SEARCH · Engineering Papers

Results for “Agents”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

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

At least 73 records · Page 4

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Non-Stationary Policy Learning for Multi-Timescale Multi-Agent Reinforcement Learning

In multi-timescale multi-agent reinforcement learning (MARL), agents interact across different timescales. In general, policies for time-dependent behaviors, such as those induced by multiple timescales, are non-stationary. Learning non-stationary policies is challenging and typically requires sophisticated or inefficient algorithms. Motivated by the prevalence of this control problem in real-world complex systems, we introduce a simple framework for learning non-stationary policies for multi-timescale MARL. Our approach uses available information about agent timescales to define and learn periodic multi-agent policies. In detail, we theoretically demonstrate that the effects of non-stationarity introduced by multiple timescales can be learned by a periodic multi-agent policy. To learn such policies, we propose a policy gradient algorithm that parameterizes the actor and critic with phase-functioned neural networks, which provide an inductive bias for periodicity. The framework's ability to effectively learn multi-timescale policies is validated on a gridworld and building energy management environment.

control↗

DOE OSTI2023

Control of multi-agent systems: Results, open problems, and applications

The purpose of this review article is to present some recent results on the modeling and control of large systems of agents. We focus on particular applications where the agents are capable of independent actions instead of simply reacting to external forces. In the literature, such agents were referred to as autonomous, intelligent, self-propelled, greedy, and others. The main applications we have in mind are social systems (as opinion dynamics), pedestrians’ movements (also called crowd dynamics), animal groups, and vehicular traffic. We note that the last three examples include physical constraints; however, the agents are able to inject energy into the system, thus preventing the typical conservation of momentum and energy. In addition, the control problems posed by such systems are new and require innovative methods. We illustrate some ideas developed recently, including the use of sparse controls, limiting the total variation of controls, and defining new control problems for measures. After reviewing various approaches, we discuss some future research directions of potential interest. The latter encompasses both new types of equations and new types of limiting procedures to connect several scales at which a system can be represented. We conclude by illustrating a recent real-life experiment using autonomous vehicles on an open highway to smooth traffic waves. This opens the door to a new era of interventions to control real-time multi-agent systems and to increase the societal impact of such interventions guided by control research.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2020

Application of Gaussian Bayes classifier to differentiate chlorine-based chemical agents

The Portable Isotopic Neutron Spectroscopy (PINS) is a commercialized system developed by Idaho National Laboratory (INL) to examine chemical warfare agents (CWA) non-destructively, utilizing Prompt Gamma Neutron Activation Analysis (PGNAA) techniques. The PINS system takes advantage of a high-resolution gamma-ray spectrum from a mechanically-cooled high-purity germanium (HPGe) detector. One of the difficult technical challenges is to discriminate the chlorine-based chemical agents. Especially, CN, CNB, CNS and CG have similar chemical compositions to make it hard to discriminate them with a higher confidence. Current identification algorithms for PINS systems with 252-Cf sources have been improved and updated continuously as more field data became available, and new algorithms was studied to complement the current algorithms by adopting the Gaussian Bayes classifier. These new algorithms were intended to be applied to a subset of chlorine-based chemical agents, and their main goal is discriminate CN, CNB, CNS and CG with their ratios of the chlorine neutron inelastic 1763keV peak to the chlorine thermal neutron capture 1959keV peak, which is referred to as the “Cl i/c” or “clic” ratio in this study. The Cl i/c ratios were assumed to follow Gaussian distributions with the means and the standard deviations unique to their corresponding chemical agents. The prior probabilities of these four chemical agents were optimized with a collection of field data to achieve the best performance in terms of precision or positive predictive value (PPV). Finally, their posterior probabilities as functions of the Cl i/c ratio were implemented in the current version of PINS analysis software in order to be tested with more field data.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗

DOE OSTI2020

Janus: A Python Package for Agent-Based Modeling of Land Use and Land Cover Change

Janus is an open source Python package for agent-based modeling (ABM) of land use and land cover change (LULCC). Many ABMs of LULCC have been created across platforms, some of which are not ideal for large scale, high resolution scenarios. This model provides a simple object-oriented framework for creating ABMs specific to LULCC. The organizational philosophy of the modeling framework is to create software objects (agents) that are associated with specific and contextual attributes which are isolated from where those agents exist in the spatial setting of the model, yet provide clear linkages between the agent, their environment, and other agents in the simulation. In this way, the framework allows for assembly of LULCC ABMs with low (programmatic) overhead, making the models extensible and providing clear mechanisms for integrating them with process-oriented biophysical models. Provided with Janus is a suite of geospatial data preprocessing tools that can use arbitrary land cover products as an input. Crop choice decisions are based on potential crop prices, these can be created synthetically, or drawn from integrated human-Earth systems models such as the GCAM. Janus is publicly accessible through GitHub and provides an example dataset for testing.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2021

Challenges to detection: Humidity as a spur to chemical agent change

Detecting chemical agents in outdoor environments such as a battlefield is made challenging by not only the spurious signatures from background chemicals and surfaces (e.g. asphalt, dirt, concrete), but also by the chemical transformation of the actual agents. The change of CW agents to other species can be catalyzed by other chemicals present in the scene, by different substrates, as well as by local weather conditions. Some of the final environmental transformation products are known (e.g. for the G agents methylphosphonic acid), but many of the intermediate chemical states are not, nor are the rates of transformation to the other intermediates or the end products. In this study we have made preliminary optical investigations into the degradation products of a G-agent intermediate, namely methylphosphonic anhydride and its rate of conversion to the more stable methylphosphonic acid. Using infrared and Raman spectroscopies, we have found that the relative humidity (RH) greatly affects the rate of change and we report first results from these studies.

: chemical warfare agent detection, Methylphosphon↗

DOE OSTI2020

Consensus Weighting of a Multi-Agent System for Load Shedding

An agent-based scheme is proposed for distributed underfrequency load shedding (UFLS). The key concept is a consensus weighting protocol (CWP) for agents to reach an agreement. Unlike the well adopted average-consensus protocol (ACP), the proposed CWP enables each agent to converge to its weighted portion of the sum of all initial values. Thus, the proposed CWP is more suitable for the UFLS application, as it allows load buses with a higher level of loading to shed more, rather than reducing by the same average value over all load buses as required by the ACP. Proof of convergence for the proposed CWP is derived and presented in this paper, together with the constraints. For implementation of the multi-agent system (MAS), the monitoring, estimation, and distribution steps are developed. Two study cases and the simulation results are provided to validate the performance of the proposed agent-based UFLS scheme.

Xie, Jing↗

DOE OSTI2020

Role of Capping Agents in the Synthesis of Salicylate-Capped Zinc Oxide Nanoparticles

Capping agents are often used for controlling the size, aggregation, and properties of nanoparticles. To guide the design of improved nanomaterials for targeted performance, one can use mechanistic insights into the interactions between capping agents and nanoparticles. Here, we employ density functional theory (DFT), reactive force-field molecular dynamics (ReaxFF MD) simulations, and optical spectroscopy to study the interactions between salicylate, as a model capping agent, and zinc oxide (ZnO) nanoparticles. In this work, we find that salicylate strongly interacts with the nanoparticle via the formation of O–Zn bonds in a distorted six-membered coordination ring structure. We describe the mechanisms of capping of ZnO nanoparticles by salicylate via three different binding modes. Simulations indicate that salicylate undergoes dissociative adsorption at the highly active surface Zn sites via a hydrogen-transfer process, thereby forming a tridentate configuration. The water-mediated interaction also facilitates the dissociative adsorption, leading to two salicylate O atoms coordinating with a surface Zn atom, while the other salicylate O atom bonds with another surface Zn atom. For molecular adsorption, binding free energies indicate that salicylate binds more strongly to ZnO, often in a bidentate configuration, than water does. The formation of the salicylate–ZnO complex is substantiated by UV–visible and Fourier transform infrared spectra. We find that the C=O stretching mode of salicylate becomes softened when it interacts with the nanoparticle, suggesting chemisorption of salicylate on ZnO. Although DFT predicts strong interaction between salicylate and ZnO, ReaxFF MD simulation indicates the moderate interaction between these two components in aqueous solution. Water molecules in close contact with the nanoparticle surface undergo dissociation, thus resulting in a surface hydroxyl, a reactive oxygen species that may influence the nanoparticle’s catalytic properties. Overall, the atomic-level information provided here can guide the selection process of salicylate as an appropriate agent for ZnO nanoparticle synthesis when strong interactions of particles with capping agents are required.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2021

Assessing Adaptive Irrigation Impacts on Water Scarcity in Nonstationary Environments—A Multi‐Agent Reinforcement Learning Approach

Abstract One major challenge in water resource management is to balance the uncertain and nonstationary water demands and supplies caused by the changing anthropogenic and hydroclimate conditions. To address this issue, we developed a reinforcement learning agent‐based modeling (RL‐ABM) framework where agents (agriculture water users) are able to learn and adjust water demands based on their interactions with the water systems. The intelligent agents are created by a reinforcement learning algorithm adapted from the Q‐learning algorithm. We illustrated this framework in a case study where the RL‐ABM is two‐way coupled with the Colorado River Simulation System (CRSS), a long‐term planning model used for the administration of the Colorado River Basin, for assessing agriculture water uses impacts on water scarcity. Seventy‐eight intelligent agents are simulated, which can be grouped into three categories based on their parameter values: the “aggressive” (swift actions; low regrets), the “forward‐looking conservative” (mild actions; high regrets; fast learning), and the “myopic conservative” (mild actions; median regrets; slow learning). The ABM‐CRSS results showed that the major reservoirs in the Upper Colorado Basin might experience more frequent water shortages due to the increasing water uses compared to the original CRSS results. If the drought continues, the case study also demonstrates that agents can learn and adjust their demands.

Hung, Fengwei↗

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 OSTI2023

Rutin is a potent senomorphic agent to target senescent cells and can improve chemotherapeutic efficacy

Aging is a major risk factor for most chronic disorders, for which cellular senescence is one of the central hallmarks. Senescent cells develop the pro-inflammatory senescence-associated secretory phenotype (SASP), which significantly contributes to organismal aging and age-related disorders. Development of senotherapeutics, an emerging class of therapeutic agents to target senescent cells, allows to effectively delay aging and alleviate chronic pathologies. Here we report preliminary outputs from screening of a natural medicinal agent (NMA) library for senotherapeutic candidates and validated several agents with prominent potential as senomorphics. Rutin, a phytochemical constituent found in a number of plants, showed remarkable capacity in targeting senescent cells by dampening expression of the full spectrum SASP. Further analysis indicated that rutin restrains the acute stress-associated phenotype (ASAP) by specifically interfering with the interactions of ATM with HIF1α, a master regulator of cellular and systemic homeostasis activated during senescence, and of ATM with TRAF6, part of a key signaling axis supporting the ASAP development toward the SASP. Conditioned media produced by senescent stromal cells enhanced the malignant phenotypes of prostate cancer cells, including in vitro proliferation, migration, invasion, and more importantly, chemoresistance, while rutin remarkably downregulated these gain-of-functions. Although classic chemotherapy reduced tumor progression, the treatment outcome was substantially improved upon combination of a chemotherapeutic agent with rutin. Our study provides a proof of concept for rutin as an emerging natural senomorphic agent, and presents an effective therapeutic avenue for alleviating age-related pathologies including cancer.

60 APPLIED LIFE SCIENCES↗

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 OSTI2021

PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems [SWR-22-07]

NREL's PowerGridworld provides a modular simulation environment for training heterogenous, grid-aware, multi-agent reinforcement learning (RL) policies at scale. The package enables the user to create component gym environments that can be composed into more complex agents. For example, a grid interactive building environment can be created by composing together component environments each encapsulating the building, PV, and battery physics. These multi-component environments can then be combined into multi-agent simulation where each agent's power consumption/injection becomes an input for solving the optimal power flow on a distribution feeder modeled in OpenDSS. Information from OpenDSS, such as bus voltages and line flows, can be included in the agents' observation spaces to enable grid-aware rewards. The default API for the PowerGridworld simulator conforms to RLLib's MultiAgent API and thus enables distributed training using HPC and cloud resources.

Biagioni, David↗

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 OSTI2021

Enhanced oxygen transfer agent systems for oxidative dehydrogenation of hydrocarbons

Aspects of the invention relate to enhanced oxygen transfer agent systems and methods of use thereof. According to one aspect, a method for producing olefins from a hydrocarbon feed includes the step of contacting a hydrocarbon feed comprised of one or more alkanes with an oxygen transfer agent at a temperature of 350° C. to 1000° C. The oxygen transfer agent comprising an oxygen-donating chalcogen agent comprised of at least one of S, Se, or Te and a reducible metal oxide. The chalcogen having an oxidation state greater than +2. According to another aspect, a method for producing one or more olefins by partial combustion of a hydrocarbon feed includes partially combusting a hydrocarbon feed comprised of one or more alkanes by contacting the hydrocarbon feed with an oxygen transfer agent comprising CaS04 at a temperature of 350° C. to 1000° C. to produce one or more olefins comprising ethylene and coproducing water.

Sofranko, John A.↗

DOE OSTI2022

Enhanced oxygen transfer agent systems for oxidative dehydrogenation of hydrocarbons

Enhanced oxygen transfer agent systems and methods of use thereof are provided. According to one aspect, a method for producing olefins from a hydrocarbon feed includes the step of contacting a hydrocarbon feed comprised of one or more alkanes with an oxygen transfer agent at a temperature of 350° C. to 1000° C. The oxygen transfer agent includes an oxygen-donating chalcogen agent including at least one of S, Se, or Te and a reducible metal oxide. The chalcogen has an oxidation state greater than +2. A method for producing one or more olefins by partial combustion of a hydrocarbon feed is provided. The method includes partially combusting a hydrocarbon feed comprised of one or more alkanes by contacting the hydrocarbon feed with an oxygen transfer agent comprising CaSO 4 at a temperature of 350° C. to 1000° C. to produce one or more olefins comprising ethylene and coproducing water.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

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↗