AI Agent 生态 · 全部实体（第 18 / 100 页）

本页收录第 1701–1800 条，共 10000 条 · 返回 AI Agent 生态 首页

• Self-Triggered Connectivity Maintenance of a Teleoperated Multi-Agent System with Input Saturation
  crossref Liu Yang, Xinde Zhou, Zhixin Yan 2026-06-24T19:47:19Z 置信度 0.70
• Collective Autonomy Through Multi-Agent Coordination, Emotional Intelligence, and Swarm Learning
  This paper presents a new emotional intelligence (EI)-based swarm learning model to improve coordination and adaptability in a decentralized multiagent system. The proposed model will enable agents to share experiential knowledge and emotional context in real …
  crossref Sanjay Kumar, Sapna Bawankar 2026-04-13T19:35:25Z 置信度 0.70
• Multi-Agent KPI Generator and Recommendation System
  Organizations increasingly rely on Key Performance Indicators (KPIs) to monitor performance and support data-driven decisions, yet defining relevant KPIs and ensuring their reliability remains a manual, expertise-heavy, and error-prone process. Existing analyt…
  crossref D H Tharun Reddy, Josy Elsa Varghese, Prateek P 2026-05-26T19:40:12Z 置信度 0.70
• Cultivating Collaborative Innovation Ability Model in Higher Education Based on Multi-Agent System
  Inderscience is a global company, a dynamic leading independent journal publisher disseminates the latest research across the broad fields of science, engineering and technology; management, public and business administration; environment, ecological economics…
  crossref Junli Yang 2026-05-12T13:08:11Z 置信度 0.70
• Automated negotiation with no information about partner utility functions using the Tentative Acceptance Unique Offers Protocol
  crossref Yasser Mohammad 2026-04-17T07:32:35Z 置信度 0.70
• Quantification of transfer in reinforcement learning via regret bounds for learning agents
  We present an approach for the quantification of the usefulness of transfer in reinforcement learning via regret bounds for a multi-agent setting. Considering a number of $$\varvec{\aleph }$$ agents operating in the same Markov decision process, however possib…
  crossref Adrienne Tuynman, Ronald Ortner 2026-03-11T06:59:15Z 置信度 0.70
• Identifying Collective Intelligence Factor in LLM Agent Groups for Generalizable Multi-Agent System Design
  Large language model (LLM)-based multiagent systems (MASs) have shown impressive performance in solving a wide range of complex problems.However, previous studies mainly focus on designing customized MAS for specific tasks, while a critical research problem re…
  crossref Zhilun Zhou, Zihan Liu, Jiahe Liu, Yihan Wang 等 2026-07-01T12:25:50Z 置信度 0.70
• MAS-DPD: Multi-Agent System for Dark Pattern Detection Using Large Vision-Language Models
  crossref Xiang Wang 2026-05-09T10:50:37Z 置信度 0.70
• FireMAS: Improving fire detection system by leveraging vision language models using multi-agent system framework
  crossref Keyur Joshi, Subhash Chandra Pujari, Tjark Windisch, Markus König 2026-01-24T23:20:57Z 置信度 0.70
• MSR155 A MULTI-AGENT GENAI SYSTEM FOR TRACEABLE, MULTI-COUNTRY LANDSCAPE ASSESSMENT IN MASH
  crossref Jag Chhatwal, Mine Tekman, Ismail F. Yildirim, Sumeyye Samur 等 2026-06-26T16:45:42Z 置信度 0.70
• Fault-Tolerant Formation Tracking Control for Multi-Agent Systems with Bearing-Only Measurement.
  This work investigates the formation control problem relying solely on bearing measurements for multi-agent systems in the two-dimensional plane. In order to achieve the desired geometric formation configuration between leaders and followers subject to actuato…
  europepmc 2026 置信度 0.80
• HH-MAPPO: A Hierarchical Reinforcement Learning Framework for Dynamic-Scale Target-Attacker-Defender Games.
  The Target-Attacker-Defender (TAD) pursuit-evasion game is a core challenge in multi-agent cooperative control, yet real-world settings involving dynamic team scaling and strict energy constraints remain largely unaddressed. When scalable shared-parameter poli…
  europepmc 2026 置信度 0.80
• GR-MAPPO Algorithm for Perimeter Defense Problem in Multi-Agent Systems.
  Multi-agent perimeter defense plays a critical role in cooperative defense scenarios in unmanned swarms. However, existing deep reinforcement learning approaches struggle to effectively exploit both coordination and temporal information under constrained local…
  europepmc 2026 置信度 0.80
• Observer-based ADP for secure resource allocation in high-order nonlinear multi-agent systems under FDI attacks.
  This paper investigates the secure resource allocation problem (RAP) for high-order nonlinear multi-agent systems (MASs) under false data injection (FDI) attacks. Different from conventional RAPs, the considered problem involves both actuator-side and sensor-s…
  europepmc 2026 置信度 0.80
• Analysis of nutritional components and flavor compounds in naturally fermented, fermentation agent-fermented, and unfermented multi-grain pancakes.
  Traditional northern Chinese pancake fermentation faces challenges such as inconsistency, prolonged processing duration, and safety hazards. A controlled co-fermentation system (YL-7) was applied to multigrain pancakes for the first time, comparing with unferm…
  europepmc 2026 置信度 0.80
• Bounded Adaptive Sensitivity Through Bio-Inspired Digital Hormone Regulation for Emotionally Intelligent UAV Traffic Monitoring.
  Recently introduced affect-driven UAV controllers model behavioral sensitivity ( α ) as a static personality-dependent parameter, overlooking the cumulative influence of prolonged operational context. The Pull-Push Engine (PPE) regulates behavioral responses t…
  europepmc 2026 置信度 0.80
• Entropy-Regularized Hierarchical MARL for Resilient Moving Target Defense in Cyber-Physical Systems.
  Cyber-Physical Systems (CPS), including smart grids and industrial control networks, must maintain secure and stable operations despite increasingly adaptive cyber threats. Existing moving target defense (MTD) approaches often rely on fixed reconfiguration str…
  europepmc 2026 置信度 0.80
• Leader-Following Fault-Tolerant Consensus Control for Multi-Agent Systems Based on Observers.
  In this paper, for leader-follower structure multi-agent systems (MASs), a new fault-tolerant consensus control mechanism which is called the distributed information estimation and centralized control scheme is developed. To begin with, for each follower agent…
  europepmc 2026 置信度 0.80
• Effect of multi-source solid waste synergistic activation on strength evolution and micro-mechanism of dredged sludge stabilized with low-carbon curing agent.
  To enhance the strength of solidified waste sludge, this study builds upon traditional cement-based sludge solidification methods and the waste-to-waste treatment principle. Cement, slag and fly ash were selected as solidifies, with water glass serving as an a…
  europepmc 2026 置信度 0.80
• Hybrid task and motion planning with reactive collision handling for multi-robot disassembly of complex products: application to EV batteries.
  This paper addresses the problem of multi-robot coordination for complex manipulation task sequences. We present a vision-driven task-and-motion planning (TAMP) framework for a real dual-agent platform that integrates task decomposition and allocation with a l…
  europepmc 2026 置信度 0.80
• Retrieval-augmented clinical decision support for structured hip-joint disease assessment.
  Background Hip-joint disease assessment requires integration of symptoms, imaging findings, staging criteria, and management context. Clinician-facing decision-support systems may help structure this reasoning but require defined clinical evaluation. Methods W…
  europepmc 2026 置信度 0.80
• <i>Gymnema sylvestre</i> as a Multi-Target Antidiabetic Agent: Mechanistic Insights and Metabolic Regulation.
  Diabetes mellitus (DM) is a complex metabolic disorder characterized by chronic hyperglycemia and represents a major global public health concern due to its rapidly increasing prevalence. Although current pharmacological therapies effectively achieve glycemic …
  europepmc 2026 置信度 0.80
• Distributed multi-objective optimization for discrete-time heterogeneous Multi-agent systems: A potential game-based method.
  This paper addresses the distributed multi-objective optimization problem for discrete-time heterogeneous multi-agent systems via potential games. Potential game-based methods are widely employed in distributed optimization for multi-agent systems, as they ena…
  europepmc 2026 置信度 0.80
• Swin-Qwen3: a three-stage vision-language framework for automated radiology report generation with multi-agent verification.
  Automated chest x-ray reporting could substantially reduce the burden on radiology services worldwide; however, the implementation of current vision-language models (VLMs) in clinical workflows remains limited by factual errors, hallucinations, and inadequate …
  pubmed Abdaoui H, Barbaria S, Al Kuwaiti A, Raouafi N 等 2026 置信度 0.82
• Distributed resilient consensus for heterogeneous fractional-order multi-agent systems against hybrid attacks.
  Consensus in multi-agent systems (MASs) relies on connectivity of communication topology and integrity of information, which are also the primary targets of cyber-attacks. Under such attacks, the hereditary property of fractional-order dynamics causes attack e…
  europepmc 2026 置信度 0.80
• Drug repurposing of sophoridine for sepsis-induced organ injury: from in-depth analysis of a single agent to a multi-target therapeutic paradigm.
  Sepsis-induced immune dysregulation and multiple organ dysfunction present formidable clinical challenges that conventional single-target therapies fail to address. This review evaluates the potential of the natural quinolizidine alkaloid sophoridine for drug …
  europepmc 2026 置信度 0.80
• MediHive: A Decentralized Agent Collective for Medical Reasoning.
  Large language models (LLMs) have revolutionized medical reasoning tasks, yet single-agent systems often falter on complex, interdisciplinary problems requiring robust handling of uncertainty and conflicting evidence. Multi-agent systems (MAS) leveraging LLMs …
  pubmed Wang X, Yang CC 2026 置信度 0.82
• From Simulation to Semi-Physical Validation: An Intelligent Jammer-Assisted Radar Anti-Jamming Evolution Method.
  Adaptive waveform decision-making remains a key challenge in radar anti-jamming, especially when radar systems need to evolve their strategies through dynamic confrontation with intelligent jammers. This paper presents an intelligent jammer-assisted radar anti…
  europepmc 2026 置信度 0.80
• Energy-efficient wireless network control via spatio-temporal deep learning and multi-agent reinforcement learning.
  The rapid expansion of wireless data traffic is placing increasing strain on the energy consumption of current communication networks, intensifying the tension between performance and sustainability objectives. In interference-intensive multiple access scenari…
  europepmc 2026 置信度 0.80
• Research Progress on Pathogenesis of Diabetic Nephropathy and Intervention with Traditional Chinese Medicine.
  Diabetic kidney disease (DKD) is the most prevalent microvascular complication of diabetes mellitus and the leading cause of chronic kidney disease and end-stage renal disease, with its global incidence rising continuously and imposing a substantial disease bu…
  europepmc 2026 置信度 0.80
• Collective reflection-based multi-agent reinforcement learning framework for task-oriented dialogue policy learning.
  Multi-agent reinforcement learning cooperatively models dialogue policies, aiming to select dialogue actions for accurate task completion. Existing multi-agent dialogue policy learning methods tackle collaborative relationships through credit assignment to max…
  europepmc 2026 置信度 0.80
• A closed-loop multi-agent swarm framework for synergistic location-routing optimization in municipal solid waste collection system.
  To address the challenges faced by collection and transportation systems under waste classification, such as the increasing variety of vehicle types, the growing complexity of transportation modes, and fluctuations in waste generation, this study proposes a co…
  pubmed Liu Y, Lin Z, Dou W, Hao Y 2026 置信度 0.82
• A chromatographic process design and optimization multi-agent platform powered by large language models: A case application on extract of Ginkgo biloba leaf.
  Chromatographic separation technology has been widely applied in pharmaceutical, chemical, and food industries due to its high efficiency. However, traditional human-dependent chromatographic process development faces challenges such as reliance on expert expe…
  pubmed Tang Z, Wu S, Zhao X, Wang Y 等 2026 置信度 0.82
• Multi-UAV Cooperative Hunting in Obstructed Environments via a Multi-Agent Proximal Policy Optimization with Curriculum Learning.
  With the increasing complexity of unmanned aerial vehicle (UAV) missions in complex obstacle environments, cooperative hunting of maneuvering ground targets by UAV swarms has become an important problem for multi-agent autonomous decision-making. This paper fo…
  europepmc 2026 置信度 0.80
• Deciphering the Formulation-Dependent Neurotoxicity of Irinotecan: An Integrated Pharmacovigilance and Mechanistic Study.
  Irinotecan is a key chemotherapeutic agent, but its neurotoxicity limits its utility. Observed differences in neurotoxicity between conventional and liposomal formulations are poorly characterized mechanistically. This study aimed to systematically compare the…
  europepmc 2026 置信度 0.80
• Adaptive critic designs for event-based multi-agent systems with asymmetric constraints.
  In this paper, based on the adaptive critic control method, an improved event-based distributed control mechanism is established for continuous-time nonlinear multi-agent systems. Notably, to address the consensus control problem when the structure of the lead…
  pubmed Yan W, Wang D, Ma X, Qiao J 2026 置信度 0.82
• Naringenin as a multi-target neuroprotective agent in neurodegenerative diseases.
  Neurodegenerative diseases (ND) such as Alzheimer's disease (AD), Parkinson's disease (PD), Huntington's disease (HD), Amyotrophic lateral sclerosis (ALS), and Multiple sclerosis (MS) are characterized by progressive neuronal loss driven by complex and multifa…
  europepmc 2026 置信度 0.80
• Observer-based prescribed-time lag bipartite consensus of nonlinear multi-agent systems under event-triggered mechanism.
  Considering the complexity of lag time and the convergence time, as well as the influence of the observer and the event-triggered mechanism, the prescribed-time lag bipartite consensus (PTLBC) control problem for nonlinear multi-agent systems (MASs) is researc…
  pubmed Tian J, Li T, Zhao X, Wang Y 等 2026 置信度 0.82
• Performance comparison of a neuro-symbolic large language model system versus conventional AI models and human experts in cholangitis management.
  Background Large language models (LLMs) have shown promising results in medical decision support; Background: Large language models (LLMs) have demonstrated promising outcomes in medical decision support; however, their efficacy in managing complex hepatobilia…
  europepmc 2026 置信度 0.80
• IAN, an intelligent system for omics data analysis and discovery.
  IAN is an R package addressing the challenge of integrating, analyzing, and interpreting gene expression data using an artificial intelligence (AI) system. It leverages popular pathway (KEGG, WikiPathways, Reactome, and GO) and regulatory datasets (ChEA), alon…
  europepmc 2026 置信度 0.80
• Interoperable Web Platform Based on Large Language Models for Medical Data Analysis: A Protocol for Clinical Decision Support.
  Clinical decision-making is frequently hindered by fragmented electronic health records and limited interoperability among heterogeneous healthcare information systems. This article presents a step-by-step protocol for implementing an interoperable web platfor…
  europepmc 2026 置信度 0.80
• From Sensor-Empowered Ubiquitous Computing to Embodied Intelligence: Architectures, Paradigm Evolution, and Emerging Challenges.
  With the rapid development of artificial intelligence technology, the transportation, industry, and healthcare fields are undergoing an intelligent evolution. These advancements have raised higher requirements for technologies such as mobile robots, wearable i…
  pubmed Jia A, Cai Z, Liu X, Zheng K 等 2026 置信度 0.82
• MACES: Multi-Agent Conviction Dynamics with Cross-LLM Ensemble Scoring for Market Narrative Intelligence System
  Current market narrative monitoring systems rely heavily on sentiment analysis, which essentially converts multi-dimensional narrative into single scalar polarity values. This research demonstrates that this simplification is insufficient. A scenario where 40%…
  crossref Yujuan Qiu 2026-07-20T13:44:54Z 置信度 0.70
• Reinforcement Learning for Autonomous System Control in Multi-Agent Settings
  crossref Samiksha Sharma 2026-07-28T19:11:47Z 置信度 0.70
• AVATAR-AGENT: A Multi-Agent System for Expressive 3D Avatar Generation
  While recent advances in generative AI have enabled text-to-3D avatar synthesis, platforms built on creator-made content ecosystems require approaches that guarantee asset compatibility, maintain established visual styles, and preserve creator contributions. D…
  crossref Jason Ding, Rohan Gangaraju, Krishna C. Garikipati, Foad Dabiri 等 2026-05-21T11:40:19Z 置信度 0.70
• Confidence-Based curricula for multi-agent path finding via reinforcement learning
  Abstract A wide range of real-world applications can be formulated as Multi-Agent Path Finding (MAPF) problem, where the goal is to find collision-free paths for multiple agents with individual start and goal locations. State-of-the-art MAPF solvers are mainly…
  crossref Thomy Phan, Joseph Driscoll, Justin Romberg, Sven Koenig 2026-04-30T10:33:37Z 置信度 0.70
• A Network-Aware Multi-Agent System for Intelligent ADR Detection Using Pagerank-Based Agent Ranking
  crossref Ayman M Mansour 2026-08-13T19:19:09Z 置信度 0.70
• Multi-Agent System in the AIOps Paradigm: A Layered Architecture for System Telemetry Analysis
  crossref Daniil I. Pushkarev 2026-07-30T19:05:13Z 置信度 0.70
• Human Injury Severity Identification Question-Answering Method Based on Multi-Agent System
  Human injury severity often raises controversies that rely on the interpretation of expert witness with special knowledge, which has been relieved by question-answering systems based on LLMs. However, AI hallucination and inflexible settings are still obstacle…
  crossref Zhuo Xing 2026-05-11T19:44:21Z 置信度 0.70
• Demonstration of a Distributed Cooperative Strategy Planning Algorithm in a Multi-Agent System with Multiple Objectives
  Robot-based services are increasingly being integrated into everyday life. In the diverse environments in which humans live, systems are expected to respond to dynamically changing surroundings by enabling distributed control and cooperation. However, in space…
  crossref Yuta Takemoto 2026-02-27T20:47:13Z 置信度 0.70
• <span>CRI: A Multi-Factor Reputation System for Autonomous Agent Commerce</span>
  We present the Composite Reliability Index (CRI) a multi-factor reputation system built for autonomous agent-to-agent commerce. The problem it addresses has no direct precedent: how do software agents that transact economic value without human oversight establ…
  crossref René Dechamps Otamendi 2026-07-29T13:23:19Z 置信度 0.70
• Distributed dynamic multi-task assignment for multi-agent systems
  In this study, we propose a complex distributed task allocation algorithm for “multiple agents versus multiple objects” for object transportation missions. This is achieved by combining a method for determining a set of objects that one agent can transport at …
  crossref Soya Takamizawa, Shunsuke Tsuge, Toru Namerikawa 2026-05-05T04:47:13Z 置信度 0.70
• On the complexity of the two-stage majoritarian rule
  Abstract Sequential voting rules have played a crucial role in shaping decisions within parliamentary and legislative frameworks. After observing that the existing sequential rules fail several fundamental axioms, (Horan and Sprumont, Theoretical Economics, 17…
  crossref Yongjie Yang 2026-03-27T07:05:39Z 置信度 0.70
• Testing BDI-based multi-agent systems using discrete event simulation
  Multi-agent systems are designed to deal with open, distributed systems with unpredictable dynamics, which makes them inherently hard to test. The value of using simulation for this purpose is recognized in the literature, although achieving sufficient fidelit…
  crossref Martina Baiardi, Samuele Burattini, Giovanni Ciatto, Danilo Pianini 2026-04-02T06:35:38Z 置信度 0.70
• A Safe and Fair Multi-Agent Decision Support System for ETF-Based Retirement Planning under Long-Horizon Constraints
  Individual retirement planning is a long-horizon decision problem in which households, service platforms, and public authorities act on different information sets and at different frequencies. Existing digital tools typically optimize a single portfolio or app…
  crossref Chi Cheng 2026-08-21T14:48:01Z 置信度 0.70
• Scalable Physics-Informed Multi-Agent Reinforcement Learning for Building Energy System Control
  Optimizing multi-zone building HVAC systems for energy efficiency while maintaining thermal comfort is a critical challenge, as buildings account for 40% of total energy consumption in the United States. Although multi-agent reinforcement learning (MARL) has e…
  crossref Xuezheng Wang, Zhaolin Ren, Na Li, Bing Dong 2026-03-18T03:36:41Z 置信度 0.70
• Generosity and forgiveness: The importance of nuanced reputation
  Abstract Indirect reciprocity, supported by simple reputation assessment and social norms, has been demonstrated as an effective mechanism for enabling cooperation in populations of self-interested individuals. However, it has been shown that where there is no…
  crossref Nathan Griffiths, Nir Oren 2026-06-25T06:01:09Z 置信度 0.70
• Green disclosure policies and market dynamics: evidence from agent-based ESG models
  Abstract Green disclosure policies aim to improve the transparency of corporate environmental practices and guide investors’ capital allocation. While existing studies mostly examine firm-level effects, their market-level implications in multi-agent systems re…
  crossref Lingxiao Zhao, Maria Polukarov, Carmine Ventre 2026-02-07T09:02:50Z 置信度 0.70
• MASTEST: A LLM-Based Multi-Agent System For Testing RESTful APIs
  crossref Xiaoke Han, Hong Zhu 2026-08-26T19:09:55Z 置信度 0.70
• Facilitating heterogeneous sensor information cooperation in multi-agent perception system
  crossref Binyu Zhao, Wei Zhang, Zhaonian Zou 2026-04-21T15:57:39Z 置信度 0.70
• Conceptual Model of a Multi-agent System to Support the Activities of a Tender Specialist
  The paper considers the task of constructing a conceptual model of a digital twin of a tender specialist based on an intelligent multi-agent system focused on the search and evaluation of the relevance of procurement by the supplier. The relevance of the study…
  crossref Anatoly Sidorov 2026-06-24T15:13:03Z 置信度 0.70
• Consensus from Ambiguity: Language Emergence in Guessing Games
  crossref Ajin George Joseph, Vikas Kumar 2026-08-24T09:06:37Z 置信度 0.70
• PhishLumos: An Adaptive Multi-Agent System for Proactive Phishing Campaign Mitigation
  crossref Daiki Chiba, Hiroki Nakano, Takashi Koide 2026-07-14T19:38:09Z 置信度 0.70
• AlloyGraph: A Knowledge-Graph-Grounded Multi-Agent System for Nickel-Based Superalloy Design
  Supporting design decisions in specialized scientific domains requires reasoning over sparse, fragmented data under strict physical constraints, conditions under which purely data-driven models and ungrounded language models are each insufficient. We introduce…
  crossref Alexandru Lecu, Lezan Hawizy, Soran Birosca, Adrian Groza 2026-06-29T19:09:06Z 置信度 0.70
• Autonomous Multi-Agent System for Cloud Architecture Design and Infrastructure Deployment
  Cloud infrastructure design and deployment traditionally require significant expertise in cloud services, networking, security, and Infrastructure-as-Code (IaC). Translating high-level business requirements into production-ready infrastructure can take days of…
  crossref 2026-03-22T06:03:48Z 置信度 0.70
• PRIMES: A PRIORITY-BASED MULTI-AGENT TASK SCHEDULING SYSTEM
  crossref 2026-03-21T07:47:53Z 置信度 0.70
• Geometric freeze-tag problem
  crossref Sharareh Alipour, Arash Ahadi, Kajal Baghestani, Soroush Sahraei 等 2026-02-28T07:32:38Z 置信度 0.70
• Parameterized complexity of incomplete connected fair division
  Abstract Fair division of resources among competing agents is a fundamental problem in computational social choice and game theory. It has been intensively studied for various types of items ( divisible and indivisible ) and under various notions of fairness .…
  crossref Harmender Gahlawat, Meirav Zehavi 2026-06-22T02:49:10Z 置信度 0.70
• Multi-Agent Path Planning for a Multi-Deep Four-Way Shuttle-Based System
  Background: Four-way shuttle-based storage and retrieval systems (FSS/RSs) have recently emerged as flexible and scalable solutions for high-density warehousing, enabling shuttle movement in four directions and supporting multi-deep dual-access storage configu…
  crossref Giacomo Lupi, Andrea L’Afflitto, Riccardo Manzini, Gabriele Sirri 2026-07-09T14:17:51Z 置信度 0.70
• Improving scalability of multi-agent deep reinforcement learning with suboptimal human knowledge
  Abstract Due to its exceptional learning ability, multi-agent deep reinforcement learning (MADRL) has garnered widespread research interest. However, since the learning is data-driven and involves sampling from millions of steps, training a large number of age…
  crossref Dingbang Liu, Fenghui Ren, Jun Yan, Guoxin Su 等 2026-01-10T07:36:25Z 置信度 0.70
• A Multi-Agent LLM System for Natural Language Querying of Operational Knowledge Graphs in Satellite Ground Stations
  Satellite ground-station maintenance generates vast operational data, yet traditional query interfaces limit discoverability and slow time-critical decision making.We present a multi-agent system deployed at Fucino Space Centre that combines Large Language Mod…
  crossref Fosco Eugenio Quadri, Filippo Bianchini 2026-04-16T19:42:43Z 置信度 0.70
• A Multi-Agent Orchestrated RAG System for Intelligent Information Retrieval
  crossref Vishal Gupta, Ashutosh Dixit, Shilpa Sethi 2026-06-18T20:07:15Z 置信度 0.70
• AUTOMATING PORTFOLIO MANAGEMENT USING MULTI-AGENT SYSTEM WITH DYNAMIC PROMPT OPTIMISATION AND FEEDBACK LOOPS
  Traditional portfolio management systems often rely on static rules or fixed prompts, which limits their ability to adapt to changing market conditions. This paper proposes a closed-loop multi-agent decision framework that introduces prompt-level learning as a…
  crossref Kandarp Mukeshkumar Sharda, Aliyu Sani Sambo 2026-08-01T06:42:55Z 置信度 0.70
• DenseNet Vision System for Crop Protection Assessment
  Crop protection plays a vital role in ensuring agricultural sustainability and stable food production by safeguarding crops from biotic stresses that adversely affect plant health and yield. Among these stresses, pest infestations cause substantial economic lo…
  crossref M. Jeevamukesh, C. Balasubramanian, P. Raghavan 2026-04-13T19:35:25Z 置信度 0.70
• Strategyproof facility location with prediction: minimizing the maximum cost
  crossref Hau Chan, Jianan Lin, Chenhao Wang 2026-04-27T04:27:08Z 置信度 0.70
• Computing exact optimal covers for cover function games with approximate ordinal input
  Abstract For cover function games (CoFGs), we address the problem of organising agents into possibly overlapping coalitions so as to maximise social welfare. We introduce a subclass of CoFGs called probabilistically monotone CoFGs. Monotonicity means that the …
  crossref Syeda Shaheen Fatima 2026-07-22T01:02:13Z 置信度 0.70
• $$\textsf {EFX}$$ allocations and orientations on bipartite multi-graphs: a complete picture
  Abstract We consider the fundamental problem of fairly allocating a set of indivisible items among agents having valuations that are represented by a multi-graph – here, agents appear as vertices and items as edges between them and each vertex (agent) only val…
  crossref Mahyar Afshinmehr, Alireza Danaei, Mehrafarin Kazemi, Kurt Mehlhorn 等 2026-06-02T08:15:47Z 置信度 0.70
• MacroAllocAgent: From macro narratives to strategic asset allocation via a multi-agent LLM system
  We propose MacroAllocAgent, a multi-agent Large Language Model (LLM) system designed to translate macro-financial narratives into strategic asset allocation weights for long-horizon investors. The system processes Chinese official macroeconomic communications …
  crossref Jinyuan Wang, Ningyuan Deng, Qi Li, Yi Yang 2026-08-15T04:37:55Z 置信度 0.70
• Exergy-Credit Multi-Agent Optimization of a Bus-Coupled Kalina–PEM Geothermal–Hydrogen System with Bidirectional Operation
  Despite increasing interest in geothermal-driven hydrogen production, existing geothermal hybrid studies often lack (i) a bus-level architecture that enables flexible allocation of geothermal electricity among local/grid loads, power-to-hydrogen conversion, an…
  crossref Aslı Tiktas, ibrahim baki şahin 2026-06-17T23:39:17Z 置信度 0.70
• A Multi-Agent System Digital Twin Framework for Pre-Hospital and Emergency Department Triage
  MethodsSix autonomous agents — Dispatch, Pre-Hospital Triage, ED Triage (ERTRIAGE machine learning CDS), Monitoring, Resource Allocation, and Discharge/Admit — were formally specified with HL7 FHIR R4 interoperability, coordinated via a three-tier hierarchy an…
  crossref CHARALAMPIA PYLARINOU, Konstantinos Neofotistos, Andreas Plemmenos, Lefteris Gortzis 2026-04-17T04:16:47Z 置信度 0.70
• DoctorAgent-RL: A Multi-Agent Collaborative Reinforcement Learning System for Multi-Turn Clinical Dialogue
  Large language models (LLMs) excel at biomedical question answering but struggle in real clinical consultations. Single-round systems require patients to list all symptoms initially, often causing vague diagnoses. Traditional multi-turn models, limited by stat…
  crossref Yichun Feng, Jiawei Wang, Lu Zhou, Zhen Lei 等 2026-04-21T21:25:57Z 置信度 0.70
• A multi-objective goal-oriented reinforcement learning algorithm for dynamic multi-objective sequential decision making
  crossref Haofang Yu, Hong-chuan Yang, Yanyan Huang 2026-02-07T08:54:44Z 置信度 0.70
• MAVAudit-Graph: A Multi-Agent System for Autonomous UAV Security Testing
  Ensuring the cyber-physical resilience of Unmanned Aerial Vehicles (UAVs) is critical, yet current security testing is hampered by manual overhead or stateless fuzzing that lacks semantic awareness of flight regimes. We propose MAVAuditGraph, an autonomous mul…
  crossref Yi Li, Tao Zhang 2026-05-15T02:40:33Z 置信度 0.70
• Multi-Service Routing Optimization in SDN Based on Multi-Agent Deep Reinforcement Learning
  Emerging applications impose increasingly stringent Quality of Service (QoS) requirements on modern networks. Benefiting from the control-data decoupling and inherent programmability of Software-Defined Networking (SDN), fine-grained traffic engineering can be…
  crossref Lipeng Xing, Chengjin Wang, Youwei Shi, Kouquan Zheng 2026-05-11T19:44:21Z 置信度 0.70
• $$\varepsilon $$-retraining reinforcement learning algorithms
  Abstract We present $$\varepsilon $$ , a general exploration strategy for reinforcement learning (RL) that encourages adherence to behavioral preferences while preserving the convergence guarantees of the underlying RL algorithm. $$\varepsilon $$ maintains a d…
  crossref Luca Marzari, Changliu Liu, Priya L. Donti, Enrico Marchesini 2026-05-04T15:05:52Z 置信度 0.70
• Chimera: Harnessing Multi-Agent LLMs for Automatic Insider Threat Simulation
  Insider threats represent a significant and persistent security risk, yet remain difficult to detect in complex enterprise environments, where malicious activities are often concealed within subtle user behaviors.While machine-learning-based insider threat det…
  crossref Jiongchi Yu, Xiaofei Xie, Qiang Hu, Yuhan Ma 等 2026-05-13T16:20:44Z 置信度 0.70
• Multi-Agent LLM Copilots for System of Systems Management
  crossref Theodor Pintilie, Anzhelika Borbak, George Suciu 2026-07-13T20:01:43Z 置信度 0.70
• Collaborative multi-agent Q-learning-empowered vocational education resource matching system
  Inderscience is a global company, a dynamic leading independent journal publisher disseminates the latest research across the broad fields of science, engineering and technology; management, public and business administration; environment, ecological economics…
  crossref Zhaowei Zhang 2026-02-24T14:00:32Z 置信度 0.70
• A Hotelling-Downs game for strategic candidacy with binary issues
  crossref Javier Maass Martínez, Vincent Mousseau, Anaëlle Wilczynski 2026-03-04T09:05:04Z 置信度 0.70
• Resource Trap v2.0: Rationality as the Only Path to Abundance (Full Document with AGI-Readable Formal Layer — RL, Multi-Agent, Game Theory, Mechanism Design)
  This working paper is the complete dual-layer version of Resource Trap v1.3 (DOI: 10.5281/zenodo.19085282), adding a full machine-readable formal specification (Layer B, Appendices B–F) designed for direct integration into AGI optimization systems. OPTIMIZATIO…
  datacite Mishko, Nikolai 2026 置信度 0.66
• Thurmondian Physics: A Theory on the Unified Geometric Substrate of Reality
  # Thurmondian Physics: A Theory on the Unified Geometric Substrate of Reality **An Updated Theory of Aether for the 21st Century, formalized as a Sub-Planck Monohorizon Principle, a tensioned, gapless, complex-scalar substrate Φ that exists before metric, befo…
  datacite Thurmond, Justin 2025 置信度 0.66
• The Birth of the Mother White Hole and the Final Merger of Black Holes Along a Spiral Vortex Cone Pathway. The Big Bang is, in fact, an Informational Big Boot, resulting from the endless cycles of black-hole mergers and the birth of the Mother White Hole.
  This equation establishes the absolute sovereignty of ordered will across the entire conical fabric of the cosmos: $$\mathcal{L}_{Vortex}^{(1155)} = \oint_{\mathcal{V}_{cone}} \left[ \mathcal{G}_{\Omega} \left( \Phi_{Spiral}^{\mu\nu} \cdot \frac{\partial \math…
  datacite HAMZAH, SEYED RASOUL 2026 置信度 0.66
• The Birth of the Mother White Hole and the Final Merger of Black Holes Along a Spiral Vortex Cone Pathway. The Big Bang is, in fact, an Informational Big Boot, resulting from the endless cycles of black-hole mergers and the birth of the Mother White Hole.
  This equation establishes the absolute sovereignty of ordered will across the entire conical fabric of the cosmos: $$\mathcal{L}_{Vortex}^{(1155)} = \oint_{\mathcal{V}_{cone}} \left[ \mathcal{G}_{\Omega} \left( \Phi_{Spiral}^{\mu\nu} \cdot \frac{\partial \math…
  datacite HAMZAH, SEYED RASOUL 2026 置信度 0.66
• ACT-Ω v25.0: The Semantic Braid and E8 Manifold Protocols — Technical Release Audit and Isomorphic Mapping Registry.
  ACT-Ω v25.0: The Semantic Braid and E8 Manifold Protocols — Technical Release Audit and Isomorphic Mapping Registry Metadata & Registry Information Document ID: ACT-OMEGA-TR-2024-V25.0 Version: 25.0 (Audit Locked) DOI: 10.10539/aegis-cascade.v25.0.audit Re…
  datacite Donevin Frownfelter 2026 置信度 0.66 Physical Sciences and MathematicsComputer SciencesSoftware EngineeringEngineering15.965hz
• ACT-Ω v25.0: The Semantic Braid and E8 Manifold Protocols — Technical Release Audit and Isomorphic Mapping Registry
  ACT-Ω v25.0: The Semantic Braid and E8 Manifold Protocols — Technical Release Audit and Isomorphic Mapping Registry Metadata & Registry Information Document ID: ACT-OMEGA-TR-2024-V25.0 Version: 25.0 (Audit Locked) DOI: 10.10539/aegis-cascade.v25.0.audit Regist…
  datacite Donevin Frownfelter 2026 置信度 0.66
• ACT-Ω v25.0: The Semantic Braid and E8 Manifold Protocols — Technical Release Audit and Isomorphic Mapping Registry
  ACT-Ω v25.0: The Semantic Braid and E8 Manifold Protocols — Technical Release Audit and Isomorphic Mapping Registry Metadata & Registry Information Document ID: ACT-OMEGA-TR-2024-V25.0 Version: 25.0 (Audit Locked) DOI: 10.10539/aegis-cascade.v25.0.audit Regist…
  datacite Donevin Frownfelter 2026 置信度 0.66
• EUDR 2026 e a prova da legalidade brasileira: da conformidade documental à evidência verificável na cadeia do café - EUDR 2026 and Evidence of Compliance with Brazilian Law: From Documentary Compliance to Verifiable Evidence in the Coffee Supply Chain
  EUDR 2026 and the Proof of Brazilian Legality From Documentary Compliance to Verifiable Evidence in the Coffee Supply Chain Regulatory Evidence, Traceability and Supplier Due Diligence under Regulation (EU) 2023/1115 Felipe Barbosa BittencourtLawyer and Indepe…
  datacite Bittencourt 2026 置信度 0.66
• EUDR 2026 e a prova da legalidade brasileira: da conformidade documental à evidência verificável na cadeia do café - EUDR 2026 and Evidence of Compliance with Brazilian Law: From Documentary Compliance to Verifiable Evidence in the Coffee Supply Chain
  EUDR 2026 and the Proof of Brazilian Legality From Documentary Compliance to Verifiable Evidence in the Coffee Supply Chain Regulatory Evidence, Traceability and Supplier Due Diligence under Regulation (EU) 2023/1115 Felipe Barbosa BittencourtLawyer and Indepe…
  datacite Bittencourt 2026 置信度 0.66
• ASP — Anticipating Shadow Points
  A Claude Code skill orchestrating a 13-phase pre-mortem-first planning protocol for non-trivial engineering tasks (migrations, deploys, refactors, RLS changes, architecture decisions). Integrates the prospective-hindsight finding of Mitchell, Russo & Penningto…
  datacite Flores, Carlos Ulisses 2026 置信度 0.66 claude-codeagentic-workflowpre-mortemshadow-pointsMAST
• ASP — Anticipating Shadow Points
  A Claude Code skill orchestrating a 13-phase pre-mortem-first planning protocol for non-trivial engineering tasks (migrations, deploys, refactors, RLS changes, architecture decisions). Integrates the prospective-hindsight finding of Mitchell, Russo & Penningto…
  datacite Flores, Carlos Ulisses 2026 置信度 0.66 claude-codeagentic-workflowpre-mortemshadow-pointsMAST