AI Agent 生态 · 全部实体（第 22 / 100 页）

本页收录第 2101–2200 条，共 10000 条 · 返回 AI Agent 生态 首页

• Democratizing cloud data lake analytics: natural language access to Apache Iceberg via LLM agents.
  Business analysts and non-technical users need insights from enterprise data lakes but lack SQL expertise to query them directly. While large language models (LLMs) can translate natural language to SQL, existing text-to-SQL approaches face critical limitation…
  europepmc 2026 置信度 0.80
• BACI-VI-Bench: A dataset of variational inequality benchmark instances for multi-agent trade-network equilibrium.
  This article presents BACI-VI-Bench, a processed benchmark dataset and reproducible construction pipeline that transforms CEPII-BACI product-level international trade records into finite-dimensional variational inequality instances for multi-commodity trade-ne…
  europepmc 2026 置信度 0.80
• Gradual introduction of carbon allowance auctions facilitates sustainable emission reductions in the power sector.
  Achieving deep decarbonization of the power sector is essential for China's carbon neutrality goal and global climate mitigation. However, the coordination among emission reduction effectiveness, carbon market stability, and energy security remains unclear. Th…
  europepmc 2026 置信度 0.80
• Cross-language hotel review sentiment analysis via multi-agent federated learning with heterogeneous graph attention networks.
  This paper presents an integrated framework for cross-language hotel review sentiment analysis that combines multi-agent federated learning with heterogeneous graph attention networks to address privacy preservation and multilingual data processing challenges …
  pubmed Han X 2026 置信度 0.82
• Multi-objective inventory optimization using reinforcement learning: a comparative study on profitability and carbon emissions.
  Inventory management is a core part of supply chains, and over the years it has been increasingly challenged by the need to balance economic performance with environmental considerations. While prior reinforcement learning (RL) studies have incorporated carbon…
  europepmc 2026 置信度 0.80
• Enhancing multi-component alloy composition prediction based on generative adversarial networks and proximal policy optimization.
  This article belongs to the cross fusion of material genomics engineering and artificial intelligence. In response to the challenges of data scarcity and high experimental costs faced by traditional alloy design methods in complex composition systems, an innov…
  europepmc 2026 置信度 0.80
• Evolutionary Digital Twin for Oil and Gas Pipelines: A Cognitive Multi-Agent Framework with Continuous Feedback Learning.
  The structural integrity and risk management of long-distance oil and gas pipelines are critically challenged by multi-source data heterogeneity, complex multi-physics degradation mechanisms, and the dynamic nature of operational environments. Traditional mono…
  europepmc 2026 置信度 0.80
• Comparing screening frameworks for populations with multiple overlapping high-risk factors: A case of tuberculosis screening in China
  Background Public health initiatives increasingly target multiple overlapping high-risk groups to maximize impact. However, a common challenge in modelling these initiatives is to capture these overlapping risk factors, leading to potential misallocation of re…
  europepmc 2026 置信度 0.80
• A unified multimodal GenAI platform integrating GraphRAG multi-agent systems and custom language models for intelligent document processing and knowledge synthesis.
  Retrieval-Augmented Generation (RAG) based enterprise systems on document reasoning tasks are getting to grow more based on Large Language Models (LLMs); however, non-vector-based RAG pipelines continue to show inadequate relational consistency, multi-document…
  pubmed Parihar BS, Singh TK, Gonnade G, Dewangan BK 等 2026 置信度 0.82
• Research on embodied agent multimodal perception and real-time path planning algorithms for complex unstructured environments.
  Autonomous navigation of embodied agents in complex unstructured environments demands tightly coupled multimodal perception and real-time path planning capabilities, forming a core technical bottleneck in physical-world robot deployment. Heterogeneous sensor d…
  europepmc 2026 置信度 0.80
• Hydrogen supplementation improves glucose-based n-caproate production in Caproiciproducens galactitolivorans with reverse β-oxidation-associated redox remodeling.
  Medium-chain carboxylic acids, such as n-caproate, are attractive sustainable platform chemicals. However, their microbial production is often limited by electron availability and low product selectivity. This study investigated the effect of hydrogen suppleme…
  europepmc 2026 置信度 0.80
• Multi-party open-ended conversation with a social robot.
  Multi-party open-ended conversation remains a major challenge in human-robot interaction, particularly when robots must recognise speakers, allocate turns, and respond coherently under overlapping or rapidly shifting dialogue. This paper presents a multi-party…
  europepmc 2026 置信度 0.80
• A multi-agent reinforcement learning scheduling algorithm integrating state graph and task graph structural modeling for ride-sharing dispatching.
  Urban-scale ride-hailing dispatch faces critical challenges such as heterogeneous demand density, highly dynamic state transitions, and multi-agent coordination. Traditional rule-based or heuristic matching strategies struggle to maintain efficiency under larg…
  pubmed Sha J, Song M, Sui G, Sun H 等 2026 置信度 0.82
• An Evaluation of Foreign Clinical Data in the Approval Reviews of Antimicrobial Medicines in Japan: Considering Ethnic and Regional Differences in Data Extrapolations in Accordance With Regulatory Circumstances.
  The approval requirements in new regions that do not require domestic clinical data and the clinical data evaluation of multi-regional clinical trials (MRCTs) and foreign clinical trials (FCTs) in the Japanese approval review processes for antimicrobial medici…
  europepmc 2026 置信度 0.80
• Application of Reinforcement Learning Techniques in De Novo Drug Design: A Systematic Literature Review.
  Background and aims De novo drug design is the process of generating novel lead compounds that possess desirable pharmacological activities and optimal physicochemical properties for therapeutic development. In recent years, it has evolved into a key computati…
  europepmc 2026 置信度 0.80
• Hierarchical multi-agent reinforcement learning for retrieval-augmented industrial document question answering.
  Multimodal industrial documents-such as operation manuals, circuit diagrams, and parameter tables-contain domain knowledge distributed across text, images, and document layout. However, most existing retrieval-augmented generation (RAG) frameworks rely on stat…
  europepmc 2026 置信度 0.80
• Time to antibiotic administration in intra-amniotic infections: impact of cefoxitin monotherapy versus traditional antibiotic therapy.
  Objective This study addresses treatment of intra-amniotic infection (IAI) by comparing timely receipt of recommended antibiotic administration between cefoxitin and traditional antimicrobial therapy, ampicillin and gentamicin, with or without clindamycin. Met…
  europepmc 2026 置信度 0.80
• An integrated AI-enabled system using One Class Twin Cross Learning for early gastric cancer detection.
  Background Early detection of gastric cancer, a leading cause of cancer-related mortality worldwide, remains significantly hampered by the limitations of current diagnostic technologies, resulting in high rates of misdiagnosis and missed diagnoses. Methods To …
  europepmc 2025 置信度 0.80
• ChemGraph as an agentic framework for computational chemistry workflows.
  Atomistic simulations are essential in chemistry and materials science but remain challenging to run due to the expert knowledge required for the setup, execution, and validation stages of these calculations. We present ChemGraph, an agentic framework powered …
  europepmc 2026 置信度 0.80
• Properties and Applications of Advanced Textile Materials.
  Advanced textile materials have undergone a revolutionary transformation from traditional clothing and decorative fabrics to high-performance, intelligent, and environmentally friendly functional systems that connect materials science, fiber engineering, weara…
  europepmc 2026 置信度 0.80
• Large Language Models in equity markets: applications, techniques, and insights.
  Recent breakthroughs in Large Language Models (LLMs) have the potential to disrupt equity investing by enabling sophisticated data analysis, market prediction, and automated trading. This paper presents a comprehensive review of 84 research studies conducted b…
  europepmc 2025 置信度 0.80
• DRL-based multi-objective task scheduling for edge-cloud computing: latency, energy, and SLA optimisation.
  Task scheduling is a fundamental challenge in edge-cloud computing systems, as it needs to address dynamic workloads, heterogeneous resources, and stringent latency requirements. While many traditional scheduling algorithms, such as First-In-First-Out (FIFO) a…
  europepmc 2026 置信度 0.80
• The Evolution of Lupus Nephritis Therapy from the 1960s to the Present.
  Lupus nephritis (LN) stands out as one of the most critical complications of systemic lupus erythematosus (SLE), affecting almost 60% of the patient population. Even though more therapies have been made available for LN in the past decade, clinical outcomes re…
  europepmc 2026 置信度 0.80
• Blueprint2Code: a multi-agent pipeline for reliable code generation via blueprint planning and repair.
  Automated programming has become a powerful tool for solving real-world problems. Code generation, in particular, plays a key role in improving developer productivity and reducing the entry barrier to software development. Recent advances in large language mod…
  europepmc 2025 置信度 0.80
• Biofilm-associated antibiotic tolerance in the era of multidrug resistance: quorum-sensing mechanisms and emerging therapeutic strategies.
  Biofilms are highly organised complex structures formed by microorganisms that adhere to surfaces and are embedded with an extracellular polymeric matrix. This matrix provides structural stability, retains nutrients and offers defence against unfavourable envi…
  europepmc 2026 置信度 0.80
• Conceptualising systems thinking and complexity modelling for circular economy quantification: A systematic review and critical analysis.
  Quantification of circular economy (CE) is essential for effective implementation, yet also fundamentally challenging, because it is inherently complex, featuring multiple interactions and system-level dynamicity. Two main approaches of systems thinking, commo…
  europepmc 2026 置信度 0.80
• Application of immune checkpoint inhibitors in hepatocellular carcinoma: a landscape analysis of clinical trial databases.
  Background Hepatocellular carcinoma (HCC) is a leading global malignant tumor with poor prognosis. Immune checkpoint inhibitors (ICIs) have become a breakthrough treatment for HCC, but a systematic landscape analysis of global ICI clinical trials is lacking. M…
  europepmc 2026 置信度 0.80
• Metal-polyphenol nanomedicines for malignant tumor therapy.
  Malignant tumor is still one of the most critical diseases in clinic. Current therapeutic strategies include surgery, chemoradiotherapy, targeted therapy, and immunotherapy. Nevertheless, the development of novel drugs with superior efficacy and reduced drug t…
  europepmc 2026 置信度 0.80
• Gestational trophoblastic neoplasia treated with low-dose induction chemotherapy despite prognostic score < 13: a case report.
  Background Gestational trophoblastic neoplasia (GTN) can cause significant morbidity and mortality if not appropriately recognized and treated. Low-dose induction chemotherapy is recommended for "ultra-high risk" GTN- defined as prognostic score ≥ 13 - to prev…
  europepmc 2026 置信度 0.80
• SPHTRLM: secure and privacy-preserving hyperparameter-tuned reinforcement learning method for robot path finding in dynamic environments.
  Autonomous robot navigation within a dynamic environment is a complicated issue since environmental factors keep on changing, safety remains a factor, and issues of data privacy concern are also on the increase. The existing reinforcement learning (RL) navigat…
  pubmed Dewangan RR, Thombre D, Parganiha V, Verma M 等 2026 置信度 0.82
• FLT3 Testing and Guideline Concordance in Acute Myeloid Leukemia Across a Community Health System.
  Introduction FMS-like tyrosine kinase 3 (FLT3) mutations are present in approximately one-third of patients with acute myeloid leukemia (AML) and are associated with higher relapse and reduced survival. National Comprehensive Cancer Network (NCCN) guidelines r…
  europepmc 2026 置信度 0.80
• A Curriculum Approach to Reduce the Dynamics-Related Reality Gap in Autonomous Driving Decision-Making.
  Decision-making is a fundamental component of autonomous driving, where complex urban scenarios require safe, robust, and adaptable behaviours. This work presents a curriculum learning approach to reduce the dynamics-related reality gap in autonomous driving d…
  europepmc 2026 置信度 0.80
• A Reinforcement Learning-Based Framework for Tariff-Aware Load Shifting in Energy-Intensive Manufacturing.
  Optimizing energy-intensive manufacturing under time-varying electricity tariffs requires scheduling strategies that reduce cost without compromising operational feasibility. This study is grounded in readily available industrial sensing: we exclusively use ti…
  europepmc 2026 置信度 0.80
• Integrating viral kinetics and population spread in a one health framework to explain variant-specific epidemic dynamics.
  The COVID-19 pandemic underscored the importance of modeling frameworks that integrate biological mechanisms with heterogeneous social contact patterns to accurately characterize variant-specific transmission. Motivated by a One Health perspective that connect…
  europepmc 2026 置信度 0.80
• Development of Potency Assays for Therapeutic EVs: The Art of Congruence.
  europepmc 2026 置信度 0.80
• Transcendental model selection: a computational account of symbolic cognition and general intelligence through morality and culture.
  General intelligence enables flexible problem solving across diverse contexts by minimizing uncertainty. Symbolic systems such as language extend this capacity, allowing humans to build social groups and construct world models beyond typical biological constra…
  europepmc 2026 置信度 0.80
• The prevalence and risk factors of drug allergy in Sri Lanka-a multi-centre cross-sectional observational study (2024-2025).
  Background There is a huge burden of drug allergy (DA) in High-Income Countries and is a major impediment to clinical management, adversely affecting outcomes. Data regarding DA from low-and middle-income countries (LMICs) are sparse. Also, there is a vast unm…
  europepmc 2026 置信度 0.80
• Rehab-DRLX: explainable neurorehabilitation prognosis using deep reinforcement learning and transformer-based models.
  Neurorehabilitation poses a crucial problem in clinical recovery tasks, particularly for individuals with poor motor functions and neurological impairments, and problems in activities of daily living (ADL). To resolve this, we design a novel model, Rehab-DRLX,…
  europepmc 2026 置信度 0.80
• A pan-cancer atlas of metabolic regulatory circuitries integrating multi-omic, immune, and clinical dimensions.
  Introduction Metabolic reprogramming is a central determinant of tumor progression, immune evasion, and susceptibility to regulated cell death. However, the integration of metabolic regulation across genomic, multi-omic, immune, and clinical dimensions remains…
  europepmc 2026 置信度 0.80
• Alzheimer's disease drug development pipeline: 2026.
  Introduction Discovery and development of new therapies for Alzheimer's disease (AD) are urgently needed to address the world's growing population of individuals on the AD pathophysiological continuum. Clinicaltrials.gov is a resource for studying drugs in dev…
  europepmc 2026 置信度 0.80
• Deep reinforcement learning for network resource optimization in MIMO-NOMA networks to maximize utilization with minimal overhead.
  The next-generation multiple-input Multiple-Output Non-Orthogonal Medium Access (MIMO-NOMA) system requires seamless mobility, enhanced spectral efficiency, and higher sum rates with minimal interference. Selecting the optimal network and optimizing resources …
  europepmc 2026 置信度 0.80
• Medicinal plants as alternative and adjunct antimicrobial agents in ear, nose, and throat (ENT) Infections.
  Medicinal plants are widely used worldwide for ear, nose, and throat (ENT) disorders and have a long history of traditional application. This review aims to summarize current experimental and clinical evidence on medicinal plants used for ENT conditions such a…
  europepmc 2026 置信度 0.80
• Evaluating LLMs on Kazakhstan's mathematics exam for university admission.
  Introduction The rapid advancement of large language models (LLMs) has prompted their exploration in educational contexts, particularly in high-stakes standardized tests such as Kazakhstan's Unified National Testing (UNT) mathematics component, which is critic…
  europepmc 2025 置信度 0.80
• Social and emotional learning in artificial agents.
  Social and emotional intelligence are fundamental to human cognition, yet current artificial agent frameworks typically treat these capabilities separately, limiting their ability to generate authentic social interactions. We present SELAgents (Social and Emot…
  pubmed Torres N 2026 置信度 0.82
• From data silos to insights: the PRINCE multi-agent knowledge engine for preclinical drug development.
  The pharmaceutical industry faces pressure to improve the drug development process while reducing costs in an evolving regulatory landscape. This paper presents the Preclinical Information Center (PRINCE), a cloud-hosted data integration platform developed by …
  europepmc 2025 置信度 0.80
• Interactive imitation learning for dexterous robotic manipulation: challenges and perspectives-a survey.
  Dexterous manipulation is a crucial yet highly complex challenge in humanoid robotics, demanding precise, adaptable, and sample-efficient learning methods. As humanoid robots are usually designed to operate in human-centric environments and interact with every…
  europepmc 2025 置信度 0.80
• Energy collaborative optimization of power routing based on PPO and generative adversarial imitation learning.
  Under the general trend of global energy transformation, the proportion of renewable energy in the power sector continues to increase. Power routers are of great significance for improving energy utilization efficiency and ensuring the stable operation of powe…
  pubmed Lyu J, Huang J 2026 置信度 0.82
• An Emerging Disease of Leaf Spot Caused by Paramyrothecium vignicola on Soybean in China.
  Soybean (Glycine max) is an important legume crop worldwide. An emerging leaf spot was observed in soybean plants with obvious black necrotic spot symptoms during the disease survey in Changping District, Beijing, China. To confirm the causal agent, the pathog…
  europepmc 2026 置信度 0.80
• Tri-stream multi-model architecture for real-time detection of BeiDou signal manipulation in UAV swarms.
  This study presents a novel framework for detecting and mitigating BeiDou Global Navigation Satellite Systems (GNSS) spoofing in decentralized Unmanned Aerial Vehicle (UAV) swarm systems and addressed a critical vulnerability in autonomous aerial operations. T…
  europepmc 2026 置信度 0.80
• When robots reshape teams: neurodynamic insights into taskwork and teamwork in search and rescue.
  Introduction Beyond traditional, dyadic human-robot interaction, embedding robots into multi-human teams, such as search and rescue (SAR), requires an understanding of fundamental aspects of team composition and dynamics. While considerable work has examined h…
  europepmc 2026 置信度 0.80
• A fusion deep Q-learning and particle swarm optimization algorithm for adaptive resource allocation in cloud computing circumstances.
  Effective resource allocation in cloud computing continues a critical challenge due to dynamic loads, stringent service-level expectations, and the need to balance execution time, energy, and cost. This study suggests a hybrid framework that integrates Deep Q-…
  europepmc 2026 置信度 0.80
• Dynamic appliance scheduling and energy management in smart homes using adaptive reinforcement learning techniques.
  Smart home energy management is complicated because of varying user preferences, expenses, and consumption. These dynamics are difficult for traditional systems to handle, but new developments in reinforcement learning and optimization may be able to help. The…
  europepmc 2025 置信度 0.80
• Decentralized Computation Offloading Strategy via Multi-Agent Deep Reinforcement Learning for Multi-Access Edge Computing Systems.
  Multi-access edge computing (MEC) has been widely recognized as a promising solution for alleviating the computational burden on edge devices, particularly in supporting fast and real-time processing of resource-intensive applications. In this paper, we propos…
  pubmed Adu E, Lee Y, Moon J, Jang S 等 2026 置信度 0.82
• Rethinking microbial biopesticide development and uptake.
  Biopesticides, pesticides based on living organisms and/or their bioactive compounds, are increasingly being used as alternatives and replacements to chemical and synthetic pesticides. This is largely due to human and environmental safety concerns, the emergen…
  europepmc 2026 置信度 0.80
• Tetramethylpyrazine nitrone: a multifaceted neuroprotective agent in neurodegenerative disorders.
  Neurodegenerative disorders such as Alzheimer's disease (AD), Parkinson's disease (PD), and amyotrophic lateral sclerosis (ALS) share key pathological features, including oxidative stress, mitochondrial dysfunction, and impaired protein homeostasis, yet remain…
  europepmc 2026 置信度 0.80
• Norm mining, identification, and detection: a systematic literature review.
  This paper presents a systematic literature review on norm identification in multi-agent systems. Norms play a crucial role in guiding agent behavior, ensuring cooperation, and resolving conflicts. By analyzing 35 selected studies, we categorize methods for de…
  pubmed Alcaraz B, Mualla Y, Bhattacharya S, Tchappi I 等 2026 置信度 0.82
• A Decolonial Lexicon for Immunology.
  The discipline of immunology has historically been foundationally framed by metaphors of war, portraying the body as a sovereign state defending its territory against foreign invaders. This paradigm, however, is not strictly a biological necessity but also a h…
  europepmc 2026 置信度 0.80
• Embodied intelligence-driven adaptive collaboration in supply chains: A four-dimensional synergy framework and mechanism analysis.
  Existing research focuses on data-driven algorithm optimization but overlooks the embodied nature of supply chains as physical and digital integrated systems, leading to a disconnect between AI and physical collaboration. This study introduces embodied intelli…
  europepmc 2026 置信度 0.80
• Infectious bacteria as biological warfare agents: mechanisms, epidemiological threats, and defense strategies.
  Infectious bacteria remain among the most plausible agents for deliberate biological attack because they combine environmental robustness, low infectious dose, and the capacity for rapid, severe disease. This review synthesizes current knowledge on major bacte…
  europepmc 2026 置信度 0.80
• Protocatechuic Acid Alleviates D-Gal-Induced Renal Senescence and Injury in Mice by Regulating Taurine Metabolism.
  Protocatechuic acid (PCA), a natural phenolic compound with antioxidant and anti-inflammatory properties, has been proposed as a potential therapeutic agent against aging-related diseases. This study investigated the protective effects of PCA on D-galactose (D…
  europepmc 2026 置信度 0.80
• Optimization of urban freight intelligent route based on reinforcement learning.
  Increased traffic congestion, limited delivery windows, vehicles' diverse fleets, and dynamic environments are all contributing factors to the inefficiency of urban freight systems. Due to the inability of traditional routing techniques to adjust in real-time …
  europepmc 2026 置信度 0.80
• Breaking Through the Limits: Nanomedicine at the Service of New Drug Combinations to Tackle Pancreatic Cancer.
  Pancreatic ductal adenocarcinoma (PDAC) is among the most aggressive cancers, with a poor prognosis due to late diagnosis and resistance to chemotherapy. Gemcitabine (GEM) monotherapy was the gold standard treatment for PDAC until the early 2010s, when two com…
  europepmc 2026 置信度 0.80
• Evaluating clinical AI summaries with large language models as judges.
  Electronic Health Records (EHRs) contain vast clinical data that are difficult for providers to synthesize. Generative AI with Large Language Models (LLMs) can summarize records to reduce cognitive burden, but ensuring accuracy requires reliable evaluation. Hu…
  pubmed Croxford E, Gao Y, First E, Pellegrino N 等 2025 置信度 0.82
• Cerium-based nanozymes for chemodynamic therapy: tumor microenvironment-responsive mechanisms and applications.
  Cerium-based nanozymes (CeNZs) are a class of nanomaterials possessing enzyme-like catalytic activities. Their unique Ce 3+ /Ce 4+ redox pair and multi-enzyme mimicking activities make them highly advantageous for tumor chemodynamic therapy (CDT). This review …
  europepmc 2026 置信度 0.80
• EC2Seq2Sql: Patient-trial matching with LLM agents.
  Timely identification of patients who meet clinical trial eligibility criteria is a persistent bottleneck in trial recruitment because the criteria are written in flexible natural language, while hospital EHRs are stored in structured schemas. To bridge this g…
  europepmc 2026 置信度 0.80
• Biocontrol strategies for fungal diseases of <i>Ganoderma lucidum</i>: from antagonistic microbes and synthetic communities to intelligent technologies.
  Ganoderma lucidum , a rare macrofungus renowned for its substantial medicinal and economic significance, is increasingly at risk from various pathogenic fungi, such as Neurospora sitophila , Trichoderma spp., and Fusarium graminearum , particularly during exte…
  europepmc 2026 置信度 0.80
• Safety assessment of Neulasta® (pegfilgrastim) in patients with solid tumors: a real-world adverse event analysis from the FAERS database.
  The study was based on the FDA Adverse Event Reporting System (FAERS) database, with the objective of analysing the actual safety of Neulasta® (pegfilgrastim) in patients with solid tumours. This study also sought to provide a reference for the use of clinical…
  europepmc 2026 置信度 0.80
• A review of embodied intelligence systems: a three-layer framework integrating multimodal perception, world modeling, and structured strategies.
  Embodied intelligent systems build upon the foundations of behavioral robotics and classical cognitive architectures. They integrate multimodal perception, world modeling, and adaptive control to support closed-loop interaction in dynamic and uncertain environ…
  europepmc 2025 置信度 0.80
• Net Carbon Sink Potential of Porous Vegetated Concrete: A Life-Cycle Assessment.
  Porous vegetated concrete has been widely used in highway slope protection because it provides both engineering stability and ecological restoration benefits. However, its life-cycle carbon emissions and long-term carbon sequestration performance have not been…
  europepmc 2026 置信度 0.80
• Enhancing Spectral Efficiency of 6G Downlink Beamforming via Cooperative Multi-Agent Deep Reinforcement Learning.
  This paper presents a new beamforming algorithm for Multi-User Multiple-Input Multiple-Output (MU-MIMO) systems using Multi-Agent Reinforcement Learning (MARL). The proposed approach is shown to significantly enhance the efficiency and performance of future wi…
  pubmed Al Janaby A, Al-Rizzo H, Qassim Y 2026 置信度 0.82
• PROTOCOL: Advancing Agent Networks and Merchant Payments for Financial Inclusion in Low- and Middle-Income Countries (LMICs): An Evidence and Gap Map.
  This Evidence and Gap Map (EGM) protocol aims to systematically identify, map, and synthesize the existing evidence on supply-side interventions that strengthen agent networks and merchant payment systems for advancing financial inclusion in low- and middle-in…
  europepmc 2026 置信度 0.80
• Fully Bionic Self-Iterating Shared Information Body Architecture: Design of a Public Information Carrier for Global Intelligent Agents 全仿生自迭代共享信息躯体架构:面向全域智能主体的公共信息载体设计
  Core Research Conclusions Upfront 核心研究结论前置 This architecture is not a simple bionic rhetoric of distributed technology, but strictly takes the Central Dogma of eukaryotic organisms as the bottom line of information flow logic, and completely maps the "informat…
  datacite 郭, 洋洋 2026 置信度 0.66
• Multi-Agent Based Class Scheduling System
  This paper is based on the existing multi-issue Negotiation Model (NM) and Multi-Agent technology combined with a more comprehensive negotiation strategy, so that the Multi-Agent-based scheduling system can better solve the problem of resource conflict and tea…
  crossref Shenglin Liang 2024-08-01T14:26:06Z 置信度 0.70
• Decentralized multi-agent path finding framework and strategies based on automated negotiation
  Abstract This paper introduces a negotiation framework to solve the Multi-Agent Path Finding (MAPF) Problem for self-interested agents in a decentralized fashion. The framework aims to achieve a good trade-off between the privacy of the agents and the effectiv…
  crossref M. Onur Keskin, Furkan Cantürk, Cihan Eran, Reyhan Aydoğan 2024-03-13T04:55:41Z 置信度 0.70
• Multi-Agent Deep Reinforcement Learning based Multi-Objective Resource Optimization in a Distributed Manufacturing System
  Manufacturing processes of assembly lines are now changing from a single factory to distributed multi-factories for minimizing costs and meeting different customer demands. To achieve the production capacity of the distributed manufacturing system, minimize co…
  crossref Xinchang Shen, Chen-Khong Tham 2024-09-25T17:28:12Z 置信度 0.70
• High-Level Mission Planning for Multi-Agent Indoor System
  The manuscript presents a high-level mission planning for multi-agent indoor systems. The high-level mission planning separates the mission goals between the agents, plans the order of the mission goals, and provides corridors serving as constraints for a real…
  crossref Rostislav Karásek, Christian Kallies 2024-06-11T17:54:38Z 置信度 0.70
• MODEL OF A MULTI-AGENT SYSTEM FOR MONITORING AERONAUTICAL INFORMATION TELECOMMUNICATION NETWORK
  The purpose of the work in this article is to develop models and algorithms to ensure the effectiveness of monitoring the telecommunications network of information transmission in air navigation systems, allowing to systematize and improve the efficiency of th…
  crossref 2025-11-05T13:35:49Z 置信度 0.70
• Reliable Multi-agent Task Coordination Management System for Logistics System
  The global population is aging, leading to significant societal challenges, particularly in developed countries like Japan. This demographic shift exacerbates labor shortages, driving the demand for automation solutions such as warehouse logistics robots. Curr…
  crossref Bin Zhang, Jinghao Long, Duowen Chen 2024-11-06T18:37:15Z 置信度 0.70
• The Integration of Multi-Agent System and Multicriteria Analysis for Developing Participatory Planning Alternatives in Urban Contexts
  Decision-making problems, particularly in transformation and planning processes, often involve multiple conflicting objectives/criteria that should be considered. However, it is possible to distinguish between problems where a predefined and discrete set of al…
  crossref CATERINA CAPRIOLI 2024-08-07T01:26:24Z 置信度 0.70
• Introduction
  crossref Guanglei Zhao, Hailong Cui, Changchun Hua, Shuang Liu 2024-03-23T11:02:37Z 置信度 0.70
• Multi-Agent Based SOC Equalization Control Strategy for Distributed Battery Energy Storage System
  In the battery energy management system, it is important to maintain the consistency of state of charge (SOC). In this paper, a multi-agent based SOC equalization control strategy is proposed for power regulation in distributed battery energy storage system (B…
  crossref Shu Liu, Rui Ling 2025-02-13T18:29:08Z 置信度 0.70
• Multi-agent system for intelligent scheduling
  This work is dedicated to the development of a multi-agent system for intelligent scheduling: to simulate, to analyze and to optimize used parameters to achieve the best performance in terms of increasing the speed of Technician agents (they provide a field se…
  crossref Eugene Alooeff, Dzmitry Adzinets 2024-07-24T19:49:02Z 置信度 0.70
• Multi Agent System Based Control for Energy Management of Hybrid Microgrid System
  Microgrids are decentralized power generation systems installed on customer premises, incorporating various capacity generating sets and modes. These systems not only cater to the specific energy needs of the consumer but also contribute excess power back to t…
  crossref Praveen Kumar Reddy K, Balachennaiah Pagidi 2024-10-08T17:35:04Z 置信度 0.70
• Smart Scheduling in Urban Traffic: A Multi-Agent System for Dynamic Vanpooling
  crossref Negin Alisoltani, Mahdi Zargayouna 2025-03-01T23:24:53Z 置信度 0.70
• Formal contracts mitigate social dilemmas in multi-agent reinforcement learning
  Abstract Multi-agent Reinforcement Learning (MARL) is a powerful tool for training autonomous agents acting independently in a common environment. However, it can lead to sub-optimal behavior when individual incentives and group incentives diverge. Humans are …
  crossref Andreas Haupt, Phillip Christoffersen, Mehul Damani, Dylan Hadfield-Menell 2024-10-18T02:02:07Z 置信度 0.70
• Correction: Warmth and competence in human-agent cooperation
  crossref Kevin R. McKee, Xuechunzi Bai, Susan T. Fiske 2024-06-07T04:01:52Z 置信度 0.70
• Distributed Control Strategy of Central Heating System Based on Multi-Agent Consensus
  crossref Gang Su, Yongheng Peng, Wanxiang Yao, Shuangyang Zhang 2024-01-09T18:53:26Z 置信度 0.70
• Consensus of a new multi-agent system via multi-task, multi-control mechanism and multi-consensus strategy
  crossref Xiang Hu, Yu Xiong, Zufan Zhang, Chuandong Li 2024-03-21T19:19:43Z 置信度 0.70
• Team-wise effective communication in multi-agent reinforcement learning
  crossref Ming Yang, Kaiyan Zhao, Yiming Wang, Renzhi Dong 等 2024-07-18T01:01:25Z 置信度 0.70
• The Model of Benevolence for Trust in Multi-agent System
  crossref Tomasz Zurek, Adam Wyner, Tom van Engers 2025-03-01T23:24:38Z 置信度 0.70
• A Multi-Agent System Approach for Mitigating Partial Display Failures
  crossref Jacob Cappi, Jacob Hauenstein 2024-04-27T12:06:34Z 置信度 0.70
• Simulating a Multi-Agent UAV System Coordinated by State Machines Using Godot
  Unmanned aerial vehicles have advanced quickly and are now a dominant force in several domains, including military, security, and even logistics. 3D simulations with virtual environments are cost effective tools for assessing feasibility and costs of developin…
  crossref Leo Howard, Fuhua Lin, Henry Leung 2025-03-24T17:52:22Z 置信度 0.70
• Connected and Automated Transportation System in Multi-agent Environment^*
  Traffic simulation is important for transportation researchers, analysts, and policymakers. It can be used to test vehicle/traffic control algorithms, gain insights into traffic dynamics, and develop traffic management strategies that can improve the efficienc…
  crossref Ohay Angah, Yiran Zhang, Xuegang Jeff Ban 2024-07-15T17:19:28Z 置信度 0.70
• Intelligent E-Commerce Marketing System Based on Mobile Multi Agent
  Currently, research on intelligent mobile agents in the field of e-commerce is mostly still in the theoretical and mathematical argumentation stage, while actual research and system development are still in the initial stage, and there are also problems such a…
  crossref Xiaojie Zhang, Fangfang Li 2025-02-05T13:45:24Z 置信度 0.70
• Majority opinion diffusion: when tie-breaking rule matters
  Abstract Consider a graph G , which represents a social network, and assume that initially each node is either blue or white (corresponding to its opinion on a certain topic). In each round, all nodes simultaneously update their color to the most frequent colo…
  crossref Ahad N. Zehmakan 2024-05-20T07:01:37Z 置信度 0.70
• Contest partitioning in binary contests
  Abstract In this work we explore the opportunities presented by partitioning contestants in contest into disjoint groups, each competing in an independent contest, with its own prize. This, as opposed to most literature on contest design, which focuses on the …
  crossref Priel Levy, Yonatan Aumann, David Sarne 2024-02-27T08:02:39Z 置信度 0.70
• Decentralized control of multi-agent systems
  crossref Hao Zhang, Chao Huang, Zhuping Wang, Huaicheng Yan 2024-04-30T10:56:36Z 置信度 0.70
• Cost Optimization of Hybrid Energy Power Generation System Based on Multi-Agent
  crossref Xiaojuan Lu, Yuhang Zhu, Duojin Fan, Linggang Kong 等 2024-03-09T20:22:20Z 置信度 0.70
• A User-friendly Cloud-based Multi-agent Information System for Smart Energy-saving
  <p>The study focused on leveraging artificial intelligence (AI) for efficient energy conservation in scientific applications. The proposed cloud-based multi-agent system merges various intelligent technologies to swiftly gather high-quality cloud data fo…
  crossref Yi-Jen Su Yi-Jen Su, Sheng-Yuan Yang Yi-Jen Su 2024-03-28T06:16:16Z 置信度 0.70
• KAVE: A Knowledge-Based Multi-Agent System for Web Vulnerability Detection
  The growing use of the web has led to a rise in cyber attacks exploiting software vulnerabilities, thereby causing significant damage to companies and individuals. Static analysis tools can assist programmers in identifying vulnerabilities within their code. H…
  crossref Rafael Ramires, Ana Respício, Ibéria Medeiros 2024-10-15T17:19:18Z 置信度 0.70