Engineering Papers⌕ Search

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.

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 OSTI2023

Application of multi-criteria decision analysis techniques and decision support framework for informing plant select agent designation and decision making

The United States Department of Agriculture (USDA) Division of Agricultural Select Agents and Toxins (DASAT) established a list of biological agents (Select Agents List) that threaten crops of economic importance to the United States and regulates the procedures governing containment, incident response, and the security of entities working with them. Every 2 years the USDA DASAT reviews their select agent list, utilizing assessments by subject matter experts (SMEs) to rank the agents. We explored the applicability of multi-criteria decision analysis (MCDA) techniques and a decision support framework (DSF) to support the USDA DASAT biennial review process. The evaluation includes both current and non-select agents to provide a robust assessment. We initially conducted a literature review of 16 pathogens against 9 criteria for assessing plant health and bioterrorism risk and documented the findings to support this analysis. Technical review of published data and associated scoring recommendations by pathogen-specific SMEs was found to be critical for ensuring accuracy. Scoring criteria were adopted to ensure consistency. The MCDA supported the expectation that select agents would rank high on the relative risk scale when considering the agricultural consequences of a bioterrorism attack; however, application of analytical thresholds as a basis for designating select agents led to some exceptions to current designations. A second analytical approach used agent-specific data to designate key criteria in a DSF logic tree format to identify pathogens of low concern that can be ruled out for further consideration as select agents. Both the MCDA and DSF approaches arrived at similar conclusions, suggesting the value of employing the two analytical approaches to add robustness for decision making.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

MADA: Multi-Agent Design Assistant

MADA (Multi-Agent Design Assistant) is a Large Language Model (LLM) powered multi-agent framework that coordinates specialized agents for complex design workflows. The system was designed for HPC workflows with the following agents in mind: 1) A Job Management Agent (JMA) launches and manages ensemble simulations on HPC systems, 2) a Geometry Agent (GA) generates meshes, and 3) an Inverse Design Agent (IDA) proposes new designs informed by simulation outcomes. Our framework reduces cumbersome manual workflow setup, and enables automated design exploration at scale. However, the software also enables users to rapidly create new multi-agent systems. Simply define new agents in a configuration file, giving each their own set of tools (via MCP), and then chat and prompt your new multi-agent system. Is

Gunnarson, BrianS [Lawrence Livermore National Lab↗
DOE OSTI2020

Multi-agent motion planning with sporadic communications for collision avoidance

Here, a novel multi-vehicle motion planning and collision avoidance algorithm is proposed and analyzed. The algorithm aims to reduce the amount of onboard calculations and inter-agent communications needed for each vehicle to successfully navigate through an environment with static obstacles and reach their goals. To this end, each agent first calculates a path to the goal by means of an asymptotically optimal rapidly-exploring random tree (RRT*) with respect to the static obstacles. Then, other agents are treated as dynamic obstacles and potential collisions are determined by means of collision cones. Collision cones depend on the position and velocity from other agents and are grown conservatively between inter-agent communications. Based on the available information, each agent determines if a deconfliction maneuver is needed, if it can continue along its current path, or if communication is needed to make a decision about a conflict. With probability one, our algorithm guarantees that the agents keep from colliding with each other. Under an assumption on the existence of a solution for a vehicle to its goal, this algorithm also solves the planning problem with probability one. Simulations illustrate a group of agents successfully reaching their goal configurations and examine how the uncertainty affects the communication frequency of the multi-agent system.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2020

Efficacy and Delivery of Novel FAST Agents for Coronaviruses

We proposed to test and develop advanced delivery for novel agents from our collaborators Facile Accelerated Specific Therapeutics (FAST) platform to reduce coronavirus replication. Sachi Bioworks Inc., Prof. Anushree Chatterjee, and Prof. Prashant Nagpal at the University of Colorado Boulder have developed a bioinformatics and synthesis pipeline to produce sequence specific theranostic agents (agents that can be therapies and/or diagnostics) that are inherently transported into the cytoplasm of mammalian host cells and sequence-specifically interfere in nucleic acid replication. The agent comprises a small nanoparticle (2-5 nm) chosen for ideal cellular transport and/or imaging conjugated to a short, synthetic DNA analog oligomer designed for binding to one or more target viral sequences. The sequence specific binding of the FAST agent to its target prevents nucleic acid replication due to its high affinity binding. While the small nanoparticle facilitates delivery in vitro, we plan to package the FAST agents into a larger nanoparticle (80-300 nm) for future in vivo delivery applications. Our team at Sandia has expertise encapsulating biomolecules including protein, DNA, and RNA into solid lipid nanoparticles (LNP) and lipid coated mesoporous silica nanoparticles (LC-MSN) and shown successful delivery in mouse models to multiple tissues. Our team focused on formulation parameters for FAST agents into lipid nanoparticles (LNP) and lipid coated mesoporous silica nanoparticles (LC-MSN) for enhanced delivery and/or efficacy and in vivo translation. We used lipid formulas that have been shown in literature to facility in vitro and more importantly, in vivo delivery. In our work discussed below, we successfully demonstrate loading and release of FAST agents on silica core and stable LC-MSN in a reasonable size range for in vivo testing.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Projected Multi-Agent Consensus Equilibrium (PMACE) With Application to Ptychography

Multi-Agent Consensus Equilibrium (MACE) formulates an inverse imaging problem as a balance among multiple update agents such as data-fitting terms and denoisers. However, each such agent operates on a separate copy of the full image, leading to redundant memory use and slow convergence when each agent affects only a small subset of the full image. In this article, we extend MACE to Projected Multi-Agent Consensus Equilibrium (PMACE), in which each agent updates only a projected component of the full image, thus greatly reducing memory use for some applications. We describe PMACE in terms of an equilibrium problem and an equivalent fixed-point problem and show that in most cases the PMACE equilibrium is not the solution of an optimization problem. To demonstrate the value of PMACE, we apply it to the problem of ptychography, in which a sample is reconstructed from the diffraction patterns resulting from coherent X-ray illumination at multiple overlapping spots. In our PMACE formulation, each spot corresponds to a separate data-fitting agent, with the final solution found as an equilibrium among all the agents. In conclusion, our results demonstrate that the PMACE reconstruction algorithm generates more accurate reconstructions at a lower computational cost than existing ptychography algorithms when the spots are sparsely sampled.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Precipitation of gadolinium from magnetic resonance imaging contrast agents may be the Brass tacks of toxicity

The formation of gadolinium-rich nanoparticles in multiple tissues from intravenous magnetic resonance imaging contrast agents may be the initial step in rare earth metallosis. The mechanism of gadolinium-induced diseases is poorly understood, as is how these characteristic nanoparticles are formed. Gadolinium deposition has been observed with all magnetic resonance imaging contrast agent brands. Aside from endogenous metals and acidic conditions, little attention has been paid to the role of the biological milieu in the degradation of magnetic resonance imaging contrast agents into nanoparticles. Herein, we describe the decomposition of the commercial magnetic resonance imaging contrast agents Omniscan and Dotarem in the presence of oxalic acid, a well-known endogenous compound. Omniscan dechelated rapidly and preluded measurement by the means available, while Dotarem underwent a two-step decomposition process. The decomposition of both magnetic resonance imaging contrast agents by oxalic acid formed gadolinium oxalate (Gd 2 [C 2 O 4 ] 3 , Gd 2 Ox 3 ). Furthermore, both observed steps of the Dotarem reaction involved the associative addition of oxalic acid. Adding protein (bovine serum albumin) increased the rate of dechelation. Displacement reactions could occur at lysosomal pH. Through these studies, we have demonstrated that magnetic resonance imaging contrast agents can be dissociated by endogenous molecules, thus illustrating a metric by which gadolinium-based contrast agents (GBCAs) might be destabilized in vivo.

Gadodiamide↗
DOE OSTI2022

PowerNet: Multi-agent Deep Reinforcement Learning for Scalable Powergrid Control

This paper develops an efficient multi-agent deep reinforcement learning algorithm for cooperative controls in powergrids. Specifically, we consider the decentralized inverter-based secondary voltage control problem in distributed generators (DGs), which is first formulated as a cooperative multi-agent reinforcement learning (MARL) problem. We then propose a novel on-policy MARL algorithm, PowerNet, in which each agent (DG) learns a control policy based on (sub-)global reward but local states and encoded communication messages from its neighbors. Motivated by the fact that a local control from one agent has limited impact on agents distant from it, we exploit a novel spatial discount factor to reduce the effect from remote agents, to expedite the training process and improve scalability. Furthermore, a differentiable, learning-based communication protocol is employed to foster the collaborations among neighboring agents. In addition, to mitigate the effects of system uncertainty and random noise introduced during on-policy learning, we utilize an action smoothing factor to stabilize the policy execution. To facilitate training and evaluation, we develop PGSim, an efficient, high-fidelity powergrid simulation platform. Here, experimental results in two microgrid setups show that the developed PowerNet outperforms the conventional model-based control method, as well as several state-of-the-art MARL algorithms. The decentralized learning scheme and high sample efficiency also make it viable to large-scale power grids.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Evaluation of 6-OxP-CD, an Oxime-based cyclodextrin as a viable medical countermeasure against nerve agent poisoning: Experimental and molecular dynamic simulation studies on its inclusion complexes with cyclosarin, soman and VX

The ability of the cyclodextrin-oxime construct 6-OxP-CD to bind and degrade the nerve agents Cyclosarin (GF), Soman (GD) and S -[2-[Di(propan-2-yl)amino]ethyl] O -ethyl methylphosphonothioate (VX) has been studied using 31 P-nuclear magnetic resonance (NMR) under physiological conditions. While 6-OxP-CD was found to degrade GF instantaneously under these conditions, it was found to form an inclusion complex with GD and significantly improve its degradation (t 1/2 ~ 2 hrs) relative over background (t 1/2 ~ 22 hrs). Consequently, effective formation of the 6-OxP-CD:GD inclusion complex results in the immediate neutralization of GD and thus preventing it from inhibiting its biological target. In contrast, NMR experiments did not find evidence for an inclusion complex between 6-OxP-CD and VX, and the agent’s degradation profile was identical to that of background degradation (t 1/2 ~ 24 hrs). As a complement to this experimental work, molecular dynamics (MD) simulations coupled with Molecular Mechanics-Generalized Born Surface Area (MM-GBSA) calculations have been applied to the study of inclusion complexes between 6-OxP-CD and the three nerve agents. These studies provide data that informs the understanding of the different degradative interactions exhibited by 6-OxP-CD with each nerve agent as it is introduced in the CD cavity in two different orientations (up and down). For its complex with GF, it was found that the oxime in 6-OxP-CD lies in very close proximity (P GF …O Oxime ~ 4–5 Å) to the phosphorus center of GF in the ‘down GF ’ orientation for most of the simulation accurately describing the ability of 6-OxP-CD to degrade this nerve agent rapidly and efficiently. Further computational studies involving the center of masses (COMs) for both components (GF and 6-OxP-CD) also provided some insight on the nature of this inclusion complex. Distances between the COMs (ΔCOM) lie closer in space in the ‘down GF ’ orientation than in the ‘up GF ’ orientation; a correlation that seems to hold true not only for GF but also for its congener, GD. In the case of GD, calculations for the ‘down GD ’ orientation showed that the oxime functional group in 6-OxP-CD although lying in close proximity (P GD …O Oxime ~ 4–5 Å) to the phosphorus center of the nerve agent for most of the simulation, adopts another stable conformation that increase this distance to ~ 12–14 Å, thus explaining the ability of 6-OxP-CD to bind and degrade GD but with less efficiency as observed experimentally (t 1/2 ~ 4 hr. vs. immediate). Lastly, studies on the VX:6-OxP-CD system demonstrated that VX does not form a stable inclusion complex with the oxime-bearing cyclodextrin and as such does not interact in a way that is conducive to an accelerated degradation scenario. Collectively, these studies serve as a basic platform from which the development of new cyclodextrin scaffolds based on 6-OxP-CD can be designed in the development of medical countermeasures against these highly toxic chemical warfare agents.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

Beyond the List: Bioagent-Agnostic Signatures Could Enable a More Flexible and Resilient Biodefense Posture Than an Approach Based on Priority Agent Lists Alone

As of 2021, the biothreat policy and research communities organize their efforts around lists of priority agents, which elides consideration of novel pathogens and biotoxins. For example, the Select Agents and Toxins list is composed of agents that historic biological warfare programs had weaponized or that have previously caused great harm during natural outbreaks. Similarly, lists of priority agents promulgated by the World Health Organization and the National Institute of Allergy and Infectious Diseases are composed of previously known pathogens and biotoxins. To fill this gap, we argue that the research/scientific and biodefense/biosecurity communities should categorize agents based on how they impact their hosts to augment current list-based paradigms. Specifically, we propose integrating the results of multi-omics studies to identify bioagent-agnostic signatures (BASs) of disease—namely, patterns of biomarkers that accurately and reproducibly predict the impacts of infection or intoxication without prior knowledge of the causative agent. Here, we highlight three pathways that investigators might exploit as sources of signals to construct BASs and their applicability to this framework. The research community will need to forge robust interdisciplinary teams to surmount substantial experimental, technical, and data analytic challenges that stand in the way of our long-term vision. However, if successful, our functionality-based BAS model could present a means to more effectively surveil for and treat known and novel agents alike.

59 BASIC BIOLOGICAL SCIENCES↗
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 OSTI2023

Protection against Chemical Warfare Agents and Biological Threats Using Metal–Organic Frameworks as Active Layers

The SARS-CoV-2 pandemic outbreak and the unfortunate misuse of toxic chemical warfare agents (CWAs) highlight the importance of developing functional materials to protect against these chemical and pathogen threats. Metal–organic frameworks (MOFs), which comprise a tunable class of crystalline porous materials built from inorganic nodes and organic linkers, have emerged as a class of heterogeneous catalysts capable of rapid detoxification of multiple classes of these harmful chemical or biological hazards. In particular, zirconium-based MOFs (Zr-MOFs) feature Lewis acidic nodes that serve as active sites for a wide range of catalytic reactions, including the hydrolysis of organophosphorus nerve agents within seconds in basic aqueous solutions. In addition, postsynthetic modification of Zr-MOFs enables the release of active species capable of reacting with and deactivating harmful pathogens. Despite this impressive performance, utilizing Zr- MOFs in powder form is not practical for application in masks or protective uniforms. To address this challenge, our team sought to develop MOF/fiber composite systems that could be adapted for use under realistic operating conditions to protect civilians, military personnel, and first responders from harmful pathogens and chemical warfare agents. Over the last several years, our group has designed and fabricated reactive and biocidal MOF/fiber composites that effectively capture and deactivate these toxic species. In this Account, we describe the evolution of these porous and reactive MOF/fiber composites and focus on key design challenges and considerations. First, we devised a scalable method for the integration of Zr-MOFs onto textile substrates using aqueous precursor solutions and without using pretreated textiles, highlighting the potential scalability of this method. Moving beyond standard textiles, we also developed a microbial synthesis strategy to prepare hierarchically porous MOF/bacterial cellulose nanofiber composite sponges that can both capture and detoxify nerve agents when exposed to contaminated gas flows. The mass loading of the MOF in the nanofibrous composite sponge is up to 90%, affording higher work capacities compared to those of textile-fiber-based composites with relatively lower MOF loadings. Next, we demonstrated that heterogeneous polymeric bases are suitable replacements for volatile liquid bases typically used in solution-phase reactions, and we showed that these composite systems are capable of effectively hydrolyzing nerve agents in the solid state by using only water that is present as humidity. Moreover, incorporating a reactive dye precursor into the composite affords a dual function sensing and detoxifying material that changes color from white to orange upon reaction with the byproduct following nerve agent hydrolysis, demonstrating the versatility of this platform for use in decontamination applications. We then created chlorine-loaded MOF/fiber composites that act as biocidal and reactive textiles that are capable of not only detoxifying sulfur-mustard-based chemical warfare agents and simulants but also deactivating both bacteria and the SARS-CoV-2 virus within minutes of exposure. Lastly, we synthesized a mixed-metal Ti/Zr-MOF coating on cotton fibers to afford a photoactive biocidal cloth that shows fast and broad-spectrum biocidal performance against viruses and Gram-positive and Gram-negative bacteria under visible light irradiation. Given the tunable, multifunctional nature of these MOF/fiber composites, we believe that this Account will offer new insights for the rational design and preparation of functional MOF/fiber composites and pave the way toward the development of next-generation reactive and protective textiles.

36 MATERIALS SCIENCE↗
DOE OSTI2023

The onset of rare earth metallosis begins with renal gadolinium-rich nanoparticles from magnetic resonance imaging contrast agent exposure

The leitmotifs of magnetic resonance imaging (MRI) contrast agent-induced complications range from acute kidney injury, symptoms associated with gadolinium exposure (SAGE)/gadolinium deposition disease, potentially fatal gadolinium encephalopathy, and irreversible systemic fibrosis. Gadolinium is the active ingredient of these contrast agents, a non-physiologic lanthanide metal. The mechanisms of MRI contrast agent-induced diseases are unknown. Mice were treated with a MRI contrast agent. Human kidney tissues from contrast-naïve and MRI contrast agent-treated patients were obtained and analyzed. Kidneys (human and mouse) were assessed with transmission electron microscopy and scanning transmission electron microscopy with X-ray energy-dispersive spectroscopy. MRI contrast agent treatment resulted in unilamellar vesicles and mitochondriopathy in renal epithelium. Electron-dense intracellular precipitates and the outer rim of lipid droplets were rich in gadolinium and phosphorus. We conclude that MRI contrast agents are not physiologically inert. The long-term safety of these synthetic metal–ligand complexes, especially with repeated use, should be studied further.

36 MATERIALS SCIENCE↗
DOE OSTI2026

AutoLabs: cognitive multi-agent systems with self-correction for autonomous chemical experimentation

The automation of chemical research through self-driving laboratories (SDLs) promises to accelerate scientific discovery, yet the reliability and granular performance of the underlying AI agents remain critical, under-examined challenges. In this work, we introduce AutoLabs, a self-correcting, multi-agent architecture designed to autonomously translate natural-language instructions into executable protocols for a high-throughput liquid handler. The system engages users in dialogue, decomposes experimental goals into discrete tasks for specialized agents, performs tool-assisted stoichiometric calculations, and iteratively self-corrects its output before generating a hardware-ready file. We present a comprehensive evaluation framework featuring five benchmark experiments of increasing complexity, from simple sample preparation to multi-plate timed syntheses. Through a systematic ablation study of 20 agent configurations, we assess the impact of reasoning capacity, architectural design (single- vs. multi-agent), tool use, and self-correction mechanisms. Our results demonstrate that agent reasoning capacity is the most critical factor for success, reducing quantitative errors in chemical amounts (nRMSE) by over 85% in complex tasks. When combined with a multi-agent architecture and iterative self-correction, AutoLabs approaches expert-authored reference procedures on the benchmark (F1-score > 0.89) on challenging multi-plate syntheses. These findings establish a clear blueprint for developing robust and trustworthy AI partners for autonomous laboratories, highlighting the synergistic effects of modular design, advanced reasoning, and self-correction to ensure both performance and reliability in high-stakes scientific applications. Code: https://github.com/pnnl/autolabs

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

ToPolyAgent: AI agents for coarse-grained bead-spring topological polymer simulations

We introduce ToPolyAgent, a multi-agent AI framework for performing coarse-grained molecular dynamics (MD) simulations of topological polymers through natural language instructions. By integrating large language models (LLMs) with domain-specific computational tools, ToPolyAgent supports both interactive and autonomous simulation workflows across diverse polymer architectures, including linear, ring, brush, and star polymers, as well as dendrimers. The system consists of four LLM-powered agents: a Config Agent for generating initial polymer–solvent configurations, a Simulation Agent for executing LAMMPS-based MD simulations and conformational analyses, a Report Agent for compiling markdown reports, and a Workflow Agent for streamlined autonomous operations. Interactive mode incorporates user feedback loops for iterative refinements, while autonomous mode enables end-to-end task execution from detailed prompts. We demonstrate ToPolyAgent's versatility through case studies involving diverse polymer architectures under varying solvent conditions, thermostats, and simulation lengths. Furthermore, we highlight its potential as a research assistant by directing it to investigate the effect of interaction parameters on the linear polymer conformation, and the influence of grafting density on the persistence length of the brush polymer. By coupling natural language interfaces with rigorous simulation tools, ToPolyAgent lowers barriers to complex computational workflows and advances AI-driven materials discovery in polymer science. It lays the foundation for autonomous and extensible multi-agent scientific research ecosystems.

Ding, Lijie [Oak Ridge National Laboratory (ORNL),↗
DOE OSTI2024

Towards a High Fidelity Training Environment for Autonomous Cyber Defense Agents

Cyber defenders are overwhelmed by the frequency and scale of attacks against their networks. This problem will only be exacerbated as attackers leverage AI to automate their workflows. Autonomous cyber defense capabilities could aid defenders by automating operations and adapting dynamically to novel threats. However, existing training environments fall short in areas such as generalization, explainability, scalability, and transferability, making it intractable to train agents that will be effective in real networks. In this paper we take an important step towards creating autonomous cyber defense agents — we present a high fidelity training environment called Cyberwheel that includes both simulation and emulation capabilities. Cyberwheel simplifies customization of the training network and easily allows redefining the agent’s reward function, observation space, and action space to support rapid experimentation of novel approaches to agent design. It also provides visibility into agent behaviors necessary for agent evaluation and sufficient documentation / examples to lower the barrier to entry. As an example use case of Cyberwheel, we present initial results training an autonomous agent to deploy cyber deception strategies in simulation.

Oesch, T↗
DOE OSTI2025

Agentic AI vs ML-Based Autotuning: A Comparative Study for Loop Reordering Optimization

High Performance Computing (HPC) applications rely heavily on code optimizations to achieve good performance on modern CPU and GPU architectures. Traditional Machine Learning auto-tuning approaches have demonstrated success in exploring high-dimensional spaces, but they often require expensive compile-run evaluations and lack adaptability for large HPC applications. The recent advances in Large Language Models (LLMs) and Agentic AI systems raise intriguing questions about the potential of these approaches to address specific optimization methodologies. This work aims to answer an essential question for the HPC community: “How Agentic AI Systems Compare to Traditional ML Autotuning Techniques?” To address this question, we present a comparative analysis between a traditional ML-based optimization approach and an Agentic AI system, evaluating their respective capabilities and limitations for loop-level optimization. In addition, we introduced a new Agentic AI system named LoopGen-AI using three different Large Language Models: GPT-4.1, Claude 4.0, and Gemini 2.5. A key finding is that LoopGen-AI achieves competitive per-formance with only a few program runs, the reasoning logs from the agents revealed that their decisions rely heavily on the combination of semantic understanding of the target kernel with dynamic feedback from the environment, highlighting a promising new dimension in performance tuning. In contrast, ML-based autotuners focus on statistical exploration, and require orders of magnitude more runs to reach peak performance. Additionally, our analysis shows that prompt engineering, particularly using Persona + Context Manager patterns, significantly impacts the effectiveness of Agentic AI. Our results indicate that while Agentic AI systems are not yet a complete replacement for ML-based autotuners, it can effectively complement traditional methods.

Rosas, Miguel Romero↗
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 OSTI2023

A Novel Multi-Agent Deep Reinforcement Learning-enabled Distributed Power Allocation Scheme for mmWave Cellular Networks

We consider the power allocation problem over shared spectrum for millimeter-Wave (mmWave) cellular downlink. Existing approaches usually find sub-optimal solutions by solving a non-convex optimization which leads to scalability issues due to centralized control. Therefore, distributed and adaptive approaches are desirable. Recently, model-free Deep Reinforcement Learning (DRL) has achieved success in such wireless resource management tasks. By modeling the radio environment as a Markov Decision Process (MDP) with the base stations (BSs) being the agents, power allocation can be automated at the agent level with comparable throughput performance to conventional centralized schemes. The multi-agent setting presents new challenges as the radio environment is impacted by the joint actions of the agents and is no longer stationary from any individual agent’s perspective. Existing literature bypasses this non-stationarity violation by ignoring it which may cause performance degradation. To tackle this issue, we propose a distributed continuous power allocation scheme based on a modified version of multi-agent Deep Deterministic Policy Gradient (MADDPG) that is tailored for the distributed multiple-agent setting. The proposed scheme employs a centralized-training distributed-execution framework where Q-functions are trained over subsets of BSs while each BS determines its transmit power based only on its own local observation. It admits constant per-BS communication and computation complexity and is thus scalable to large networks. Numerical evaluation shows that the proposed scheme adapts well to a wide range of interference conditions and can achieve comparable or better performance than several state-of-the-art non-learning approaches.

99 GENERAL AND MISCELLANEOUS↗