AI Agent 生态 · 全部实体（第 23 / 100 页）

本页收录第 2201–2300 条，共 10000 条 · 返回 AI Agent 生态 首页

• Preference Definition in a Multi-agent System Approach for User-Centric Internet of Things Smart Environments
  crossref Katarina Mandaric, Gordan Jezic 2025-03-01T23:24:47Z 置信度 0.70
• Human Resource Management Decision Support System Based on Multi Agent
  Due to the rapid development of the economy and the increasing level of management, human resource management is increasingly valued by enterprise managers and has become a very important and essential part of enterprise management. However, many traditional h…
  crossref Mohd Anuar Arshad, Wenyan Yao 2024-05-08T17:29:49Z 置信度 0.70
• Carbon trading supply chain management based on constrained deep reinforcement learning
  crossref Qinghao Wang, Yaodong Yang 2024-08-06T04:14:30Z 置信度 0.70
• Framework Design of a Multi-Educational-Agent System for University Lecturers
  Lecturers play a crucial role in students' learning activities. Their teaching planning, understanding of students' situations, and teaching methods all impact student success. The use of artificial intelligence in education is growing, but there is limited re…
  crossref Kai Yang, Lei Niu 2025-04-14T17:36:04Z 置信度 0.70
• Enterprise Dynamic Resource Allocation Optimization Based on Multi-agent System
  This research aims to solve the efficiency and flexibility problems in enterprise resource allocation by constructing an enterprise dynamic resource allocation optimization model based on a multi-agent system. The research introduces a dynamic adjustment mecha…
  crossref Xiaowang Niu 2024-11-18T20:38:38Z 置信度 0.70
• LFC Strategy of Power System with Hybrid Regulation Resources: A Multi-Agent-Based Reinforcement Learning Algorithm
  As renewable energy sources become increasingly prevalent, relying solely on conventional generators for load frequency control (LFC) in power systems proves to be neither cost-effective nor practical. Consequently, a variety of regulation resources (called hy…
  crossref Huixin Jiang, Chongxin Huang 2025-02-13T18:29:08Z 置信度 0.70
• Multi-agent system control based on first-order consensus algorithm
  The goal of this study is to investigate the control of multi-agent systems (MAS) using consensus algorithms, which have gained important attention due to their applications in robotics. We explored the basics of graph theory to understand the network structur…
  crossref Adjal Akram, Sebbagh Abdennour 2025-01-09T19:37:19Z 置信度 0.70
• Collaborative optimization of multi-energy multi-microgrid system: A hierarchical trust-region multi-agent reinforcement learning approach
  crossref Xuesong Xu, Kai Xu, Ziyang Zeng, Jiale Tang 等 2024-08-13T09:20:51Z 置信度 0.70
• Multi-agent Reinforcement Learning-based Network Intrusion Detection System
  Intrusion Detection Systems (IDS) play a crucial role in ensuring the security of computer networks. Machine learning has emerged as a popular approach for intrusion detection due to its ability to analyze and detect patterns in large volumes of data. However,…
  crossref Amine Tellache, Amdjed Mokhtari, Abdelaziz Amara Korba, Yacine Ghamri-Doudane 2024-07-02T17:23:51Z 置信度 0.70
• The Troupe System: An autonomous multi-agent rover swarm
  Autonomous cooperative robotic systems are the future of space exploration. The complexity of such systems makes their development, verification and assurance challenging. The Robust Software Engineering group at NASA Ames has developed the Troupe project that…
  crossref Nathaniel Benz, Irfan Sljivo, Pavlo G. Vlastos, Aaron Woodard 等 2024-01-29T22:19:16Z 置信度 0.70
• Designing a Multi-Agent System for Smart Grid Management
  This paper addresses the claim that by enabling intelligent, flexible, and autonomous decision-making at the local scale, a multi-agent system (MAS) can substantially strengthen the performance, reliability, and durability of smart grid operations. We discuss …
  crossref Y. Vahi, Ashrey Ignise 2025-08-11T09:49:11Z 置信度 0.70
• The Multi Agent System Solutions for Wireless Sensor Network Applications
  crossref Khin Haymar Saw Hla, YoungSik Choi, Jong Sou Park 2008-04-01T20:15:40Z 置信度 0.70
• Multi-agent low-carbon optimal dispatch of regional integrated energy system based on mixed game theory
  crossref Ziwen Liang, Longhua Mu 2024-03-08T07:32:18Z 置信度 0.70
• Optimization of Logistics Information System based on Multi-Agent Reinforcement Learning
  Real-time traffic management and optimization are crucial for the efficiency and sustainability of logistics information systems. This research work proposes an innovative approach to optimize logistics information systems using a multi-agent reinforcement lea…
  crossref Chunrong Lu, Yue Wu 2024-04-11T18:47:30Z 置信度 0.70
• Cooperative Control of Multi-Agent Systems with Uncertainties
  crossref 2024-04-30T12:50:30Z 置信度 0.70
• Multi-Agent Reinforcement Learning for Energy Management in Community Energy Trading
  Considering the differentiated characteristics of prosumers in new power systems, the high importance of privacy in energy trading and the limitations of traditional model-based optimization methods within multiple uncertainties, this paper proposes a multi-ag…
  crossref Zeting Liang, Jiehui Zheng, Zhigang Li 2024-10-23T17:44:28Z 置信度 0.70
• Emergent cooperation from mutual acknowledgment exchange in multi-agent reinforcement learning
  Abstract Peer incentivization (PI) is a recent approach where all agents learn to reward or penalize each other in a distributed fashion, which often leads to emergent cooperation. Current PI mechanisms implicitly assume a flawless communication channel in ord…
  crossref Thomy Phan, Felix Sommer, Fabian Ritz, Philipp Altmann 等 2024-07-11T06:01:45Z 置信度 0.70
• Explainability and Interpretability of an Ensemble Multi-agent System for Supervised Learning
  crossref Clément Blanco-Volle, Nicolas Verstaevel, Stéphanie Combettes, Marie-Pierre Gleizes 等 2024-11-16T04:57:24Z 置信度 0.70
• Logic-based cognitive planning for conversational agents
  crossref Jorge Luis Fernandez Davila, Dominique Longin, Emiliano Lorini, Frédéric Maris 2024-05-20T07:01:37Z 置信度 0.70
• A comprehensive analysis of agent factorization and learning algorithms in multiagent systems
  crossref Andreas Kallinteris, Stavros Orfanoudakis, Georgios Chalkiadakis 2024-06-26T09:03:00Z 置信度 0.70
• INTELLIGENT METHODS OF ENSURING CYBERSECURITY MULTI-AGENT CONTROL SYSTEM OF MICROGRID
  Цель исследования: разработка методов обнаружения и подавления последствий кибератак при вторичном регулировании напряжения в мультиагентных системах управления киберфизическими микросетями.Методы исследования: методы машинного обучения, вероятностные методы Р…
  crossref 2024-12-31T16:47:31Z 置信度 0.70
• A Retrieval-Augmented Multi-Agent System for Financial Statement Analysis
  We present a retrieval-augmented, multi-agent system (RAMAS) for machine-assisted analysis of corporate financial statements.The system integrates dense and sparse retrieval over XBRL/iXBRL regulatory filings, tool-using analysis agents for ratio and trend com…
  crossref 2026-02-11T09:21:31Z 置信度 0.70
• Cooperative Control of Multi-agent Systems
  This book focuses on stability analysis and control design approaches for multi-agent systems under network-induced constraints.
  crossref Guanglei Zhao, Hailong Cui, Changchun Hua, Shuang Liu 2024-03-23T11:02:37Z 置信度 0.70
• Quantum-Inspired Thermal Equilibrium: Integration of Collective Dynamics into Real-Time Stabilization of Magnetically Confined Fusion Plasmas — Extended Edition: Full-Pulse Operation, Hardware-Bounded Adversarial Stress Benchmark and Burn Control on TORAX 1.4, Hardware-in-the-Loop on Four Microcontroller ISAs, and a Second Machine: the GOLEM Tokamak from Public Data (Validated One-Parameter TORAX Model, 500 Blind-Predicted Shots, Chip-in-the-Loop Shot-to-Shot Campaigns, Power-Setpoint Regulation of a Burning Plasma, Balancing the Thermally Unstable Burn Point of the Canonical 0D Model in Hardware, and a Measured Decision-Rate Scaling Law for Unstable-Equilibrium Control)
  2026-08-01 — Scaling-law extension of the deposit: the price of a decision. Chapter 35 established that the collective balances the thermally unstable burn equilibrium (T* = 3.59 keV, e-folding time tau = 30.5 s); this chapter measures the quantitative law beh…
  datacite Westrick, Bernd 2026 置信度 0.66
• Quantum-Inspired Thermal Equilibrium: Integration of Collective Dynamics into Real-Time Stabilization of Magnetically Confined Fusion Plasmas — Extended Edition with Adversarial Stress Benchmark on TORAX 1.4 (Full ITER Pulse, Extended Severity Sweep up to ×1800 ITER Worst-Case, Hardware-in-the-Loop Demonstration on STM32F411 Microcontroller, and Single-Seed 500 000 s Long-Pulse Observation
  2026-06-25 — Hardware-in-the-loop extension of the IterHybrid-XHARD adversarial control-theory stress benchmark. The same controller, same plant, same disturbance cascade are re-run with the 8-bit quantised QITE collapse kernel transplanted onto a physical 5 E…
  datacite Westrick, Bernd 2026 置信度 0.66
• Quantum-Inspired Thermal Equilibrium: Integration of Collective Dynamics into Real-Time Stabilization of Magnetically Confined Fusion Plasmas — Extended Edition: Full-Pulse Operation, Hardware-Bounded Adversarial Stress Benchmark and Burn Control on TORAX 1.4, Hardware-in-the-Loop on Four Microcontroller ISAs, and a Second Machine: the GOLEM Tokamak from Public Data (Validated One-Parameter TORAX Model, 500 Blind-Predicted Shots, Chip-in-the-Loop Shot-to-Shot Campaigns, Power-Setpoint Regulation of a Burning Plasma, and Balancing the Thermally Unstable Burn Point of the Canonical 0D Model in Hardware)
  2026-07-30 — Unstable-branch extension of the deposit: the collective leaves the stable operating points. After stabilise (chapters 29–32), optimise (chapter 33) and regulate (chapter 34), the controller now BALANCES — it holds the thermally unstable equilibri…
  datacite Westrick, Bernd 2026 置信度 0.66
• Quantum-Inspired Thermal Equilibrium: Integration of Collective Dynamics into Real-Time Stabilization of Magnetically Confined Fusion Plasmas — Extended Edition with Adversarial Stress Benchmark on TORAX 1.4 (Full ITER Pulse Update)
  2026-06-12 — Full ITER pulse update of the IterHybrid-XHARD adversarial control-theory stress benchmark. The same controller, the same plant, the same disturbance cascade are re-run at 1200 s of plasma flat-top — the full ITER pulse duration target (van Mulder…
  datacite Westrick, Bernd 2026 置信度 0.66
• Quantum-Inspired Thermal Equilibrium: Integration of Collective Dynamics into Real-Time Stabilization of Magnetically Confined Fusion Plasmas — Extended Edition with Adversarial Stress Benchmark on TORAX 1.4 (Full ITER Pulse, Extended Severity Sweep up to ×1800 ITER Worst-Case, Hardware-in-the-Loop Demonstration on STM32F411 Microcontroller, Single-Seed 500 000 s Long-Pulse Observation, Third-ISA Verification on ESP32-C3 RISC-V Microcontroller with 16-bit Q16 Kernel, 100-Seed Nominal Sweep on the van Mulders ITER-Hybrid Scenario, and 10-Seed Full-Pulse Operation from 3 MA Cold-Start Rampup through L-H Transition to 10 000 s Self-Heated Burn under Continuous Chip Control)
  2026-07-13 — Full-pulse extension of the deposit: the controller drives the complete ITER pulse envelope — cold start, current rampup, L-H transition, ignition and self-heated burn — in one continuous closed-loop simulation on the same physical 2 EUR ESP32-C3 …
  datacite Westrick, Bernd 2026 置信度 0.66
• Quantum-Inspired Thermal Equilibrium: Integration of Collective Dynamics into Real-Time Stabilization of Magnetically Confined Fusion Plasmas — Extended Edition: Full-Pulse Operation, Hardware-Bounded Adversarial Stress Benchmark and Burn Control on TORAX 1.4, Hardware-in-the-Loop on Four Microcontroller ISAs, and a Second Machine: the GOLEM Tokamak from Public Data (Validated One-Parameter TORAX Model, 500 Blind-Predicted Shots, Chip-in-the-Loop Shot-to-Shot Campaigns, Power-Setpoint Regulation of a Burning Plasma, Balancing the Thermally Unstable Burn Point of the Canonical 0D Model in Hardware, a Measured Decision-Rate Scaling Law for Unstable-Equilibrium Control, its Blind Validation on the Full Transport Plant, and Commanded Burn Cycles Through the Unstable Branch)
  2026-08-02 — Validation extension of the deposit: the law holds, and the unstable branch becomes a road. Chapter 36 measured a decision-rate law on the canonical 0D model (existence boundary ~4.3 decisions per e-folding time, migrating logarithmically with sen…
  datacite Westrick, Bernd 2026 置信度 0.66
• Quantum-Inspired Thermal Equilibrium: Integration of Collective Dynamics into Real-Time Stabilization of Magnetically Confined Fusion Plasmas — Extended Edition with Adversarial Stress Benchmark on TORAX 1.4
  2026-06-07 — Adversarial control-theory stress benchmark of the QITE multi-agent plasma controller on the native Google DeepMind TORAX 1.4 step-level API (Citrin et al., 2024) under the deliberately exaggerated IterHybrid-XHARD disturbance cascade. The benchma…
  datacite Westrick, Bernd 2026 置信度 0.66
• An Information-Flow Perspective on Explainability Requirements: Specification and Verification
  Explainable systems expose information about why certain observed effects are happening to the agents interacting with them. We argue that this constitutes a positive flow of information that needs to be specified, verified, and balanced against negative infor…
  datacite Finkbeiner, Bernd, Frenkel, Hadar, Siber, Julian 2025 置信度 0.66 Logic in Computer Science (cs.LO)Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• Mathematical Models for Soil-Transmitted Helminth Control: A Systematic Review Protocol
  To: The Selection Committee Nordic Africa Institute African Scholarship Programme Uppsala, Sweden Subject: Letter of Support for Lemjini Masandawa African Scholarship Programme 2027 Dear Members of the Selection Committee, I am pleased to give my strongest rec…
  datacite Miracle, Amadi, Isambi Sailon, Mbalawata, Safari, Kinung'hi, Silas Steven, Mirau 2026 置信度 0.66
• Mathematical Models for Soil-Transmitted Helminth Control: A Systematic Review Protocol
  To: The Selection Committee Nordic Africa Institute African Scholarship Programme Uppsala, Sweden Subject: Letter of Support for Lemjini Masandawa African Scholarship Programme 2027 Dear Members of the Selection Committee, I am pleased to give my strongest rec…
  datacite Miracle, Amadi, Isambi Sailon, Mbalawata, Safari, Kinung'hi, Silas Steven, Mirau 2026 置信度 0.66
• The Secondary Signature of Immune System - The Architecture of Secondary Stage - Sam Coole 2026 ©️
  The Secondary Signature of the Immune System Framework / The Architecture of Secondary Stage Anti-Cooling-Coding-Maintenance (ACCM) Author: Sam Coole‌ Foreword This work is not a minor revision to existing immunology—it is a paradigm reset. For decades, the fi…
  datacite COOLE, SAM 2026 置信度 0.66
• The Secondary Signature of Immune System - The Architecture of Secondary Stage - Sam Coole 2026 ©️
  The Secondary Signature of the Immune System Framework / The Architecture of Secondary Stage Anti-Cooling-Coding-Maintenance (ACCM) Author: Sam Coole‌ Foreword This work is not a minor revision to existing immunology—it is a paradigm reset. For decades, the fi…
  datacite COOLE, SAM 2026 置信度 0.66
• A Multi-Layer Resilient Architecture for Autonomous Quadcopter Flight Under Environmental Uncertainties
  This paper presents a resilient, multi-layer architecture designed to ensure reliable autonomous operation of single and multiple quadcopters. The architecture leverages the resilient spacecraft executive to hierarchically organize trajectory-planning and flig…
  preprints 2025 置信度 0.74
• Research on API Security Gateway and Data Access Control Model for Multi-Tenant Full-Stack Systems
  To address API abuse and unauthorized data access in multi-tenant systems, this paper proposes a full-stack security gateway framework based on zero-trust access and policy verification. The system integrates Envoy Gateway and the OPA (Open Policy Agent) polic…
  preprints 2025 置信度 0.74
• A Multi-Agent Approach to Generating Context-Rich Gene Sets
  Gene sets are collections of genes that share a common biological function, process, or component that can be used to get insight into the biological relevance of genomic data. Databases containing these gene sets aids in a wide array of analytical methods. Th…
  preprints 2025 置信度 0.74
• Multi-Agent Deep Reinforcement Learning for Cooperative Path Planning of UAV Swarms
  Abstract Collaborative path planning for UAV swarms in dynamic uncertain environments faces dual challenges of partial observability and cooperation mechanism design. The decentralized decision-making nature of multi-agent reinforcement learning (MARL) establi…
  preprints 2025 置信度 0.74
• A deep reinforcement learning-based task offloading algorithm for cell-free architecture CFMADRL: Co-optimization of delay-energy sensitive tasks
  Abstract With the continuous proliferation of wireless devices, the growing pressure on wireless channels has resulted in degraded network quality for edge users and increased energy consumption of mobile devices. To enhance user experience and extend device b…
  preprints 2025 置信度 0.74
• The Operational Coherence Framework (OCOF): An Admissibility-Based Theory for Artificial Agents
  We present the Operational Coherence Framework (OCOF) v1.4, a formal theory defining the necessary topological conditions for static stability in artificial agents. Distinct from reinforcement learning or alignment paradigms that optimize scalar rewards, OCOF …
  preprints 2025 置信度 0.74
• A Scalable Multi-Agent Framework for Low-Resource E-Commerce Concept Extraction and Standardization
  Understanding shopping concepts in e-commerce is hard because consumer behavior, product terms, and technical details vary a lot. This paper presents MALLM, a new multi-agent framework based on LLaMA-2 70B. It improves concept understanding by letting speciali…
  preprints 2025 置信度 0.74
• WITHDRAWN: Adaptive fuzzy secure consensus control of  strict-feedback MASs under energy-constrained  DoS attacks: A high-order fully actuated system approach
  Abstract In this paper, an adaptive fuzzy secure consensus control strategy based on a high-order fully actuated (HOFA) system approach is proposed for strict-feedback multi-agent systems (SFMASs) under energy-constrained denial-of-service (DoS) attacks. The m…
  preprints 2025 置信度 0.74
• Multi-Weather DomainShifter: A Comprehensive Multi-Weather Transfer LLM Agent for Handling Domain Shift in Aerial Image Processing
  Recent deep learning-based remote sensing analysis models often struggle with performance degradation due to domain shifts caused by illumination variations (clear to overcast), changing atmospheric conditions (clear to foggy, dusty), and physical scene change…
  preprints 2025 置信度 0.74
• DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery
  Abstract Large language models (LLMs) integrated with autonomous agents hold significant potential for advancing scientific discovery through automated reasoning and task execution. However, applying LLM agents to drug discovery is still constrained by challen…
  preprints 2025 置信度 0.74
• Variation in uptake and dose reduction of CDK4/6 inhibitors for the treatment of breast cancer in England, 2019–2024: a descriptive observational study using OpenPrescribing Hospitals
  Background The number of novel cancer therapies approved for use in England by the National Institute for Health and Care Excellence is increasing. Monitoring the adoption of new therapies is important to assess equity of access and evaluate real-world prescri…
  europepmc 2026 置信度 0.80
• StimMAS: A Multi-Agent Framework for Automated Linguistic Stimulus Construction in Psychological Research
  The construction of high-quality experimental stimuli is foundational to psychological research, yet current practices remain labor-intensive, reliant on expert intuition, and limited in scale and reproducibility. As the field increasingly pursues large-scale,…
  preprints 2025 置信度 0.74
• Adaptive Distributed Fault-Tolerant Control for High-Speed Trains Based on a Multi-Body Dynamics Model
  This paper addresses the distributed control problem for high-speed trains subject to unknown actuator faults, input saturation, and parametric uncertainties—including structural variations among actuators, external resistance, and inter-carriage forces. A car…
  preprints 2025 置信度 0.74
• BioLab: End-to-End Autonomous Life Sciences Research with Multi-Agents System Integrating Biological Foundation Models
  ABSTRACT Scientific discovery in the life sciences remains hindered by fragmented workflows, narrow-scope computational models, and inefficient links between in silico prediction and wet-lab validation. We present BioLab, a multi-agent system that integrates d…
  preprints 2025 置信度 0.74
• Adaptive Workflow Allocation in Human–Machine Cooperative Anti-Money Laundering Operations
  This study develops an adaptive workflow allocation mechanism for anti-money laundering (AML) operations, aiming to improve the accuracy and efficiency of suspicious-transaction review. A multi-agent simulation platform was constructed to model transaction flo…
  preprints 2025 置信度 0.74
• (CMMSE paper) Social power of a stubborn leader and synchronization of agent opinions in the Concord/Partial Antagonism model of opinion dynamics
  Complex multi-parametric networked agent based social system described by a large set (system) of nonlinear coupled difference equations, the coupling being multiplicative, with a non-markovian stochastic dynamics is considered. In social modelling context, th…
  preprints 2025 置信度 0.74
• PhysAgent: A Multi-Agent Approach to the Automated Discovery of Physical Laws
  The discovery of physical laws has traditionally relied on human intuition, analytical reasoning, and experimental observation. However, modern physics research is increasingly constrained by challenges such as high specialization, fragmented workflows, and li…
  preprints 2025 置信度 0.74
• Topology-Driven Anti-Entanglement Control for Soft Robots
  In the field of precision manufacturing in complex constrained environments, the role of soft robots is increasingly prominent, and the realization of anti-winding control based on multi-intelligent body reinforcement learning has become a research hotspot. On…
  preprints 2025 置信度 0.74
• Strategic Ignorance in Financial Markets: When Not Knowing Improves Alpha and Stability
  The contemporary financial landscape is characterized by a paradox of plenty: while the volume and velocity of market data have increased exponentially, the decision-making quality of human and algorithmic agents often deteriorates under the weight of informat…
  preprints 2025 置信度 0.74
• The Spiritual Sniper: A Quantitative Metaphysical Framework
  This paper constructs a novel metaphysical framework for the archetype of the “Spiritual Sniper”—a figure whose silent awareness operates with precision at the level of karmic, temporal, and ontological structures. By synthesizing spiritual traditions, quantum…
  preprints 2025 置信度 0.74
• An Intelligent Architecture for University Institutional Knowledge: Integrating Ontologies, Intelligent Agents, and the Semantic Web
  This article presents a distributed architecture for university institutional knowledge management, integrating OWL ontologies, FIPA-ACL-compliant multi-agent systems (MAS), and Semantic Web technologies (RDF, SPARQL). An ontology engineered through the METHON…
  preprints 2025 置信度 0.74
• BPMN-Based Design of Multi-Agent Systems: Personalized Language Learning Workflow Automation with RAG-Enhanced Knowledge Access
  The intersection of Artificial Intelligence (AI) and education is revolutionizing learning and teaching in this digital era, with Generative AI and large language models (LLMs) heralding even greater possibilities for the future. This paper presents a novel ap…
  preprints 2025 置信度 0.74
• Prompt-to-Pill: Multi-Agent Drug Discovery and Clinical Simulation Pipeline
  This study presents a comprehensive, modular framework for AI-driven drug discovery (DD) and clinical trial simulation, spanning from target identification to virtual patient recruitment. Synthesized from a systematic analysis of 51 LLM-based systems, the prop…
  preprints 2025 置信度 0.74
• AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems
  The rapid advancement of Large Language Models (LLMs) has catalyzed the development of multi-agent systems, where multiple LLM-based agents collaborate to solve complex tasks. However, existing systems predominantly rely on centralized coordination, which intr…
  preprints 2025 置信度 0.74
• Fault-tolerant control of nonlinear heterogeneous multi-agent systems with sensors/ actuators faults under inconsistent Markov via double event-triggered strategy
  Abstract This paper addresses the fault-tolerant control of nonlinear heterogeneous multi-agent systems with actuators and sensors affected by faults under inconsistent Markov switching topology.A double event-triggered strategy is introduced to reduce the com…
  preprints 2025 置信度 0.74
• Foodways of “The Wall People”: Organic Residue Analysis and Scanning Electron Microscopy of the Pottery Assemblages from the Long-Wall System in Mongolia
  Abstract This research presents the first comprehensive analysis of medieval pottery (10th–13th centuries CE) from Mongolia, focusing on ceramics unearthed from the Medieval Border Systems. Lipid residue and archaeobotanical analyses revealed the presence of d…
  preprints 2026 置信度 0.74
• Multi-agent AI System for High Quality Metadata Curation at Scale
  High-quality metadata is essential for downstream AI applications, yet metadata curation remains a persistent bottleneck in biomedical research. The core challenge lies in balancing quality and scalability. Manual curation delivers high quality, reliable annot…
  preprints 2025 置信度 0.74
• RoDA: A Role-Playing Dual-Agent Framework to Drive Nursing Robots in Bimanual Coordination Tasks
  Abstract Effective bimanual collaboration represents a significant research objective for Large Language Model (LLM)-driven nursing robots. However, current approaches are constrained by critical limitations: the single-thread LLM task planner (ST-Planner) lac…
  preprints 2025 置信度 0.74
• PathSync: A Multi-Agent Path Finder
  This paper presents a multi-agent pathfinding system designed for industrial environmentswhere multiple autonomous robots operate simultaneously. The system supports up to four robots andleverages the A* search algorithm to compute optimal, collision-free path…
  preprints 2025 置信度 0.74
• Breaking Barriers: Multi-Agent Prompt Fusion for Automated LLM Jailbreaks
  Abstract With the widespread deployment of Large Language Models (LLMs) across various natural language processing tasks, their potential security vulnerabilities have become increasingly prominent, emerging as a crucial issue in AI safety research. Although v…
  preprints 2025 置信度 0.74
• Uncovering biological patterns across studies through automated large-scale reanalyses of public transcriptomic data
  Large amounts of transcriptomic data have been made available in public repositories. Systematic reanalyses of these data offer the potential to identifying conserved biological patterns or context-specific signatures. However, this is a labour intensive proce…
  preprints 2025 置信度 0.74
• TheraMind: A Multi-LLM Agent for Accelerating Drug Repurposing in Lung Cancer via Case Report Mining
  Abstract Published clinical case reports are a valuable yet underutilized source of evidence for drug repurposing. However, systematically identifying relevant reports remains a challenge due to the volume of literature and the diversity of candidate compounds…
  preprints 2025 置信度 0.74
• A Chatbot for the Management of Bipolar Disorder: Using Retrieval-Augmented Generation with an Open-Weight Large Language Model to Answer Clinical Questions Based on the CANMAT and ISBD 2018 Guidelines for Bipolar Disorder
  Objective Clinical practice guidelines support evidence-based care but are often underused due to complexity, time constraints, and navigation challenges. We investigated whether a conversational agent (chatbot) using an open-weight large language model (LLM) …
  preprints 2025 置信度 0.74
• Prescribing Trends of Antimicrobials in Obstetric and Gynaecological Inpatients: A Prospective Drug Utilization Study with Concurrent Antimicrobial Stewardship Audit from a Tertiary Care Hospital in Karachi, Pakistan
  Background Antimicrobial resistance (AMR) disproportionately affects low- and middle-income countries (LMICs) such as Pakistan, where obstetric and gynaecological (OBGYN) patients carry high antibiotic exposure. Specialty-specific drug utilization data with co…
  preprints 2026 置信度 0.74
• Research on Data-Driven Building Form Performance-Based Design Method of Libraries
  Abstract With the prevalence of the concept of low-carbon sustainable development in the building industry, building form performance-based design has garnered widespread attention from related scholars. This research takes a public library building located in…
  preprints 2025 置信度 0.74
• A Multi-Scale AI Framework for Informal STEM Learning: Paramorphic Digital Twins for Underserved Communities
  This research presents a novel Multi-scale PAramorphic Kernel (MPAK) learning framework that is designed to enable autonomous, context-adaptive STEM learning for electrical and renewable energy topics. By employing distributed multi-agent kernel cores, recursi…
  preprints 2025 置信度 0.74
• Digraph-based cluster consensus in delayed MASs with delayed aperiodic intermittent communication--with or without even-triggered mechanism
  Abstract This paper studies a novel type of clustered MAS(multi-agent system) model combined with both the factor of delayed and non-delayed intermittent communication , and strongly directed graph and event-triggered condition for the system are also consider…
  preprints 2025 置信度 0.74
• Collaborative Mechanisms in Manufacturing Ecosystems under Digitalization and Greenization Initiatives
  Abstract Under the backdrop of developing new quality productive forces, digital technology has provided new impetus for the transformation and upgrading of traditional manufacturing and opened new pathways for the green and collaborative development of the ma…
  preprints 2025 置信度 0.74
• The Potential of a "Theory of Everything": A Demonstration from Generalized Agent Theory and its Three Criteria
  Inspired by the concept of 'Agent' from artificial intelligence, this paper posits a novel theoretical premise: any viable 'Theory of Everything' (ToE) must first provide a unified descriptive framework for all forms of existence in the Universe, encompassing …
  preprints 2025 置信度 0.74
• Simulation-Based Performance Analysis of Ventilation and Fire Protection Strategies in Road Tunnel Fires: Review
  Abstract Tunnel fires are among the most critical hazards in transportation infrastructure due to rapid smoke spread, high heat release, and constrained evacuation opportunities. In recent years, computational simulation has become the primary tool to evaluate…
  preprints 2025 置信度 0.74
• PhenoGraph: A Multi-Agent Framework for Phenotype-driven Discovery in Spatial Transcriptomics Data Augmented with Knowledge Graphs
  Spatial transcriptomics (ST) provides powerful insights into gene expression patterns within tissue structures, enabling the discovery of molecular mechanisms in complex tumor microenvironments (TMEs). Phenotype-based discovery in ST data holds transformative …
  preprints 2025 置信度 0.74
• Coal Mine Data Analysis using Multi-Agent Assisted Knowledge Map and DRL Model
  Abstract To improve mining operations in terms of productivity, safety, and decision-making, intelligent mine architecture makes use of cutting-edge technology like knowledge graphs. By visually representing the interconnected data, processes, as well as equip…
  preprints 2025 置信度 0.74
• Agentic memory-augmented retrieval and evidence grounding for medical question-answering tasks
  Objective: To evaluate if a tool-using agent-based system utilizing large language models (LLMs) for medical question-answering (QA) tasks outperforms standalone LLMs. Methods: We developed a unified, open-source LLM-based agentic system that integrates docume…
  preprints 2025 置信度 0.74
• First-in-human case series of Embrace, a polyethylene glycol-based liquid embolic agent, utilisation for embolisation of arterial haemorrhage
  Abstract Background : There are a number of liquid embolic agents available and in development for the use of endovascular embolization. The Embrace Hydrogel Embolic System (HES) is an aqueous polyethylene glycol (PEG)-based liquid embolic agent that has been …
  preprints 2025 置信度 0.74
• Adaptive consensus tracking control of uncertain nonlinear system: A multi-channel triggering strategy
  Abstract This paper considers the consensus tracking control problem for a class of uncertain high-order nonlinear multi-agent systems (MASs) based on event-triggered communication. In order to maximize the savings of communication resources for MASs, the even…
  preprints 2025 置信度 0.74
• Fixed Time Leader Following Speed Consensus Control for MultiPMSMs Based on Multiagent Systems Consensus
  Abstract Consensus control of multi-agent systems offers scalability and robustness in group tasks. To improve the performance of multiple permanent magnet synchronous motors (multi-PMSMs) speed coordination, in this paper, we propose a fixed-time leader-follo…
  preprints 2025 置信度 0.74
• Deep Reinforcement Learning Approaches the MILP Optimum of a Multi-Energy Optimization in Energy Communities
  As energy systems transition toward high shares of variable renewable generation, local energy communities (ECs) are increasingly relevant for enabling demand-side flexibility and self-sufficiency. This shift is particularly evident in the residential sector, …
  preprints 2025 置信度 0.74
• Preclinical efficacy of combinatorial B7-H3 CAR T cells and ONC206 against diffuse intrinsic pontine glioma
  ABSTRACT Background Diffuse intrinsic pontine glioma (DIPG) is a fatal pediatric brain tumor affecting over 300 children annually in the United States. Chimeric antigen receptor (CAR) T cells are a targeted immune effector cell therapy with substantial clinica…
  preprints 2025 置信度 0.74
• The Paradigm Shift of Sustainable Development in Educational Economics in the Digitization-Intelligent Era: A Kuhnian Analysis
  This study employs Kuhn’s paradigm theory to analyze the imperative transition toward sustainable development in educational economics amid the Digitalization-Intelligent Era. Through factor deconstruction, we reveal that traditional educational economics—anch…
  preprints 2025 置信度 0.74
• Controlled Iterated Function Systems for Minority Dynamics and Diversity-Preserving Ergodic Control
  Abstract We study \emph{ergodic regulation} of large-agent strategic systems in which agents prefer to be in the minority. The population dynamics are modeled as a controlled iterated function system (IFS) on a Polish space; the control reshapes the transition…
  preprints 2025 置信度 0.74
• UniROS: ROS-Based Reinforcement Learning Across Simulated and Real-World Robotics
  Reinforcement Learning (RL) enables robots to learn and improve from data without being explicitly programmed. It is well-suited for tackling complex and diverse robotic tasks, offering adaptive solutions without relying on traditional, hand-designed approache…
  preprints 2025 置信度 0.74
• Application of reinforcement learning methods to allocate logistics resources to production halls in an automotive industry
  Abstract Efficiently managing internal logistics in the contemporary automobile industry is paramount. This paper delves into the simulation of an internal logistics (IL) system within an automotive factory, employing reinforcement learning. By capturing the u…
  preprints 2025 置信度 0.74
• Decoding the Multi-Dimensional Complexity of Glycosylation Reaction via Machine Learning
  Abstract Precise stereocontrol in glycosidic bond formation remains a central challenge in carbohydrate chemistry, governed by subtle, interdependent chemical and environmental factors that limit access to complex oligosaccharides and glycoconjugates. We devel…
  preprints 2025 置信度 0.74
• New flexible bidirectional converter for electric vehicle substations connecting microgrids
  Abstract This paper proposes a flexible and energy-efficient power conversion system capable of bidirectional energy flow betweenAC and DC microgrids, as well as electric vehicles (EVs). The converter is designed by integrating fundamental DC/DCtopologies—name…
  preprints 2025 置信度 0.74
• Agents’ Cognition in the Smart City: Agent Architecture Assessment Framework
  This paper presents an agent architecture interaction assessment framework developed using constructsand measures from architecture [11,12, 18, 26, 27, 28, 35, 46], agent-based modeling [15, 52], humanfactors [36, 38, 39, 40, 45, 49, 50, 51], systems science e…
  preprints 2025 置信度 0.74
• A Federated Domain-Specific Architecture for Safe and Scalable Artificial Intelligence
  The pursuit of monolithic, general-purpose Artificial General Intelligence (AGI) has led to models that are computationally inefficient, inherently unsafe, and prone to unreliable performance on specialized tasks. We propose a new architectural paradigm, the S…
  preprints 2025 置信度 0.74
• The Sovereign SOC: A Simulation Framework for Quantum-Enhanced Federated Security Operations
  Traditional Security Operations Centers (SOCs) lack physical-layer visibility and suffer from high false positive rates, leaving critical infrastructure vulnerable to hardware implants and electromagnetic side-channel attacks. This paper presents the Sovereign…
  preprints 2025 置信度 0.74
• Hybrid Active Learning with Privacy-Preserving Synthetic Data for Medical Multimodal LLM Enhancement
  Abstract We propose a novel framework for enhancing medical multimodal learning by integrating hybrid active learning (HAL) with privacy-preserving synthetic data generation, addressing critical challenges of data scarcity and patient privacy. The framework re…
  preprints 2025 置信度 0.74
• Prioritizing Combinational Drug Screening: A Ranking System for <i>In Vitro</i> Drug Combinations in Neurofibromatosis Type 1
  Neurofibromatosis type 1 (NF1) is a genetic disorder characterized by benign tumors, including plexiform neurofibromas, which can be difficult to treat. Currently, only two FDA-approved therapies exist: selumetinib, approved for pediatric patients with inopera…
  preprints 2025 置信度 0.74
• Experience-based Integral Reinforcement Learning Consensus for Nonlinear Multi-agent Systems
  Abstract This paper investigates an optimal consensus control problem and proposes a policy iteration algorithm based on online integral reinforcement learning for nonlinear multi-agent systems with unknown dynamics. Introducing a critic and actor networks int…
  preprints 2025 置信度 0.74
• Generalized Agent Theory from First Principles
  To address the fragmentation in the definition of Agent and the profound challenges concerning the nature of intelligence, consciousness, and the observer-based unification of physics, this paper establishes Generalized Agent Theory from first principles. The …
  preprints 2025 置信度 0.74
• Multi-Examiner: A Knowledge Graph-Driven System for Generating Comprehensive IT Questions with Higher-Order Thinking
  The Question Generation System (QGS) for Information Technology (IT) education, designed to create, evaluate, and improve Multiple-Choice Questions (MCQs) using Knowledge graphs (KGs) and Large Language Models (LLMs), encounters three major needs: ensuring the…
  preprints 2025 置信度 0.74
• Emergent Cognitive Convergence via Implementation: A Structured Loop Reflecting Four Theories of Mind – A Position Paper
  We report the discovery of a meaningful structural convergence among four influential theories of mind—Kahneman's dual-system theory, Friston's predictive processing, Minsky's society of mind, and Clark's extended mind—through their unintentional but systemati…
  preprints 2025 置信度 0.74
• Multi-Target Neuroprotective Mechanisms of Phenolic Compounds from Antiaris Africana against Parkinson's Disease
  Abstract Parkinson's disease (PD) is a neurodegenerative disorder with progressive motor and non-motor symptoms. Conventional treatments mainly manage symptoms, not causes, highlighting the need for new therapies. Natural phytochemicals, particularly phenolic …
  preprints 2025 置信度 0.74
• Time-Delay Resilient Cooperative Filters for Cyber-Physical Systems
  Reliable real-time and uninterrupted data tele-communication between subsystems in a Cyber Physical System (CPS) is at the core of secure operation of the CPS. Time-delay and Denial-of-Service (DoS) cyberattacks are among CPS cyber threats that could impair no…
  preprints 2025 置信度 0.74