AI Agent 生态 · 全部实体（第 78 / 100 页）

本页收录第 7701–7800 条，共 10000 条 · 返回 AI Agent 生态 首页

• IntelForge: Multi-Agent LLM Framework for Cyber Threat Intelligence Enrichment
  crossref Noam Tarshish, Daniel Hodisan, Asaf Shabtai 2026-03-09T19:56:13Z 置信度 0.70
• Multi-Agent LLM Framework for Formulaic Alpha Generation and Selection in Quantitative Trading
  crossref Qizhao Chen, Hiroaki Kawashima 2026-03-06T20:57:57Z 置信度 0.70
• Plan-Execute-Generate-Judge: A Self Verifying Multi Agent LLM Framework for Complex NoSQL Querying
  crossref Alex Kaplunovich 2026-03-06T20:57:57Z 置信度 0.70
• VTR-LLM: Multi-Agent LLM Framework for Automated Debugging of FPGA CAD Flows
  Modern FPGA computer-aided design (CAD) flows have grown increasingly complex, integrating numerous stages, configuration parameters, timing constraints, and physical implementation specifications. As designs scale, failures often arise from subtle interaction…
  crossref Mohamed A. Elgammal, Jamie Wu, Lynne Liu, Taehoon Kim 等 2026-07-13T13:38:41Z 置信度 0.70
• An LLM-Based Multi-Agent Framework for Evolutionary Blackbox Optimization
  Optimizing blackbox functions requires a structured approach to ensure an effective and efficient search for the optimal solution, supported by a deep understanding of the problem domain, algorithmic behavior and programming abilities. Large Language Models (L…
  crossref Jill Baumann, Oliver Kramer 2025-08-11T15:18:11Z 置信度 0.70
• Fostering collective intelligence in CPSS: an LLM-driven multi-agent cooperative tuning framework
  Cyber-Physical-Social Systems (CPSS) have emerged as a transformative paradigm in recent years, embracing computational processes, physical systems, and human social interactions within an integrated architectural framework. Advances in artificial intelligence…
  crossref Rongjun Chen, Chengbo He 2025-06-30T04:10:48Z 置信度 0.70
• Intelligent Test Automation: A Multi-Agent LLM Framework for Dynamic Test Case Generation and Validation
  Automated software testing is essential in modern software development, ensuring stability and resilience. This study describes a unique technique for using the capabilities of Large Language Models (LLMs) via a system of autonomous agents. These agents collab…
  crossref Pragati Kumari - 2025-03-06T18:01:53Z 置信度 0.70
• An LLM-Driven Multi-Agent Simulation Framework for Coupled Epidemic–Economic Dynamics
  Traditional Agent-based Models (ABMs) often struggle to capture the nuance of adaptive human decision-making during complex crises due to their reliance on static, predefined rules. Large Language Models (LLMs) offer a transformative solution by acting as cogn…
  crossref Shanrui Wang, Huiyong Liu, Shiyi Zhang, Qunsheng Yang 2026-03-05T10:31:14Z 置信度 0.70
• Introduction to The MACI Framework: A System 2 Architecture for Artificial General Intelligence
  crossref 2025-12-12T16:55:26Z 置信度 0.70
• Advancing Automated Bim Information Retrieval with Synergistic Bim Aligners: An Llm Agent-Driven Framework for Enhanced Query Alignment
  crossref Peizhuo Guo, Huiyuan Xue, Jun Ma, Jack C.P. Cheng 2024-12-21T21:37:22Z 置信度 0.70
• EduCore: A Privacy-Aware LLM-Driven Education Framework with Intelligent Multi-Agent Support
  crossref Debashis Das, Tenicka Norwood, Pushpita Chatterjee, Uttam Ghosh 2026-04-20T20:01:37Z 置信度 0.70
• MASON - A Multi-Agent LLM Framework for No-Code Development
  The rise of No-Code Development (NCD) has enabled citizen developers to build applications without traditional programming expertise. However, as these platforms scale to handle complex, interdependent tasks, their limitations become apparent. Large Language M…
  crossref Muhammed Roshan Palayamkot, Kayvan Karim 2025-08-01T07:50:39Z 置信度 0.70
• Agentic AI Modernization: Transforming Institutional Infrastructure Through Orchestrated Multi-Agent LLM Framework
  While managing constrained funds and strict regulatory requirements, the higher education institutions are under unprecedented pressure to modernize outdated information systems, such as mainframe-based Student Information Systems (SIS), custom registration pl…
  crossref Mahesh Kumar Damarched 2026-02-10T18:11:59Z 置信度 0.70
• Econometric Foundations for Multi-Agent Negotiation Systems: A Theoretical Framework for LLM-Driven Strategic Advisor Evaluation
  Purpose: This study develops a comprehensive econometric framework for evaluating LLM-based multi-agent negotiation systems. The framework targets the StrategicAdvisorAgent—an LLM-powered component implementing six specialised methods: context analysis, strate…
  crossref Ehsan Hatamian 2026-03-31T21:03:36Z 置信度 0.70
• COLLAB-LLM: A Communication-Centric Role-Based Framework for Scalable Multi-Agent LLM Collaboration
  Large Language Models (LLMs) are increasingly deployed in multi-agent systems; however, existing frameworks continue to suffer from communication ambiguity, coordination failures, and poor scalability as task complexity increases. This paper introduces COLLAB-…
  crossref Elham Albaroudi, Mohammad Hatamleh, Sirin Mohammed Hejazi, Ahmad Yasser Alshalabi 等 2026-01-12T12:43:32Z 置信度 0.70
• A Validation and Governance Framework for Multi-Agent LLM Scientific Software Development
  Large language models are non-deterministic systems whose outputs vary across runs, model versions, and context configurations. Existing benchmarks for LLM code generation evaluate correctness against synthetic test suites or competitive programming problems, …
  crossref Tim Bass 2026-06-15T10:34:51Z 置信度 0.70
• RoMa: A Credibility-Aware Fault-Tolerance Framework for LLM Multi-Agent Systems
  crossref Kunyu Li, FengHe Wu 2026-07-06T19:42:40Z 置信度 0.70
• Multi-Agent LLM Framework for Stock Recommendation via Financial Feature Summarization
  Escalating data complexity and volume in financial markets make stock investment choices very difficult for investors at every experience level. Multiple associated factors, such as economic signals, global events, corporate information, and psychological shif…
  crossref Siddhika Joshi, Anupkumar Bongale, Deepak Dharrao 2025-11-04T18:33:55Z 置信度 0.70
• Interactional Fairness in LLM Multi-Agent Systems: An Evaluation Framework
  As large language models (LLMs) are increasingly used in multi-agent systems, questions of fairness should extend beyond resource distribution and procedural design to include the fairness of how agents communicate. Drawing from organizational psychology, we i…
  crossref Ruta Binkyte 2025-10-15T13:19:42Z 置信度 0.70
• Multi-Agent RAG Framework for Entity Resolution: Advancing Beyond Single-LLM Approaches with Specialized Agent Coordination
  Entity resolution in real-world datasets remains a persistent challenge, particularly for identifying households and detecting co-residence patterns within noisy and incomplete data. While Large Language Models (LLMs) show promise, monolithic approaches often …
  crossref Aatif Muhammad Althaf, Muzakkiruddin Ahmed Mohammed, Mariofanna Milanova, John Talburt 等 2025-12-04T16:07:38Z 置信度 0.70
• A Practical MCP×A2A Integration Framework for Interoperability in LLM-Based Autonomous Multi-Agent Systems
  최근 대규모 언어 모델(LLM)의 발전은 다양한 분야에서 복잡한 작업을 수행할 수 있는 자율 에이전트의 개발을 가속화하고 있다. 그러나 실제 환경에서 LLM 기반 멀티에이전트 시스템(MAS)의 적용은 여전히 제한적이며, 그 주요 원인으로는 이기종 에이전트 간의 동적 상호운용성 부족과 외부 도구 및 서비스와의 구조화된 연동의 어려움이 있다. 본 논문은 이러한 문제를 해결하기 위해 Google의 Agent-to-Agent(A2A) 프로토콜과 Anthropic의 Mo…
  crossref Cheonsu Jeong 2025-10-21T01:08:17Z 置信度 0.70
• Trustable AI Framework for Intelligent Meter Monitoring: A Multi-Agent, LLM-Driven Approach
  Intelligent meter monitoring in modern utility systems demands robust, scalable, trustable AI solutions. This paper introduces a hybrid AI framework designed for enhanced accuracy, interpretability, and operational trust in meter anomaly detection. The system …
  crossref Tiantian Guo, Leong Jun Hoe 2026-02-25T20:55:10Z 置信度 0.70
• Multi-Agent LLM Framework for Autonomous Network Fault Remediation
  The growing complexity of today’s enterprise networks is challenging traditional approaches to fault management. The proposed solution utilizes a multi-agent large language model (LLM) framework that autonomously detects, diagnoses, and resolves network faults…
  crossref Baddipadiga Praneeth Reddy 2026-04-07T13:05:55Z 置信度 0.70
• A Multi-Agent LLM-Driven Intelligent EV Charging Framework with Rag based Personalization and CGAN-Generated Behavioral Modeling
  The rapid growth of electric vehicles (EVs) has a demand on charging station management it's necessary of handling user diversity, dynamic grid constraints and real time pricing variations. This paper proposes a multi-agent EV charging framework comprising a U…
  crossref Santharam M, B. Ashok Kumar, S. Senthilrani, J. Rajeswari 2026-04-13T19:35:25Z 置信度 0.70
• Agent-as-a-Graph: Knowledge Graph-Based Tool and Agent Retrieval for LLM Multi-Agent Systems
  crossref Faheem Nizar, Elias Lumer, Anmol Gulati, Pradeep Basavaraju 等 2026-03-14T10:34:06Z 置信度 0.70
• SocraSynth: Adversarial Multi-LLM Reasoning
  crossref 2025-12-12T16:55:26Z 置信度 0.70
• A heterogeneous multi-agent reinforcement learning framework with LLM-guided preference-score rewards for data center cooling optimization
  Data center cooling is a major source of non-IT energy consumption, and optimal cooling control must reduce power consumption while maintaining safe rack inlet air temperatures. To address insufficient state representation, credit-assignment difficulty, and li…
  crossref Wei Quan, Long Deng, Na Zhang, Zengxi Feng 等 2026-07-13T15:38:10Z 置信度 0.70
• Orchestrate-on-Graph: A Multi-Agent Hybrid Retrieval and Reasoning Framework for Reliable LLM Reasoning
  crossref Bohan Cao, Gewei Lu, Liping Shen 2026-03-06T20:57:57Z 置信度 0.70
• MACV: A Specialized Multi-Agent and Consensus Framework for Reliable LLM Outputs
  Large language models (LLMs) write smoothly but still sometimes make believable yet incorrect or unsupported claims so called hallucinations. To address this, we propose MACV (Multi-Agent Cross-Verification), a modular system that has several cooperating compo…
  crossref Rakesh More, Sudarshan Varma, Nilay Varma 2026-03-04T20:48:26Z 置信度 0.70
• An LLM-Based Agent Framework for Intelligent Power Module Design
  This paper proposes a large language model (LLM)driven agent for power module design. Unlike conventional automation pipelines, it employs a standardized tool interface contract (description-schema-function) to encapsulate modeling, simulation, optimization, a…
  crossref Ruiting Ke, Jianfeng Tao, Xiaojian Ding, Chengliang Liu 2026-06-12T19:40:44Z 置信度 0.70
• ResStock-LLM: A Multi-Agent Framework for Climate-Adaptive Residential Retrofit Decisions
  Residential building retrofits are essential for improving energy efficiency and reducing greenhouse gas emissions, yet identifying effective retrofit actions for building stocks remains challenging. Current methods often compare pre- and post-retrofit simulat…
  crossref Xinyue Xu, Julian Wang, Xingjian Liu 2026-06-09T07:52:59Z 置信度 0.70
• Agri-LAPP: An LLM-Based Agent Framework for Adaptive Path Planning in Precision Agriculture
  Precision agriculture increasingly relies on autonomous unmanned ground vehicles (UGVs) to handle complex tasks. Path planning is the key to empowering intelligent automation, directly improving efficiency and reducing energy consumption by generating globally…
  crossref Ye Zeng, Ruyi Wang, Yuze Liu, Chao Chen 等 2026-02-18T06:36:51Z 置信度 0.70
• Architectural Safety Mechanisms for Multi-Agent Clinical LLM Systems Under Knowledge Base Distribution Shift
  Objective To evaluate whether multi-agent LLM architectures with explicit safety verification maintain guideline compliance when their clinical knowledge bases undergo temporal or institutional distribution shift. Materials and Methods We designed a controlled…
  europepmc 2026 置信度 0.80
• Agentic AI and LLM-Driven Framework for Contextual Anomaly Detection
  The rapid proliferation of autonomous LLM-based agents in high-stakes enterprise and operational environments has created a critical safety gap: these agents generate multi-step action plans that can fail through contextual misalignment, structural incoherence…
  europepmc 2026 置信度 0.80
• An Agentic OODA Framework for Transparent End to End Clinical Decision Support
  Abstract Artificial Intelligence (AI) agents are increasingly being explored for automation purposes in healthcare applications. However, their deployment raises concerns regarding the reliability, usability, and trustworthiness in clinical decision support. I…
  europepmc 2026 置信度 0.80
• A Large Language Model-Powered Multiagent Framework Emulating Standardized Patients in Clinical Communication Skills Training: Development and Evaluation Study.
  Background Effective clinical communication is essential for medical practice, with standardized patients (SPs) being a reliable standard training method despite resource limitations. While large language models (LLMs) show strong role-playing abilities, curre…
  europepmc 2026 置信度 0.80
• A multimodal multi-agent LLM framework for identifying key drivers of sleep disorders.
  Introduction Sleep quality and sleep disorders are influenced by interacting lifestyle, behavioral, physiological, and occupational determinants, but most existing studies examine these factors in isolation. Traditional statistical methods may be limited in mo…
  europepmc 2026 置信度 0.80
• Multi-camera vision-based structural health monitoring of historic masonry minarets with LLM/VLM-assisted damage interpretation.
  This study proposes an LLM/VLM-orchestrated multi-agent framework for multi-camera vision-based Structural Health Monitoring (SHM) of historic masonry minarets. The main novelty of the framework is its region-aware and auditable decision-support strategy: came…
  europepmc 2026 置信度 0.80
• Multi-Agent Dynamic Refinement Outperforms Static RAG in Clinical Reasoning for Complex Nephrology Cases
  Background Large language models (LLMs) struggle with dynamic, longitudinal clinical reasoning. We developed a Multi-Stage Iterative Clinical Reasoning Agent framework to address this gap and systematically decouple the clinical efficacy of static retrieval-au…
  europepmc 2026 置信度 0.80
• Water-MAS: A multi-agent LLM framework with instruction-data decoupling for smart water management.
  Sustainable water management demands transforming heterogeneous, long-sequence water data into timely, data-driven insights. While single-agent systems can perform basic tasks through tool integration, they suffer from low accuracy, limited adaptability, and i…
  europepmc 2026 置信度 0.80
• Patient Cognitive Bias in Large Language Model-Supported Health Consultations: Simulation-Based Comparative Study.
  Background Large language models (LLMs) are increasingly used by patients for health information and preliminary medical advice. In patient-facing consultations, users may present explicitly stated diagnostic preferences or symptom narratives emphasizing a pre…
  europepmc 2026 置信度 0.80
• Multi-Agent Social Simulation: Protocolizing LLM-Driven Agent-Based Modeling as a Quantitative Research Method
  Social and behavioral research often requires the examination of policy shocks, information interventions, platform-mediated attention, and governance feedback. However, direct experiments on real populations are frequently constrained by ethical risks, interv…
  europepmc 2026 置信度 0.80
• A Topological Robustness and Anti-Fragility Framework for LLM Agents
  Abstract Adversarial evaluation of large-language-model agents is usually expressed as event counts: attack-success rate, policy-violation rate, refusal-failure rate, pass percentage, or robustness score. These measures are necessary, but they do not show whet…
  europepmc 2026 置信度 0.80
• Measuring What Survives: Pressure-Filtered Persistence and a Masking Index for LLM-Agent Safety Evaluation
  Abstract When a safety intervention lowers an agent’s attack-success rate, two different things may have happened: the intervention removed a load-bearing failure route, or the agent learned the measured attacks while the route survived. Frequency metrics are …
  europepmc 2026 置信度 0.80
• Evaluating LLM-Based Coders in Psychological Assessment: A Validation Framework With Application to the Rorschach Morbid Content Variable.
  Large language models (LLMs) are increasingly used to support psychological assessment, but standards for evaluating their scoring accuracy remain limited. This article introduces a clear, reproducible validation framework to evaluate LLM-based scoring systems…
  europepmc 2026 置信度 0.80
• Affect-Aware Human-Agent Conversations: Towards Empathic LLM Interaction
  Abstract Large Language Models can produce supportive responses, but their apparent empathic behavior is usually grounded only in explicit textual input. This paper presents Empathic Extended Prompting a real-time affect-aware framework that enriches human--LL…
  europepmc 2026 置信度 0.80
• Advanced persistent threat detection through multi-modal behavioral analysis.
  Advanced Persistent Threats (APTs) represent sophisticated cyberattacks characterized by stealth, persistence, and evasion of traditional detection mechanisms. We observed that APT behaviors during lateral movement and data exfiltration share notable similarit…
  europepmc 2026 置信度 0.80
• LLM-Driven Diagnostic Reasoning for Distributed Hydrological Model Calibration
  Abstract Calibration of distributed hydrological models remains computationally intensive in nested-basin systems, where upstream errors propagate downstream, and performance must be balanced across multiple outlets. Traditional optimization algorithms rely on…
  europepmc 2026 置信度 0.80
• HAMAgent: human assisted multiagent system for emotion recognition and digital health-a survey and preliminary study.
  This study surveys existing multi-large language model (LLM) agent applications, comparing systems that incorporate active human participation with those that operate fully autonomously within digital health contexts. Building on this analysis, we conduct an e…
  pubmed Li Y, Sun Q, Xue J, Javadov A 等 2026 置信度 0.82
• Multi-Agent LLMs for Occupational Profiling: Psychometric Validation on 1636 Chinese Occupations.
  Occupation-level psychological profiles, such as RIASEC interests and Big Five personality, underpin career counseling, person-job matching, and workforce research, but building them at scale has been expensive and limited to a few national taxonomies. The O*N…
  europepmc 2026 置信度 0.80
• A Study on an Explainable Causal-Enhanced LLM Agent for Predicting the Forming Quality of Automotive Component Materials
  Abstract Raw material composition, heat treatment, cooling, equipment parameters and die condition have an impact on the forming quality of materials for automotive components. Current prediction models can detect the defect or deviation in the performance, bu…
  europepmc 2026 置信度 0.80
• MCP-TAD: An MCP-Based Agent Framework with Tool Routing and Alarm Suppression for Time-Series Anomaly Detection
  Abstract Anomaly detection for time series is essential in Artificial Intelligence for IT Operations (AIOps), yet practical deployment remains difficult because monitoring data are often weakly labeled, high-volume, and heterogeneous across services. Recent La…
  europepmc 2026 置信度 0.80
• GeoExtractor: A Framework for Structured Information Extraction from Geoscientific Literature
  Abstract Earth science research increasingly depends on the integration of large volumes of heterogeneous data distributed across publications. And a substantial amount of quantitative information remains embedded in unstructured literature, making large-scale…
  europepmc 2026 置信度 0.80
• BIOGEN: evidence-grounded multi-agent reasoning framework for transcriptomic interpretation in antimicrobial resistance.
  Introduction Interpreting gene clusters derived from RNA sequencing (RNA-seq) remains difficult in functional genomics, particularly in antimicrobial resistance studies where mechanistic context is needed for downstream hypothesis generation. Methods We presen…
  europepmc 2026 置信度 0.80
• Hands-free motor imagery EEG classification via LLM multi-agents.
  Background Motor imagery (MI) brain-computer interfaces (BCI) rely on precise electroencephalogram (EEG) classification. However, issues such as the reliance on extensive manual experience for MI-EEG model design, parameter tuning, and optimization directions,…
  europepmc 2026 置信度 0.80
• LLM-Guided Digital Twin Agents for Autonomous Threat Detection and Response in Cyber-Physical Energy Systems
  Abstract Cyber-physical energy systems increasingly depend on digital monitoring, communication infrastructures, distributed energy resources, flexible demand response, and automated control mechanisms. This growing digitalization improves operational flexibil…
  europepmc 2026 置信度 0.80
• Semantic Camouflage in Artificial Organizations: A Real-LLM Multi-Agent Simulation of Information Distortion and Audit
  Abstract Large language model (LLM) agents are increasingly organized as role-based teams, yet most technical demonstrations assume cooperative alignment. This study develops a transcript-based simulation framework for examining how organizational structure an…
  europepmc 2026 置信度 0.80
• Bounded Rationality and Resilience in Global Rare Earth Supply Chains: An LLM-Powered Multi-Agent Simulation
  Abstract Rare earth elements (REEs) rely on highly concentrated trade networks that are structurally vulnerable to geopolitical shocks. Conventional static network models and local optimization algorithms struggle to capture the complex behavioral dynamics—suc…
  europepmc 2026 置信度 0.80
• RESCUE: An end-to-end multi-agent LLM system for proactive rare-disease patient screening in the EHR
  Rare diseases affect a significant portion of the global population, yet patients often endure a lengthy diagnostic odyssey, frequently missing the opportunity for timely diagnoses with exome or genome sequencing (ES/GS). Existing informatics tools often rely …
  pubmed Liu C, Geltzeiler A, Afyouni A, Nie M 等 2026 置信度 0.82
• A Beginner's Guide to Applying Large Language Models in Behavioral Interventions.
  Digital behavioral interventions are increasingly used to support chronic disease self-management, yet many systems rely on predetermined content that limits personalization and sustained engagement. Large language models (LLMs) offer new opportunities to deli…
  europepmc 2026 置信度 0.80
• From raw audio to structure: an agent-based pipeline that boosts medical LLM performance.
  Large language models (LLMs) are increasingly applied in clinical communication, yet their reliability depends on high-quality conversational corpora. Real-world doctor-patient recordings are frequently degraded by noise, transcription errors, speaker overlap,…
  europepmc 2026 置信度 0.80
• A hierarchical multi-agent reinforcement learning framework with high-level guidance from large language models.
  Multi-agent reinforcement learning (MARL) has achieved substantial progress in cooperative decision-making, but learning remains difficult in environments with sparse rewards, long decision horizons, and strong inter-agent coupling. Existing methods usually op…
  europepmc 2026 置信度 0.80
• CA2-MARL: A Multi-Agent Fairness-Aware Order Dispatching System with LLM-Guided Policy and Competitive Attention
  Abstract In recent years, the proliferation of ride-hailing platforms such as Uber and Didi Chuxing has profoundly transformed urban mobility. While efficiency remains a core operational metric for these platforms, an exclusive focus on this metric risks negle…
  europepmc Jinhuan Dong, Xiaohui Huang, Nan Jiang, Xuebo Cheng 2026 置信度 0.80
• Automated Symptom Identification from Clinical Interview Transcripts in Diagnosed Schizophrenia: A Multi-Agent LLM Framework.
  We present a multi-agent LLM framework for automated evaluation of symptom-criteria consistency in diagnosed schizophrenia cases. Our system decomposes evaluation into seven specialized agents with RAG-augmented DSM-5/ICD-11 knowledge: symptom extraction, stan…
  europepmc 2026 置信度 0.80
• Harness Engineering for LLM Agents: A Survey of Harness Component Taxonomy, Evaluation, and Model–Harness Coevolution
  As large language model-driven autonomous agents are increasingly deployed in real-world long-horizon, open-environment tasks, foundation models expose systematic capability gaps in context retention, reliable tool invocation, persistent state management, and …
  europepmc 2026 置信度 0.80
• FedMARL-LTI: Federated Multi-Agent Reinforcement Learning with LLM-Driven Threat Intelligence for Cooperative Cyber Defense
  Cross-organization cyber defense must reconcile collaborative learning with privacy and adversarial robustness — yet standard federated learning ships full gradient tensors, leaking sensitive posture and inviting Byzantine manipulation. We present FedMARL-LTI,…
  europepmc 2026 置信度 0.80
• A Large Language Model-Driven System for Advance Care Planning Training Among Health Care Providers in the Chinese Context: Development and Technical Evaluation.
  Background With the expanding need for advance care planning (ACP), innovative educational strategies for training health care providers are increasingly required. Large language model (LLM)-based ACP chatbots offer a novel and potentially effective solution t…
  europepmc 2026 置信度 0.80
• Value crucible for evaluating robustness of value attributed LLM response profiles via agent adversarial debates.
  Static benchmarks reveal what large language models (LLMs) output in isolated prompts but provide limited insight into whether value-attributed response profiles remain consistent during extended interactions. We introduce Value Crucible, a three-stage agent-b…
  europepmc 2026 置信度 0.80
• Conversational AI for Child Abuse Detection Through Multistage Counseling: Model Development and Validation Study.
  Background Child abuse severely disrupts the healthy growth and development of children, resulting in long-term physical as well as emotional consequences. In real-world settings, despite the continuous increase in reported abuse cases, the chronic shortage of…
  europepmc 2026 置信度 0.80
• LLM-Augmented Multi-Agent Reinforcement Learning for Cross-Scenario Knowledge Transfer.
  Multi-agent reinforcement learning (MARL) relies on trial-and-error interactions to update policies. However, trial-and-error learning typically requires extensive interactions to achieve satisfactory performance, resulting in low sample efficiency, which limi…
  europepmc 2026 置信度 0.80
• SafeCodeRL: Security-Constrained Multi-Agent Reinforcement Learning for Trustworthy LLM-Generated IoT/CPS Software.
  Internet of Things (IoT), sensor-network, and cyber-physical system (CPS) software increasingly relies on large language models (LLMs) and autonomous agents for code generation, maintenance, and vulnerability repair. However, LLM-generated edge services, telem…
  europepmc 2026 置信度 0.80
• On-Device Large Language Models for Mobile Applications: A Systematic Survey of Compression, Runtime Efficiency, and Accuracy Latency Privacy Energy Trade-offs
  The rapid advancement of large language models (LLMs) has accelerated a major transition from cloud-centric inference toward on-device deployment on smartphones and edge devices. Running LLMs locally offers important advantages, including lower latency, offlin…
  europepmc 2026 置信度 0.80
• AGREE-YOLO: A Framework for Seafood Recognition and Cross-Cultural Gastronomic Recommendation.
  Real-time visual recognition systems integrated with culturally adaptive reasoning are urgently demanded in globalized culinary scenarios. An agent-oriented framework, Agent-based Gastronomy Recommender Enhanced Engine with YOLO (AGREE-YOLO), is proposed in th…
  europepmc 2026 置信度 0.80
• AutoKFL: Linux Kernel Fault Localization via ReAct-Based Multi-Agent Framework with Dynamic Crash Reproduction.
  Fault localization (FL) is the task of identifying code locations responsible for bugs in software, and it is a prerequisite step in the bug-fixing process. FL in large-scale systems such as the Linux kernel involves three core challenges: First, the vast code…
  europepmc 2026 置信度 0.80
• Mitigating LLM Hallucination Snowballing in Multiagent Systems via Context-Aware Semantic Consistency Reasoning.
  Leveraging the collective intelligence of large language models (LLMs)-based multiagent collaboration has led to significant advancements in intelligent applications across multiple domains. However, due to the untruthful content generated by LLMs, these colla…
  europepmc 2026 置信度 0.80
• PetroAgents: A Multi-Agent, Multi-Modal Large-Language-Model Framework for Integrated Upstream Petroleum Asset Reasoning, Benchmarked on the Equinor Volve Open Dataset
  We present PetroAgents, a multi-agent, multi-modal large-language-model framework for petroleum-engineering reasoning on the Equinor Volve open dataset. The target architecture mirrors an integrated asset team: discipline-specific evidence surfaces, cross-exam…
  europepmc 2026 置信度 0.80
• A framework for clinical validation of generative artificial intelligence therapeutics.
  While established frameworks exist for assessing the clinical efficacy and effectiveness of human-delivered interventions, and standards are in place for pre-artificial intelligence (AI) chatbots that have achieved clearance from the US Food and Drug Administr…
  europepmc 2026 置信度 0.80
• Enhancing the capabilities of large language models for API calls through knowledge graphs.
  API calls by large language model (LLM) represent a cutting-edge technique in data analysis. However, the potential of LLM to effectively utilize tools through API calls remains underexplored in knowledge-intensive sectors such as the meteorological industry. …
  europepmc 2026 置信度 0.80
• Self-Evolving Multi-Agent Fuzzing for Industrial IoT with Knowledge-Driven Cognitive Reasoning.
  Securing the Industrial Internet of Things (IIoT) is paramount, yet proprietary protocols remain vulnerable to deep-state logic flaws that traditional fuzzers often fail to reach. We propose MALF, a Multi-Agent LLM Fuzzing Framework that couples a dynamic Indu…
  pubmed Ning B, Zong X, He K, Wang G 等 2026 置信度 0.82
• A lightweight computational method for monitoring response convergence in LLM-based synthetic populations
  Background: LLM-based synthetic populations are increasingly used to simulate open-ended survey, interview, user-research, and group-style responses. These workflows can support early exploratory research, but they also create a methodological risk: agents con…
  europepmc 2026 置信度 0.80
• Detailed curation of biological samples and experimental designs for genomics using LLM-supported agentic workflows
  We describe an automated software tool to accomplish data curation tasks previously performed by humans for the Gemma genomics data re-analysis resource. Gemma is a hand-curated database of reprocessed transcriptomic studies, currently covering over 23,000 hum…
  europepmc 2026 置信度 0.80
• Modeling Diabetes Risk and Progression With Public Health Data: Ontology-Guided, Simulation-Capable Digital Twin Study.
  Background Digital twins (DTs) offer a paradigm for health care by enabling data-driven, simulation-capable representations of individual health trajectories. However, DT development remains limited by the scarcity of standardized, temporally structured, and m…
  europepmc 2026 置信度 0.80
• AMULED: Addressing Moral Uncertainty using Large language models for Ethical Decision-making.
  Introduction We address moral uncertainty in reinforcement learning (RL) by proposing a framework that integrates multiple ethical theories into decision-making. Existing approaches rely on single moral frameworks or handcrafted rewards, limiting scalability a…
  europepmc 2026 置信度 0.80
• Containment over Detection: Cryptographic Boundary Enforcement for Prompt Injection Defense in Agentic LLM Systems
  Abstract Prompt injection—the manipulation of an LLM-based agent through adversarial content embedded in user input—poses a critical security risk in production agentic systems with access to sensitive datastores and code execution environments. Detection-base…
  europepmc 2026 置信度 0.80
• Public opinion dissemination simulation based on large language model multi-agent systems.
  The Internet has fundamentally reshaped the formation and diffusion of public opinion in modern society. However, existing simulation studies often face challenges such as insufficient fidelity in evolutionary dynamics, behavioral homogenization, and high mode…
  pubmed Lan H, Hu H, Guo PC, Huang Q 2026 置信度 0.82
• Multi-agent systems and credibility-based advanced scoring mechanism in fact-checking.
  Fact-checking is crucial as rumours and misinformation negatively impact social networking services (SNS) and online discussions, often leading to the spread of misinformation. Meanwhile, fact-checking with large language models (LLMs) is becoming increasingly…
  pubmed Dong Y, Ito T 2026 置信度 0.82
• Multi-Agent AI for Chest Radiography: A Sequential Segmentation and LLM-Driven Consultative Tool for Medical Training
  Abstract Background Traditional diagnostic models lack explainability, while multimodal language models prone to hallucination remain unsafe for medical education. An interactive, risk-free artificial intelligence framework is required to serve as a reliable c…
  europepmc Furkan Kurt, Abdulhamit Subasi 2026 置信度 0.80
• A knowledge-enhanced domain-aware large language model agent for atrial fibrillation management.
  Large language models (LLMs) show considerable potential for atrial fibrillation (AF) management, yet current clinical applications frequently remain suboptimal due to accuracy limitations. To address these limitations, this study developed PULSE (Potentiated …
  europepmc 2026 置信度 0.80
• A Lightweight Retrieval-Grounded Framework for Hallucination Detection and Correction in Large Language Models
  Abstract Large Language Models (LLMs) have demonstrated strong performance across question answering, summarization, content generation, and decision-support tasks. However, they remain prone to hallucinations, where generated responses appear fluent and plaus…
  europepmc 2026 置信度 0.80
• Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction
  Abstract Agentic web search increasingly faces two distinct demands: deep reasoning over a single target, and structured aggregation across many entities and heterogeneous sources. Current systems struggle on both fronts. Breadth-oriented tasks demand schema-a…
  europepmc 2026 置信度 0.80
• Illuminating LLM Coding Agents: Visual Analytics for Deeper Understanding and Enhancement.
  Coding agents powered by large language models (LLMs) have gained traction for automating code generation through iterative problem-solving with minimal human involvement. Despite the emergence of various frameworks, e.g., LangChain, AutoML, and AIDE, ML scien…
  europepmc 2026 置信度 0.80
• Agentic markets.
  Generative AI enables autonomous software agents that can search, compare, and transact across digital marketplaces, promising large reductions in consumer search costs and improved matching between buyers and sellers. This paper argues that such gains are not…
  europepmc 2026 置信度 0.80
• When collaboration fails: persuasion driven adversarial influence in multi agent large language model debate.
  Recent developments have made Large Language Model (LLM) multi-agent systems a promising paradigm for enhancing reasoning via collaborative debate and collective deliberation. Prior work has demonstrated that coordinated LLM agents tend to perform better than …
  pubmed Kraidia I, Qaddara I, Almutairi A, Alzaben N 等 2026 置信度 0.82
• MDCrow: automating molecular dynamics workflows with large language models.
  Molecular dynamics (MD) simulations are essential for understanding biomolecular systems but remain challenging to automate. Recent advances in large language models (LLMs) have demonstrated success in automating complex scientific tasks using LLM-based agents…
  europepmc 2026 置信度 0.80
• Decoding China's policy-driven blockchain evolution: a multi-agent collaborative analytical framework.
  Unlike market-driven blockchain evolution paths observed globally, China follows a distinctive policy-guided trajectory integrating technology research, application scenarios, and regulatory governance. However, existing studies have seldom offered a systemati…
  europepmc 2026 置信度 0.80
• Polymer-Agent: Large Language Model Agent for Polymer Design.
  On-demand polymer discovery is essential across various industries, from biomedical applications to reinforcement materials. Experiments with polymers involve a long trial-and-error process that consumes extensive resources. For these processes, machine learni…
  europepmc 2026 置信度 0.80
• DynamiCare: A Dynamic Multi-Agent Framework for Interactive and Open-Ended Medical Decision-Making.
  europepmc 2026 置信度 0.80
• Blinded two-phase evaluation of large language models in complex cardiac surgery: task-specific performance and human-AI collaboration.
  Background Large language models (LLMs) have demonstrated strong performance on standardized medical benchmarks. However, their potential in complex surgical decision-making is largely uncharacterized. Critically, human-LLM collaboration regarding the extent t…
  europepmc 2026 置信度 0.80
• Can small language models handle context-summarized multi-turn customer-service QA? A synthetic data-driven comparative evaluation.
  Customer-service question answering (QA) systems increasingly rely on conversational language understanding. While Large Language Models (LLMs) achieve strong performance, their high computational cost and deployment constraints limit practical use in resource…
  europepmc 2026 置信度 0.80
• Toward Efficient and Generalizable Text Dataset Distillation via a Dual-Agent Large Language Model Framework.
  Large-scale datasets impose substantial training costs on machine learning models. Dataset distillation addresses this issue by synthesizing compact datasets that can achieve performance comparable to that of the original data. However, text dataset distillati…
  europepmc 2026 置信度 0.80