is tested using a real-world microgrid comprising 413 buildings in Southern California, and the results demonstrate that our approach can significantly reduce overall electricity bills while ensuring the comfort of consumers and residents.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

matsim-agents v1.0

matsim-agents is a multi-agent AI framework for atomistic materials simulation and discovery. It orchestrates large language models (LLMs), machine-learned interatomic potentials (MLIPs), and DFT codes into a single agentic loop running on laptops and DOE leadership-class supercomputers. MULTI-AGENT ORCHESTRATION A LangGraph state machine with three nodes: a Planner that converts a natural-language research objective into structured tasks; an Executor that dispatches atomistic tools and loops until the queue is empty; and an Analyst that summarizes results into a human-readable report. State is checkpointed after every step and human-in-the-loop gates can be inserted at any edge. HYPOTHESIS-DRIVEN DISCOVERY CHAT An interactive REPL (matsim-agents chat) that couples LLM dialogue with atomistic simulation. Chemical formulas are automatically detected in conversation turns and trigger a full crystal-phase exploration: structure generation → relaxation → stability scoring → result injection back into the conversation, creating a closed hypothesis-refinement loop. CRYSTAL PHASE ENUMERATION Given a composition, the phase explorer enumerates prototypes by stoichiometry: elemental (fcc/bcc/hcp/sc/diamond), binary 1:1 (rocksalt/CsCl/zincblende/ wurtzite/fluorite/rutile), ternary 1:1:3 (cubic perovskite), ternary 1:2:4 (perovskite + spinel), quaternary 1:1:2:6 (Fm-3m double perovskite). 2-D prototypes (graphene, h-BN, MoS2 2H/1T) and multilayer stacking are also supported via --include-2d and --num-layers. SUPERCELL GENERATION AND SITE DECORATION Auto-tiling to a minimum atom count (--min-atoms), explicit NxNxN tiling (--supercell), symmetry-distinct site decorations (--n-orderings), and isotropic lattice-scale sweeps (--lattice-scales) for volume bracketing. MLFF RELAXATION AND STABILITY SCORING HydraGNN (multi-headed GNN) drives structure relaxation via ASE with FIRE, BFGS, or BFGSLineSearch. Stability output: delta-E/atom ranking across phases and a max-residual-force dynamical-stability proxy. Other MLIPs (MACE, NequIP, Orb) can be plugged in through the same interface. DFT BACKENDS Quantum ESPRESSO pw.x and VASP 6.6 are first-class labellers. Both have validated GPU builds and SLURM/PBS launchers for three DOE platforms: Frontier (AMD MI250X, ROCm), Aurora (Intel PVC, oneAPI), Perlmutter (NVIDIA A100, CUDA). QE produces ~100 binaries (pw.x, ph.x, epw.x, ...). VASP supports scf, relax, vc-relax, and vc-relax-shape run types. ACTIVE-LEARNING LOOP matsim-agents al run CONFIG.yaml drives an iterative HydraGNN-DFT loop: MD generates candidates → ensemble/MC-dropout uncertainty selects the most informative → DFT labels them in parallel inside one allocation → dataset grows → HydraGNN retrains → repeat. DFT backend is a single YAML toggle (dft.backend: vasp | qe). LLM-generated seed structures are supported (no curated POSCAR library needed). Config uses ${VAR}, ${VAR:-default}, ${VAR:?msg} shell-style substitution for cross-user/cross-site portability. LLM BACKENDS Ollama (local, default), vLLM (HPC multi-GPU serving), OpenAI, Anthropic, HuggingFace Transformers+Accelerate. Selected at runtime via flag or env var with no code changes. HPC PORTABILITY Same Python entry points run on Frontier (ROCm 7.2), Aurora (oneAPI), and Perlmutter (CUDA 12). DFT and ML stacks are never co-loaded in the same shell; they couple through the scheduler and filesystem. Advanced multi-node launchers (serve, discovery-chat, single-relaxation, active-learning, QE warm-start) are provided for all three platforms. CODABENCH COMPETITION BUNDLE A self-contained benchmark: 159 atomistic test structures across 11 material classes, 5 tasks (formation energy, forces, ML relaxation, AI-DFT relaxation, phase stability ranking), public/private leaderboard split (30/70), and four ready-to-run baselines: MACE-MP-0, HydraGNN, UMA, AllScAIP.

Lupo Pasini, Massimiliano [Oak Ridge National Labo↗
DOE OSTI2026

Multi-Agent Control Planes for Quantum Networks: A Scalable Architecture for Autonomous Quantum Internet Management

Quantum networks are expected to enable distributed quantum computing, secure communication, and global entanglement distribution. However, operating such networks presents significant challenges, including stochastic quantum processes, fragile entanglement resources, dynamic topology, and cross-layer control requirements. Current quantum network control architectures largely rely on centralized or hierarchical controllers inspired by classical software-defined networking (SDN). While effective for small testbeds, these approaches face scalability, latency, and reliability limitations as quantum networks grow. This paper proposes a multi-agent control plane architecture for quantum networks. In this design, intelligent software agents operate at quantum nodes, repeaters, and orchestration layers, collectively managing entanglement generation, routing, purification, and scheduling. The distributed intelligence of the agent system allows the network to adapt dynamically to quantum hardware variability and environmental noise. We argue that multi-agent systems provide significant advantages over centralized control approaches, including scalability, resilience, local autonomy, and real-time adaptation. The paper discusses architectural design principles, agent coordination mechanisms, and research challenges in deploying multi-agent control planes for the emerging quantum Internet.

Alnajjar, Anees [ORNL] (ORCID:0000000237101601)↗
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 OSTI2026

NeuDiff Agent: a governed AI workflow for single-crystal neutron crystallography

Large-scale facilities increasingly face analysis and reporting latency as a limiting step in scientific throughput, particularly for structural studies that require iterative reduction, integration, refinement and validation. To improve the time to result and analysis efficiency, NeuDiff Agent is introduced as a governed, tool-using AI workflow for TOPAZ at the Spallation Neutron Source. NeuDiff Agent takes instrument data through reduction, integration, refinement and validation to a validated crystal structure and a publication-ready CIF. NeuDiff Agent coordinates established crystallographic tools under explicit governance by restricting actions to allowlisted tools, enforcing fail-closed verification gates at key workflow boundaries, and capturing complete provenance for inspection, auditing and controlled replay. The present benchmark is limited to structural crystallography for periodic structures; magnetic structure analysis and incommensurate or superspace refinement are outside the scope of the current workflow. Performance is assessed using a fixed prompt protocol and repeated end-to-end runs with two large language model backends, with user and machine time partitioned and intervention burden and recovery behaviors quantified under gating. In a reference-case benchmark, NeuDiff Agent reduces wall time from 435 min (manual) to 86.5 ± 4.7 to 94.4 ± 3.5 min (4.6–5.0× faster) while producing a validated CIF with no checkCIF level A or B alerts. These results establish a practical route to deploy agentic AI in facility crystallography while preserving traceability and publication-facing validation requirements.

Xiao, Zhongcan [ORNL] (ORCID:0000000220761961)↗
DOE OSTI2025

Meta Biome: a multiscale model integrating agent-based and metabolic networks to reveal spatial regulation in gut mucosal microbial communities

ABSTRACT Mucosal microbial communities (MMCs) are complex ecosystems near the mucosal layers of the gut essential for maintaining health and modulating disease states. Despite advances in high-throughput omics technologies, current methodologies struggle to capture the dynamic metabolic interactions and spatiotemporal variations within MMCs. In this work, we presentMetaBiome, a multiscale model integrating agent-based modeling (ABM), finite volume methods, and constraint-based models to explore the metabolic interactions within these communities. Integrating ABM allows for the detailed representation of individual microbial agents each governed by rules that dictate cell growth, division, and interactions with their surroundings. Through a layered approach—encompassing microenvironmental conditions, agent information, and metabolic pathways—we simulated different communities to showcase the potential of the model. Using ourin-silicoplatform, we explored the dynamics and spatiotemporal patterns of MMCs in the proximal small intestine and the cecum, simulating the physiological conditions of the two gut regions. Our findings revealed how specific microbes adapt their metabolic processes based on substrate availability and local environmental conditions, shedding light on spatial metabolite regulation and informing targeted therapies for localized gut diseases.MetaBiome provides a detailed representation of microbial agents and their interactions, surpassing the limitations of traditional grid-based systems. This work marks a significant advancement in microbial ecology, as it offers new insights into predicting and analyzing microbial communities. IMPORTANCE Our study presents a novel multiscale model that combines agent-based modeling, finite volume methods, and genome-scale metabolic models to simulate the complex dynamics of mucosal microbial communities in the gut. This integrated approach allows us to capture spatial and temporal variations in microbial interactions and metabolism that are difficult to study experimentally. Key findings from our model include the following: (i) prediction of metabolic cross-feeding and spatial organization in multi-species communities, (ii) insights into how oxygen gradients and nutrient availability shape community composition in different gut regions, and (iii) identification of spatiallyregulated metabolic pathways and enzymes inE. coli. We believe this work represents a significant advance in computational modeling of microbial communities and provides new insights into the spatial regulation of gut microbiome metabolism. The multiscale modeling approach we have developed could be broadly applicable for studying other complex microbial ecosystems.

Microbiology↗
DOE OSTI2026

Building MCP-native hierarchical AI scientist ecosystems: a perspective on scaling multi-agent scientific discovery

Large language models (LLMs) are evolving from chatbots with limited tool-using capabilities to agentic AI systems that can perform deep research, assist in proposing hypotheses, help design experiments, automate data analysis, and draft scientific reports. However, there are currently two bottlenecks limiting LLMs' real-world impact on the broader scientific research community beyond academic demonstrations: lack of interoperability (repetitive manual tool-integration is required across scenarios) and the need for scalable coordination (unstructured communication and memory become brittle as the number of agents grows). In this Perspective, we argue that the next phase of agentic scientific discovery requires the development of an ecosystem of protocol-native agents and tools organized through hierarchies inspired by human society, beyond the current paradigm of a single monolithic “AI scientist”. We use Model Context Protocol (MCP) as a concrete example of an emerging interoperability layer for scientific tool and context exchange, and we propose three complementary pathways to increase the scaling capabilities of an MCP-native scientific ecosystem by addressing the composability issues: (1) MCP servers for high-value scientific tools maintained by domain experts, (2) automated transformation of existing code repositories into MCP services, and (3) autonomous invention and evolution of new agents and workflows. Finally, we provide a practical roadmap for scaling AI-driven scientific discovery by expanding tool supply and coordination in MCP-native scientific ecosystems.

97 MATHEMATICS AND COMPUTING↗
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 OSTI2024

Towards Agentic AI on Particle Accelerators

As particle accelerators grow in complexity, traditional control methods face increasing challenges in achieving optimal performance. This paper envisions a paradigm shift: a decentralized multi-agent framework for accelerator control, powered by Large Language Models (LLMs) and distributed among autonomous agents. We present a proposition of a self-improving decentralized system where intelligent agents handle high-level tasks and communication and each agent is specialized control individual accelerator components. This approach raises some questions: What are the future applications of AI in particle accelerators? How can we implement an autonomous complex system such as a particle accelerator where agents gradually improve through experience and human feedback? What are the implications of integrating a human-in-the-loop component for labeling operational data and providing expert guidance? We show two examples, where we demonstrate viability of such architecture.

43 PARTICLE ACCELERATORS↗
DOE OSTI2026

Agentic Diagrammatica: Towards Autonomous Symbolic Computation in High Energy Physics

We present Diagrammatica, a symbolic computation extension to the HEPTAPOD agentic framework, which enables LLM agents to plan and execute multi-step theoretical calculations. Symbolic computation poses a distinctive reliability challenge for LLM agents, as correctness is governed by implicit mathematical conventions that are not encoded in a form that can be easily checked in the computational backend. We identify two complementary remedies, tool-constrained computation and targeted knowledge grounding, and pursue the first as the primary architecture. Concretely, we concentrate the agent's action distribution onto tool calls with convention-fixing semantics, in which the agent specifies a compact, human-auditable diagram specification and a trusted backend performs the symbolic or numerical manipulations exactly. The toolkit provides two complementary calculation paths consuming a shared diagram specification: Naive Dimensional Analysis (NDA) for order-of-magnitude rate estimates and Exact Diagrammatic Analysis (EDA) for tree-level symbolic calculations via automatic FeynCalc code generation, both supplemented by automatic Feynman diagram enumeration and a navigable theory knowledge base. The architecture is validated on two benchmarks: (1) an exhaustive catalog of all tree-level, single-vertex $1\to 2$ partial decay widths across scalar, fermion, and vector parents, with complete massless and threshold limits and Standard Model validation; and (2) an NDA sensitivity study of the muon decay multiplicity $μ^+ \to ν_μ\barν_e + n(e^+e^-) + e^-$, determining the maximum observable $n$ at current and planned muon experiments.

Menzo, Tony [Alabama U.; Fermilab] (ORCID:00000002↗
DOE OSTI2026

Agentic traffic intelligence: Augmented human-in-the-loop scenario generation for microscopic traffic simulation

Traditional microscopic traffic simulation generation often relies on static datasets and manual design, limiting its ability to simulate complex conditions easily. This paper presents a novel framework, Agentic Traffic Intelligence, which combines human approval large language models (LLMs), the Real-Twin tool, and multi-agent systems to perform realistic microscopic traffic simulation scenario generation. The proposed framework incorporates human-in-the-loop (HIL) control, retrieval-augmented generation (RAG), and multi-agent control mechanisms. HIL mechanisms are used to guide multiple LLMs focused on attributes for microscopic simulation generation and to improve the interpretability and transparency of LLM execution for users. RAG enhances context extraction by dynamically integrating external knowledge sources for traffic scenario generation foundations. A multi-agent architecture with supervisory control coordinates the interaction of simulation components, including traffic simulators, control logic, and calibration tools. This enables the synthesis of simulation-ready scenarios that reflect dynamic demand profiles and behavior controls. Furthermore, the framework fuses multisource traffic data with unstructured context and supports iterative refinement through interactive user feedback. Validated through microscopic simulation using Simulation of Urban Mobility, the generated scenarios demonstrate high-fidelity network generation with inflow and turn movement and behavioral calibration, offering a robust and efficient tool for stress-testing and optimizing urban mobility systems.

Hierarchical multi-agent control↗
DOE OSTI2025

Multi-scale, Multi-disciplinary, and Multi-agent Explainable AI with Koopman-Undergirded Learning, Prediction, and Analysis (M3EA KULPA) (Project Closeout Report)

The goal of this project was to develop and use domain-aware machine learning formulations, based on the Koopman Operator (KO), for modelling multi-scale, multi-disciplinary (e.g., multi-physics), and/or multi-agent systems. The project developed these formulations for the following cases: • Systems with dynamics at two separate time scales, • Systems with a bi-level hierarchical control structure, • Systems with bi-level hierarchical control and dynamics at two separate time scales (the lower level controls operating at the faster time scale), and • Systems with n separate but interacting agents/disciplines (with/without control, respectively); the controls for each agent could include bi-level hierarchical control and dynamics at two separate time scales as described above. The project then defined a set of dynamical systems consisting of different nonlinear oscillators that could be used to test these different formulations and then subsequently learned the KO models for those systems. With the KO models, we were able to do the following: • Quantify system stability, including both long-term and transient behavior, • Quantify the effects of feedbacks between the different time scales and agents/disciplines in terms of those feedbacks’ effects on system stability, • Replace a standard Proportional-Integral (PI) control in the hierarchical control structure with a KO-based Linear-Quadratic Regular (LQR), a form of optimal control, • Calculate optimal supervisory control policies a) with and without time scale separated dynamics at the lower level control levels and b) with both PI and KO-based LQR lower level control policies, and • Calculate dynamic Nash equilibria for multi-agent systems where each agent makes its own control decisions.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Enhancing Autonomous Control of Microreactors Using Multi-Agent Reinforcement Learning

In order for microreactors to be economically competitive, operation costs will need to be minimized through some degree of autonomous control. Previous work has demonstrated the effectiveness of reinforcement learning (RL) for load-following control in a drum-controlled microreactor. This study extends that work by exploring the potential of RL to independently control each of the reactor’s drums. We compare a single-agent RL approach with a multi-agent RL (MARL) framework, testing them for generalization across different load-following power profiles and control timescales, and for robustness in cases of randomly disabled control drums. Since the point kinetics simulation environment used in this study cannot resolve spatial effects, we assume that in the absence of spatially localized disturbances, optimal drum movements should be symmetrical. We demonstrate that single-agent RL is able to achieve accurate performance only when symmetric actions are ignored; otherwise, it fails to train a useful controller. Meanwhile, the MARL framework performs symmetric actions by design and trains a robust, accurate agent, as evidenced by mean absolute errors in power matching of 0.41% for the training power profile, 0.68% for a profile with half the drums disabled, and 0.21% for a profile on a realistic load-following time horizon.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2026

Desorption Electrospray Ionization–Mass Spectrometry Imaging Provides Spatiochemical Information on Potential Biocontrol Agents against Phytophthora capsici Infection in Tomato Plants

Biological control agents can offer an eco-friendly and more sustainable alternative to conventional chemical pesticides, providing protection against destructive pathogens, such as Phytophthora capsici, while reducing potential environmental harm associated with synthetic pesticide use in agricultural systems. This work evaluates the biocontrol effectiveness of Bacillus vallismortis, Bacillus amyloliquefaciens, Bacillus thuringiensis, and Bacillus subtilis, against the widespread plant pathogen Phytophthora capsici. Our studies showed that Bacillus thuringiensis and Bacillus subtilis promote plant growth and provide protection against Phytophthora capsici in both in vitro and in vivo greenhouse studies, while Bacillus vallismortis and Bacillus amyloliquefaciens were effective in vitro but not in vivo. Specifically, Bacillus thuringiensis was observed to both hinder the growth of Phytophthora capsici and enhance plant resilience to this pathogen, with B. thuringiensis-treated, pathogen-exposed plants displaying a 94.4% increase in root length and a 74.0% increase in shoot height compared to plants with only oomycete exposure. To probe the molecular interactions between the biocontrol agent and pathogen, a dual culture of Bacillus thuringiensis and Phytophthora capsici was analyzed in situ using a desorption electrospray ionization–mass spectrometry imaging (DESI-MSI) workflow. This approach interrogated the spatially oriented biochemical interactions that may serve as the molecular foundation for the effectiveness of these biological control agents in crop protection, identifying seven unique phenotypic regions within the dual culture. Herein, we demonstrate the benefits of biological control agent application in tomato cultivation and showcase the strengths of desorption electrospray ionization–mass spectrometry imaging when applied to the spatially resolved molecular characterization of agriculturally relevant microorganisms.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Data Assimilation for Robust UQ Within Agent-Based Simulation on HPC Systems

Agent-based simulation provides a powerful tool for in silico system modeling. However, these simulations do not provide built-in methods for uncertainty quantification (UQ). Within these types of models a typical approach to UQ is to run multiple realizations of the model then compute aggregate statistics. This approach is limited due to the compute time required for a solution. When faced with an emerging biothreat, public health decisions need to be made quickly and solutions for integrating near real-time data with analytic tools are needed. We propose an integrated Bayesian UQ framework for agent-based models based on sequential Monte Carlo sampling. Given streaming or static data about the evolution of an emerging pathogen this Bayesian framework provides a distribution over the parameters governing the spread of a disease through a population. These estimates of the spread of a disease may be provided to public health agencies seeking to abate the spread. By coupling agent-based simulations with Bayesian modeling in a data assimilation, our proposed framework provides a powerful tool for modeling dynamical systems in silico. We propose a method which reduces model error and provides a range of realistic possible outcomes. Moreover, our method addresses two primary limitations of ABMs: the lack of UQ and an inability to assimilate data. Our proposed framework combines the flexibility of an agent-based model with UQ provided by the Bayesian paradigm in a workflow which scales well to HPC systems. We provide algorithmic details and results on a simulated outbreak with both static and streaming data.

Spannaus, Adam [ORNL] (ORCID:0000000225213657)↗
DOE OSTI2025

Foveal vision reduces neural resources in agent-based game learning

Efficient processing of information is crucial for the optimization of neural resources in both biological and artificial visual systems. In this paper, we study the efficiency that may be obtained via the use of a fovea. Using biologically-motivated agents, we study visual information processing, learning, and decision making in a controlled artificial environment, namely the Atari Pong video game. We compare the resources necessary to play Pong between agents with and without a fovea. Our study shows that a fovea can significantly reduce the neural resources, in the form of number of neurons, number of synapses, and number of computations, while at the same time maintaining performance at playing Pong. To our knowledge, this is the first study in which an agent must simultaneously optimize its visual system, along with its decision making and action generation capabilities. That is, the visual system is integral to a complete agent.

60 APPLIED LIFE SCIENCES↗
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 OSTI2024

Multi-agent voltage control in distribution systems using GAN-DRL-based approach

Active distribution grids can experience voltage fluctuations and violations due to the high penetration of variable distributed energy resources (DERs). These problems might occur because of the uncertain and variable generation natures of these resources, especially solar photovoltaic resources, during panel shadowing scenarios. Volt-VAR control (VVC) is an efficient method that controls the reactive power set-points of the inverters to regulate the voltage of distribution grids. Although several VVC approaches have been proposed recently, the performance of these approaches degrades significantly if behind-the-meter solar generation data are unobservable/missing. Therefore, it is necessary to impute missing/unobservable PV data accurately to be utilized in VVC approaches. Further, this paper proposes a model-free, data-driven, centrally trained, and decentrally executed multi-agent deep reinforcement learning-based VVC architecture to regulate the voltage of distribution networks. A generative adversarial network (GAN) is incorporated to impute the unobservable PV data accurately, which improves the performance of the proposed control architecture. The proposed multi-agent-soft-actor–critic algorithm (MASAC)-based VVC technique utilizes the actual PV dataset as well as the imputed dataset from the GAN framework to learn the optimal coordinated control policy for controlling the optimal reactive power set-points of PV inverters. The effectiveness of the proposed approach is analyzed on a modified IEEE 34-bus test case with added PV inverters. The results are compared and analyzed with a base case model with no VVC and VVC with a local droop control approach, genetic algorithm optimization, and a centralized soft actor–critic-based approach. Moreover, the performance of the proposed approach is compared with that of a multi-agent VVC framework without using the PV generation data and load information as the system state. The results illustrate that the proposed method with more state input improves the voltage profile and reduces the power loss of the network across various loading and PV generation scenarios.

14 SOLAR ENERGY↗