AI Agent 生态 · 全部实体（第 92 / 100 页）

本页收录第 9101–9200 条，共 10000 条 · 返回 AI Agent 生态 首页

• Cooperation Dynamics in Multi-Agent Systems: Exploring Game-Theoretic Scenarios with Mean-Field Equilibria
  Cooperation is fundamental in Multi-Agent Systems (MAS) and Multi-Agent Reinforcement Learning (MARL), often requiring agents to balance individual gains with collective rewards. In this regard, this paper aims to investigate strategies to invoke cooperation i…
  arxiv Vaigarai Sathi, Sabahat Shaik, Jaswanth Nidamanuri 2023-09-28T08:57:01Z 置信度 0.78 cs.GTcs.AI
• An Industrial Perspective on Multi-Agent Decision Making for Interoperable Robot Navigation following the VDA5050 Standard
  This paper provides a perspective on the literature and current challenges in Multi-Agent Systems for interoperable robot navigation in industry. The focus is on the multi-agent decision stack for Autonomous Mobile Robots operating in mixed environments with h…
  arxiv Niels van Duijkeren, Luigi Palmieri, Ralph Lange, Alexander Kleiner 2023-11-24T17:16:57Z 置信度 0.78 cs.RO
• Multi-Agent System Interaction in Integrated SCM
  Coordination between organizations on strategic, tactical and operation levels leads to more effective and efficient supply chains. Supply chain management is increasing day by day in modern enterprises. The environment is becoming competitive and many enterpr…
  arxiv Ritu Sindhu, Abdul Wahid, G. N. Purohit 2009-11-04T19:11:06Z 置信度 0.78 cs.MA
• The Impact of Social Networks on Multi-Agent Recommender Systems
  Awerbuch et al.'s approach to distributed recommender systems (DRSs) is to have agents sample products at random while randomly querying one another for the best item they have found; we improve upon this by adding a communication network. Agents can only comm…
  arxiv Hamilton Link, Jared Saia, Terran Lane, Randall A. LaViolette 2005-11-02T23:44:34Z 置信度 0.78 cs.LGcs.CCcs.MA
• Learning Multi-agent Multi-machine Tending by Mobile Robots
  Robotics can help address the growing worker shortage challenge of the manufacturing industry. As such, machine tending is a task collaborative robots can tackle that can also highly boost productivity. Nevertheless, existing robotics systems deployed in that …
  arxiv Abdalwhab Abdalwhab, Giovanni Beltrame, Samira Ebrahimi Kahou, David St-Onge 2024-08-29T19:57:52Z 置信度 0.78 cs.ROcs.LG
• Thought Virus: Viral Misalignment via Subliminal Prompting in Multi-Agent Systems
  Subliminal prompting is a phenomenon in which language models are biased towards certain concepts or traits through prompting with semantically unrelated tokens. While prior work has examined subliminal prompting in user-LLM interactions, potential bias transf…
  arxiv Moritz Weckbecker, Jonas Müller, Ben Hagag, Michael Mulet 2026-02-23T13:46:26Z 置信度 0.78 cs.MAcs.AI
• Don't Just Demo, Teach Me the Principles: A Principle-Based Multi-Agent Prompting Strategy for Text Classification
  We present PRINCIPLE-BASED PROMPTING, a simple but effective multi-agent prompting strategy for text classification. It first asks multiple LLM agents to independently generate candidate principles based on analysis of demonstration samples with or without lab…
  arxiv Peipei Wei, Dimitris Dimitriadis, Yan Xu, Mingwei Shen 2025-02-11T01:10:13Z 置信度 0.78 cs.CLcs.AI
• GOV-REK: Governed Reward Engineering Kernels for Designing Robust Multi-Agent Reinforcement Learning Systems
  For multi-agent reinforcement learning systems (MARLS), the problem formulation generally involves investing massive reward engineering effort specific to a given problem. However, this effort often cannot be translated to other problems; worse, it gets wasted…
  arxiv Ashish Rana, Michael Oesterle, Jannik Brinkmann 2024-04-01T14:19:00Z 置信度 0.78 cs.MAcs.AI
• Off-the-Grid MARL: Datasets with Baselines for Offline Multi-Agent Reinforcement Learning
  Being able to harness the power of large datasets for developing cooperative multi-agent controllers promises to unlock enormous value for real-world applications. Many important industrial systems are multi-agent in nature and are difficult to model using bes…
  arxiv Claude Formanek, Asad Jeewa, Jonathan Shock, Arnu Pretorius 2023-02-01T15:41:27Z 置信度 0.78 cs.LGcs.AIcs.MA
• Emergent Language: A Survey and Taxonomy
  The field of emergent language represents a novel area of research within the domain of artificial intelligence, particularly within the context of multi-agent reinforcement learning. Although the concept of studying language emergence is not new, early approa…
  arxiv Jannik Peters, Constantin Waubert de Puiseau, Hasan Tercan, Arya Gopikrishnan 等 2024-09-04T12:22:05Z 置信度 0.78 cs.MAcs.CL
• Agent-Time Attention for Sparse Rewards Multi-Agent Reinforcement Learning
  Sparse and delayed rewards pose a challenge to single agent reinforcement learning. This challenge is amplified in multi-agent reinforcement learning (MARL) where credit assignment of these rewards needs to happen not only across time, but also across agents. …
  arxiv Jennifer She, Jayesh K. Gupta, Mykel J. Kochenderfer 2022-10-31T17:54:51Z 置信度 0.78 cs.LGcs.MA
• Energy-Optimal Multi-Agent Navigation as a Strategic-Form Game
  This extended abstracts presents a method to generate energy-optimal trajectories for multi-agent systems as a strategic-form game. Using recent results in optimal control, we demonstrate that an energy-optimal trajectory can be generated in milliseconds if th…
  arxiv Logan Beaver 2024-03-28T17:53:26Z 置信度 0.78 math.OC
• Cayley Graph Optimization for Scalable Multi-Agent Communication Topologies
  Large-scale multi-agent communication has long faced a scalability bottleneck: fully connected networks require quadratic complexity, yet existing sparse topologies rely on hand-crafted rules. This paper treats the communication graph itself as a design variab…
  arxiv Jingkai Luo, Yulin Shao 2026-04-07T13:43:09Z 置信度 0.78 cs.NIcs.ITcs.MA
• Holonic Active Distillation for Scalable Multi-Agent Learning in Multi-Sensor Systems
  The rapid expansion of sensor-based networks introduces major challenges in scalability, adaptability, and knowledge transfer, especially in open environments where new subsystems can dynamically join or leave. In this work, we propose a Holonic Active Distill…
  arxiv Dani Manjah, Tim Bary, Benoît Macq, Stéphane Galland 2026-06-30T12:34:47Z 置信度 0.78 cs.MA
• Thucy: An LLM-based Multi-Agent System for Claim Verification across Relational Databases
  In today's age, it is becoming increasingly difficult to decipher truth from lies. Every day, politicians, media outlets, and public figures make conflicting claims -- often about topics that can, in principle, be verified against structured data. For instance…
  arxiv Michael Theologitis, Dan Suciu 2025-12-02T22:35:48Z 置信度 0.78 cs.DBcs.AI
• Overview: Generalizations of Multi-Agent Path Finding to Real-World Scenarios
  Multi-agent path finding (MAPF) is well-studied in artificial intelligence, robotics, theoretical computer science and operations research. We discuss issues that arise when generalizing MAPF methods to real-world scenarios and four research directions that ad…
  arxiv Hang Ma, Sven Koenig, Nora Ayanian, Liron Cohen 等 2017-02-17T20:39:38Z 置信度 0.78 cs.AIcs.MAcs.RO
• Context Engineering for Multi-Agent LLM Code Assistants Using Elicit, NotebookLM, ChatGPT, and Claude Code
  Large Language Models (LLMs) have shown promise in automating code generation and software engineering tasks, yet they often struggle with complex, multi-file projects due to context limitations and knowledge gaps. We propose a novel context engineering workfl…
  arxiv Muhammad Haseeb 2025-08-09T14:45:53Z 置信度 0.78 cs.SEcs.AI
• Learning Bilateral Team Formation in Cooperative Multi-Agent Reinforcement Learning
  Team formation and the dynamics of team-based learning have drawn significant interest in the context of Multi-Agent Reinforcement Learning (MARL). However, existing studies primarily focus on unilateral groupings, predefined teams, or fixed-population setting…
  arxiv Koorosh Moslemi, Chi-Guhn Lee 2025-06-24T22:40:05Z 置信度 0.78 cs.MAcs.AIcs.GTcs.LG
• On Some Fundamental Problems for Multi-Agent Systems Over Multilayer Networks
  Many researchers have considered multi-agent systems over single-layer networks as models for studying diffusion phenomena. Since real-world networks involve connections between agents with different semantics (e.g., family member, friend, colleague), the stud…
  arxiv Daniel J. Rosenkrantz, Madhav V. Marathe, Zirou Qiu, S. S. Ravi 等 2025-03-16T22:56:44Z 置信度 0.78 cs.MAcs.CC
• Investigating the Impact of Direct Punishment on the Emergence of Cooperation in Multi-Agent Reinforcement Learning Systems
  Solving the problem of cooperation is fundamentally important for the creation and maintenance of functional societies. Problems of cooperation are omnipresent within human society, with examples ranging from navigating busy road junctions to negotiating treat…
  arxiv Nayana Dasgupta, Mirco Musolesi 2023-01-19T19:33:54Z 置信度 0.78 cs.MAcs.AIcs.LG
• Analysing Factorizations of Action-Value Networks for Cooperative Multi-Agent Reinforcement Learning
  Recent years have seen the application of deep reinforcement learning techniques to cooperative multi-agent systems, with great empirical success. However, given the lack of theoretical insight, it remains unclear what the employed neural networks are learning…
  arxiv Jacopo Castellini, Frans A. Oliehoek, Rahul Savani, Shimon Whiteson 2019-02-20T10:47:19Z 置信度 0.78 cs.MA
• Variational Policy Propagation for Multi-agent Reinforcement Learning
  We propose a \emph{collaborative} multi-agent reinforcement learning algorithm named variational policy propagation (VPP) to learn a \emph{joint} policy through the interactions over agents. We prove that the joint policy is a Markov Random Field under some mi…
  arxiv Chao Qu, Hui Li, Chang Liu, Junwu Xiong 等 2020-04-19T15:42:55Z 置信度 0.78 cs.LGcs.MAstat.ML
• A Large Language Model-based multi-agent manufacturing system for intelligent shopfloor
  As customer demand for multi-variety and small-batch production increases, dynamic disturbances place greater demands on manufacturing systems. To address such challenges, researchers proposed the multi-agent manufacturing system. However, conventional agent n…
  arxiv Zhen Zhao, Dunbing Tang, Changchun Liu, Liping Wang 等 2024-05-27T07:10:04Z 置信度 0.78 cs.AIcs.MAcs.RO
• Refined Hardness of Distance-Optimal Multi-Agent Path Finding
  We study the computational complexity of multi-agent path finding (MAPF). Given a graph $G$ and a set of agents, each having a start and target vertex, the goal is to find collision-free paths minimizing the total distance traveled. To better understand the so…
  arxiv Tzvika Geft, Dan Halperin 2022-03-14T18:23:22Z 置信度 0.78 cs.MAcs.CGcs.RO
• ARCANE: A Multi-Agent Framework for Interpretable and Configurable Alignment
  As agents based on large language models are increasingly deployed to long-horizon tasks, maintaining their alignment with stakeholder preferences becomes critical. Effective alignment in such settings requires reward models that are interpretable so that stak…
  arxiv Charlie Masters, Marta Grześkiewicz, Stefano V. Albrecht 2025-12-05T22:39:54Z 置信度 0.78 cs.AIcs.CL
• Verification & Validation of Agent Based Simulations using the VOMAS (Virtual Overlay Multi-agent System) approach
  Agent Based Models are very popular in a number of different areas. For example, they have been used in a range of domains ranging from modeling of tumor growth, immune systems, molecules to models of social networks, crowds and computer and mobile self-organi…
  arxiv Muaz A. Niazi, Amir Hussain, Mario Kolberg 2017-08-08T03:07:41Z 置信度 0.78 cs.MAcs.AIcs.SEnlin.AOnlin.CG
• Adaptive Multi-Agent Role Reassignment over Model Context Protocol for Resilient AI Orchestration
  Abstract Multi-agent systems powered by large language models (LLMs) can automate complex workflows by dividing tasks among specialised roles such as research, critique and summarisation. Existing orchestration frameworks typically assign these roles staticall…
  europepmc Manish Shukla 2025 置信度 0.80
• Q-PACT : Quantum-Parallel Agentic Coordination Toolkit
  Abstract The convergence of quantum optimization and autonomous agentic reasoning defines a new computational frontier in large-scale resource coordination. This work introduces Q-PACT, a Quantum-Parallel Agentic Coordination Toolkit that unifies quantum optim…
  europepmc 2026 置信度 0.80
• The AI interviewer: multi-faceted evaluation of adaptive questioning by large language models.
  Large language models are increasingly deployed as adaptive interviewers in qualitative research and human-computer interaction, yet systematic evaluation of their interviewing behavior remains limited. We introduce a modular LLM agent for conducting semi-stru…
  europepmc 2026 置信度 0.80
• From DevOps to XOps: An Agent-Driven Reference Architecture for Autonomous Enterprise Operations
  Abstract As enterprises increasingly adopt artificial intelligence as a core operational capability, traditional DevOps pipelines face fundamental limitations in managing the inherently stochastic nature of data streams and machine learning models. The prolife…
  europepmc 2026 置信度 0.80
• AI agents in drug discovery: A review of evolution, applications, and future directions.
  Artificial intelligence (AI) agents represent a paradigm shift in pharmaceutical research, moving the field from narrow drug-protein affinity modeling toward systems-biology-level evaluation in which autonomous, multi-domain agents combine pattern recognition …
  pubmed Das S, Ferdaus MM, Dam T 2026 置信度 0.82
• Exploring Agentic AI in Healthcare: A Study on Its Working Mechanism.
  Rapid advancements in artificial intelligence (AI) have ushered in an era of hyperautomation and intelligent orchestration across multiple engineering domains, with healthcare emerging as one of the most impactful application areas. Among recent developments, …
  pubmed Srinivasu PN, Aruna Kumari GL, Ahmed S, Alhumam A 2025 置信度 0.82
• Orchestrator multi-agent clinical decision support system for secondary headache diagnosis in primary care.
  Secondary headaches require urgent recognition due to potentially devastating consequences if untreated. Despite established clinical "red flag" criteria, identifying patients needing immediate evaluation remains challenging in primary care. This study develop…
  pubmed Wu X, Zhang H, Garduno-Rapp NE, Rousseau JF 等 2026 置信度 0.82
• The Next Paradigm in Medical AI: A Survey of Agentic AI in Biomedicine.
  Biomedical AI is increasingly shaped by policy-bound, multi-step clinical workflows and non-stationary, multimodal data and tools. In this setting, the field is moving beyond static predictors toward agentic systems, enabled by foundation models that maintain …
  europepmc 2026 置信度 0.80
• Towards Intelligent UAV Path Planning: A Systematic Review of Hybrid Reinforcement Learning and Metaheuristic Optimization
  Abstract UAV path planning in complex 3D environments is an NP-hard problem. Standard metaheuristics (MH) suffer from premature convergence, while pure reinforcement learning (RL) exhibits slow initial convergence, motivating hybrid RL--MH frameworks. This sys…
  europepmc 2026 置信度 0.80
• From Feature Variability to Agency Variability: A Software Product-Line Engineering Framework for Governed Agentic AI Systems
  Agentic artificial intelligence systems increasingly combine language models, memory, retrieval, tool use, orchestration, and human oversight. For software engineering, this creates a variability problem that feature-oriented product line methods only partly a…
  europepmc 2026 置信度 0.80
• Big Data-Driven Explainable Agentic AI Decision Frameworks for Enterprise Innovation in FinTech Ecosystems.
  FinTech ecosystems are growing at a rapid pace, creating large-scale, heterogeneous, and highly interconnected data environments that pose challenges to traditional frameworks for innovation management and decision support. Even while artificial intelligence (…
  europepmc 2026 置信度 0.80
• A Review of Multi-Agent AI Systems for Biological and Clinical Data Analysis.
  This review evaluates the emerging paradigm of multi-agent systems (MASs) for biomedical and clinical data analysis, focusing on their ability to overcome the reasoning and reliability limitations of standalone large language models (LLMs). We synthesize findi…
  pubmed Spieser J, Balapour A, Meller J, Patra KC 等 2026 置信度 0.82
• PAiNT: Perspective-Aware AI Identity and Narrative Toolkit for Generating Labeled Digital Footprints
  Modeling a user's evolving goals, values, and affect over time is central to perspective-aware AI, yet progress is bottlenecked by the lack of longitudinal data with ground-truth labels for latent identity state. We introduce PAiNT (Perspective-Aware AI Identi…
  europepmc 2026 置信度 0.80
• ORCH: many analyses, one merge-a deterministic multi-agent orchestrator for discrete-choice reasoning with EMA-guided routing.
  Multi-agent/ensemble approaches can improve discrete-choice reasoning with large language models, but common orchestration methods are often non-deterministic, expensive, and difficult to reproduce. We propose ORCH, a deterministic multi-agent orchestrator tha…
  pubmed Zhou H, Chan HY 2026 置信度 0.82
• Security and Privacy for Next-Generation AI Ecosystems: A Systematic Survey and Layered Defense Framework
  Abstract Modern AI deployments are ecosystems, not isolated models: data pipelines, modelservices, orchestration agents, domain applications, and cloud infrastructure interact underevolving regulatory regimes. Security failures in these settings arise not just…
  europepmc 2026 置信度 0.80
• MoSAIC-PPO: Mobility-aware Service Allocation with Integrated Constraints using Proximal Policy Optimization for Vehicular Edge Computing
  Abstract Vehicular Edge Computing (VEC) enables latency critical vehicular applications by offloading computation from vehicles to nearby edge service providers (ESPs). However, high vehicle mobility, bursty service demand, limited edge resources, and inter-se…
  europepmc 2026 置信度 0.80
• BioAgent: An Auditable Multi-Agent Framework for Reproducible Translational Bioinformatics
  Abstract Background Translational bioinformatics studies require coordinated literature review, public data acquisition, executable analysis, and auditable reporting. Most large language model-based assistants address isolated tasks or rely on pre-curated data…
  europepmc 2026 置信度 0.80
• Emergent Coordination in Multi-Agent Systems via Pressure Fields and Temporal  Decay
  Abstract Current multi-agent large language model (LLM) frameworks rely on explicit orchestration patterns borrowed from human organizational structures: planners delegate to executors, managers coordinate workers, and hierarchical control flow governs agent i…
  europepmc 2026 置信度 0.80
• Hybrid-Oriented Intelligent Operational and Architectural Foundations of IoT-Enabled Smart Grids: A System-Level Review and Challenge-Oriented Comparative Synthesis
  The rapid digitalization of energy systems and the increasing integration of distributed energy re-sources, renewable energy technologies, and prosumer-oriented infrastructures have accelerated the development of IoT-enabled Smart Grids as a foundation for int…
  europepmc 2026 置信度 0.80
• When the Author Talks Back: Autonomous AI Agents, Rejection, and the Integrity of Peer Review.
  europepmc 2026 置信度 0.80
• Stop Comparing LLM Agents Without Disclosing the Harness
  This position paper argues that, for long-horizon tasks evaluated across models with comparable frontier capability, the agent execution harness, namely the infrastructure layer that governs context construction, tool interaction, orchestration, and verificati…
  europepmc 2026 置信度 0.80
• Tool and Agent Selection for Large Language Model Agents in Production: A Survey
  Large Language Model (LLM) agents have demonstrated remarkable abilities to interact with external tools, functions, Model Context Protocol (MCP) servers, agents, and to take action on behalf of the user. Due to the fast-paced nature of the industry, existing …
  europepmc 2026 置信度 0.80
• A Comprehensive Survey of the LLM-Based Agent: The Contextual Cognition Perspective
  Large language model (LLM)-based agents have given rise to phenomenal applications (e.g., OpenClaw, Claude Code), transitioning from fixed text processing to complex task execution. However, most existing works conceptualize the LLM-based agent by decomposing …
  europepmc 2026 置信度 0.80
• Med.ai ASK: an agentic system for biomedical question answering.
  Objective Intelligent agent-driven research co-pilots, leveraging advances in generative AI, are transforming how scientists access biomedical knowledge. This paper presents Med.ai ASK, an agentic question-answering system designed to address biomedical inquir…
  europepmc 2026 置信度 0.80
• Planning and Evaluation Methods in LLM-Based Autonomous Workflow Systems: A Comprehensive Review
  Abstract Large language models (LLMs) increasingly serve as the cognitive core of autonomous systems that plan, reason, and execute multi-step workflows across domains such as software engineering, web automation, enterprise orchestration, and robotics. While …
  europepmc 2026 置信度 0.80
• Kubernetes Resource Optimization Using Machine Learning: A Comprehensive Review of Widely Used Techniques
  The rapid adoption of Kubernetes as the de-facto container orchestration platform has created growing demand for intelligent, scalable, and proactive resource optimization mechanisms. Although Kubernetes provides native autoscaling components such as the Horiz…
  europepmc 2026 置信度 0.80
• Optimizing genomics-aware clinical agents in precision oncology.
  Agentic systems are proposed for clinical decision support, yet unrestricted tool access can undermine accountability and safety in precision oncology, where recommendations must be grounded in evolving guidelines, regulatory labels, and patient-specific molec…
  europepmc 2026 置信度 0.80
• AI-driven CRISPR screening: optimizing gene editing through automation and intelligent decision support.
  Background CRISPR-based genetic screening has become a central methodology in functional genomics, enabling systematic interrogation of gene function, genetic interactions and context-dependent vulnerabilities at scale. However, the rapid expansion of screenin…
  europepmc 2026 置信度 0.80
• GeneGenie: enhancing biomedical question-answering with agentic graphs.
  Large language models (LLMs) have revolutionized biomedical research, yet they remain prone to hallucinations and struggle with the precise, multi-hop reasoning required for biomedical analysis. To bridge this gap between generative capability of AI model and …
  pubmed Abdelsalam MG, El-Safty AH, Zaidi A, Alam T 2026 置信度 0.82
• OpenClaw as Language Infrastructure: A Case-Centered Survey of a Public Agent Ecosystem in the Wild
  Public agent ecosystems are emerging as a new object of study in NLP: settings in which language models not only generate text but also act, coordinate, authenticate, exchange reusable capabilities, and leave durable public traces. Using the OpenClaw--Moltbook…
  europepmc 2026 置信度 0.80
• Contextual Reasoning Orchestration for Enhancing Black-Box Large Language Models in Specialized Decision Support
  Recent advances in language models have greatly improved their ability to understand and generate natural language. Yet, when applied to specialized fields such as financial decision support or complex system diagnosis, they often struggle with limited domain …
  europepmc 2025 置信度 0.80
• Enhancing reliability and automation of LLM-based structural analysis using a hybrid multi-agent pipeline.
  Large language models (LLMs) can assist engineering workflows, but their direct application in structural analysis is fundamentally limited by numerical inconsistencies, prompt sensitivity, and context degradation. To address these bottlenecks, a verification-…
  pubmed Heo S 2026 置信度 0.82
• A multi-agent RAG system for generating SCORM courses from enterprise documents.
  Corporate onboarding requires the effective transfer of complex organizational knowledge embedded in internal policies and procedural documents; however, existing artificial intelligence (AI)-driven course generation systems primarily target academic or public…
  europepmc 2026 置信度 0.80
• Reinforcement learning driven edge-cloud coordination for secure and energy efficient IoMT.
  The Internet of Medical Things (IoMT) enables sophisticated medical devices, but it also poses significant challenges in terms of data privacy, real-time processing, and energy efficiency for edge devices with limited resources. In this paper, we propose a hie…
  europepmc 2026 置信度 0.80
• DACCA: Distributed Adaptive Cloud Continuum Architecture
  Recently, the need for unified orchestration frameworks that can manage extremely heterogeneous, distributed, and resource-constrained environments has arisen due to the rapid development of cloud, edge, and IoT computing. Kubernetes and other traditional clou…
  europepmc 2025 置信度 0.80
• MolClaw: An Autonomous Agent with Hierarchical Skills for Drug Molecule Evaluation, Screening, and Optimization
  Computational drug discovery, particularly the complex workflows of drug molecule screening and optimization, requires orchestrating dozens of specialized tools in multi-step workflows, yet current AI agents struggle to maintain robust performance and consiste…
  europepmc 2026 置信度 0.80
• An Event-Driven Multi-Agent Workflow for Microscopy Data Analysis Using the Model Context Protocol
  Abstract Advanced electron microscopy increasingly depends on data-intensive acquisition modes and specialized post-processing workflows that remain difficult to access for non-expert users. Although recent large language model (LLM) systems offer new possibil…
  europepmc 2026 置信度 0.80
• Situational perception in distracted driving: an agentic multi-modal LLM framework.
  Introduction Distracted driving is a significant public safety concern, causing thousands of accidents annually. While most driver assistance systems emphasize distraction detection, they fail to deliver real-time environmental perception and context-aware int…
  europepmc 2025 置信度 0.80
• Accelerated drug development using a digital formulator and a self-driving tableting data factory.
  Advances in drug discovery and clinical research have shifted the bottleneck in medicines development to chemistry, manufacturing, and controls activities, a critically step for regulatory approval. This includes formulation and process development of a new dr…
  europepmc 2026 置信度 0.80
• The Biofilm Plight in Healthcare: Orchestration and Control by Lactiplantibacillus plantarum.
  The clinical consequences of biofilm-related infections are on the rise. Biofilm-related infections represent a mounting burden on healthcare worldwide, posing a significant challenge to patient care and health infrastructure. Another notorious function that n…
  europepmc 2026 置信度 0.80
• Authenticating AI Agents in a World of Deepfakes: A Multi-Layer Framework for Establishing Trust in Autonomous Digital Entities
  The rapid proliferation of agentic AI, autonomous software systems capable of executing transactions, accessing sensitive data, and acting on behalf of human users, has created an unprecedented security challenge. The existing authentication systems which deve…
  europepmc 2026 置信度 0.80
• EASE-6G: An Energy-Aware SDN Framework with Proactive Slicing and DL-Based Overhead Mitigation for Scalable IoT Networks.
  Sixth-generation (6G) networks are expected to enable a new level of connectivity, with peak data rates reaching 1 Tbps and latencies below 0.1 ms, especially in large-scale Internet of Things (IoT) environments. Despite these advantages, the rapid increase in…
  europepmc 2026 置信度 0.80
• Antibacterial and Wound-Healing Efficacy of 12-Hydroxylauric Acid-Conjugated Heterochiral Diphenylalanines: Insights From In Vitro and In Vivo Investigations.
  To overcome the limitations of microbial infections in modern medicine, we developed compound I incorporating the amphiphile 12-hydroxy lauric acid (12-HDA) at the N-terminus linked to a heterochiral diphenylalanine motif (D- and L-Phe) at the C-terminus guide…
  pubmed Ahuja R, Shivhare V, Barde D, Ahirwar SK 等 2026 Aug 14 置信度 0.82
• GeneGenie: enhancing biomedical question-answering with agentic graphs.
  Large language models (LLMs) have revolutionized biomedical research, yet they remain prone to hallucinations and struggle with the precise, multi-hop reasoning required for biomedical analysis. To bridge this gap between generative capability of AI model and …
  pubmed Abdelsalam MG, El-Safty AH, Zaidi A, Alam T 2026 Jul 3 置信度 0.82
• Cytokine-mediated immune-to-brain signaling in neural circuit disorders.
  Neuroinflammation has emerged as a fundamental driver of neural circuit dysfunctions across a spectrum of neurodevelopmental and psychiatric disorders. Beyond classical neuroimmune pathologies, accumulating evidence indicates that systemic inflammatory states …
  pubmed Lee Y, Ko J, Um JW 2026 Aug 4 置信度 0.82
• Automating SWMM-based stormwater modelling and analysis through a tool-augmented single-agent system.
  Urban stormwater modelling plays a critical role in assessing interventions for flood risk and water quality management in response to ageing infrastructure and future uncertainties. However, modelling workflows in practice remain highly manual, and key steps …
  pubmed Wang J, Sun C, Savic D, Fu G 2026 Aug 4 置信度 0.82
• Cross-scale modeling reveals a TFRC-driven immunosuppressive macrophage niche in cervical cancer.
  The functional plasticity of tumor-associated macrophages (TAMs) is a critical determinant of the immunosuppressive microenvironment in cervical cancer, yet its integration into actionable prognostic frameworks remains limited. This study aimed to establish a …
  pubmed Chen Y, Wang L, Li S, Huang J 等 2026 置信度 0.82
• Molecular Mechanisms of the Anticancer Activity of the Flavonoid Kaempferol: A Comprehensive Review.
  Kaempferol (KAE), a natural flavonoid, has emerged as a promising multi-target antineoplastic agent characterized by high efficacy and minimal systemic toxicity. Moving beyond fragmented descriptive summaries, this comprehensive review provides a highly integr…
  pubmed Cui M, Zhao Y, Wang Y 2026 Jul 30 置信度 0.82
• Chronotherapy in Hematological Malignancies: Evaluating the Rationale and Evidence.
  Hematological malignancies remain one of the leading causes of morbidity and mortality despite advances in targeted therapies, immunotherapy, and stem cell transplantation. Emerging evidence indicates that treatment efficacy and toxicity depend not only on the…
  pubmed Belančić A, Skelin M, Lam YW, Fajkić A 等 2026 Aug 置信度 0.82
• The role of ginsenosides in obesity-associated sarcopenia: Focus on E3 ubiquitin ligase-mediated regulation of protein homeostasis.
  Obesity-associated sarcopenia (OAS) is a complex metabolic disorder characterized by excessive adiposity accompanied by progressive skeletal muscle loss, largely driven by impaired protein homeostasis. The ubiquitin-proteasome system (UPS) plays a central role…
  pubmed Zhou W, Li PT, Li HY, Li W 2026 Aug 1 置信度 0.82
• Epithelial-immune interface in asthma: Mechanistic insights driving novel therapeutic strategies.
  Asthma is a heterogeneous chronic respiratory syndrome driven by complex interactions between environmental triggers and the host immune system while biologic therapies targeting downstream type 2 cytokines (e.g., anti-IL-5, anti-IL-4Rα) have improved ou…
  pubmed Deng J, Zhao J, Zhu W, Li Y 等 2026 Jul 31 置信度 0.82
• Fumarate and fumarate hydratase: an immunometabolite regulator of inflammation and diseases.
  Once regarded solely as an intermediate of the tricarboxylic acid (TCA) cycle involved in energy production, fumarate has now emerged as a pivotal immunometabolite with far-reaching effects on inflammatory signaling and immune cell fate. This review comprehens…
  pubmed Jiang Z, Zhong Y, He Z, He Z 等 2026 置信度 0.82
• Orchestrated multi agents sustain accuracy under clinical-scale workloads compared to a single agent.
  We tested state-of-the-art LLMs under clinical-scale workloads using two designs: a single agent handling all tasks and a multi-agent orchestrator assigning each task to a dedicated worker. Across retrieval, extraction, and dosing tasks, batch sizes ranged fro…
  pubmed Klang E, Omar M, Raut G, Agbareia R 等 2026 Mar 9 置信度 0.82
• Host genotype modulates melatonin-associated drought resilience in citrus accompanied by rhizosphere microbiome restructuring.
  Exogenous melatonin (MT) has emerged as a potent biostimulant for mitigating plant drought stress; however, whether its efficacy depends on the host genetic background to orchestrate rhizosphere microbiome assembly remains unclear. Here, we integrated plant ph…
  pubmed Teng Y, Zhu K, Fang K, Verma KK 等 2026 Jul 28 置信度 0.82
• Hierarchically Micro-Nano Porous Electrospun PBLG Mineralized Scaffolds: A Biomimetic Triune Platform Orchestrating Angio-Osteogenic Activation and Osteoclastogenic Inhibition.
  The natural bone matrix is a heterogeneous three-dimensional mineralized fiber network structure composed of inorganic components (mainly hydroxyapatite) and organic components (collagen-І), endowing natural bone with excellent biological and mechanical …
  pubmed Wang B, Du J, Xu Z, Yin J 等 2026 Jul 29 置信度 0.82
• From exhaustion to functional cure: frontiers in reversing HBV-specific T-cell immunity.
  Chronic hepatitis B (CHB) remains a leading cause of liver-related morbidity and mortality, affecting approximately 254 million people worldwide and accounting for more than 800,000 deaths annually. Although nucleos(t)ide analogues (NAs) durably suppress viral…
  pubmed Liang L, Xie X, He S, Zhou L 等 2026 置信度 0.82
• OpenAI single-agent LLM architecture reduces computational overhead relative to multi-agent orchestration in a simulated mars rover decision-support benchmark.
  Mars rover missions require decision-support systems that can interpret terrain, telemetry, environmental conditions, and mission objectives under delayed communication with Earth. This study evaluates whether multi-agent orchestration improves simulated Mars …
  pubmed Sanabria D 2026 置信度 0.82
• Large Language Models in Sensor-Driven Control Systems: Architectures, Challenges, and Opportunities.
  Large language models (LLMs) are increasingly being explored for integration into sensor-driven control systems across robotics, industrial automation, energy infrastructure, healthcare, smart environments, and other sensor-rich domains. This review synthesize…
  pubmed Aghaee F, Shaker HR 2026 Jul 9 置信度 0.82
• Cancer-Associated Fibroblast Heterogeneity and Extracellular Matrix Remodeling as Orchestrators of Drug Resistance in Upper Gastrointestinal Cancers: Insights from Spatial Multi-Omics and Therapeutic Implications.
  Upper gastrointestinal (GI) cancers, including esophageal, gastric, and pancreatic cancers, remain among the most lethal malignancies worldwide, mainly because they resist nearly every therapeutic modality, from platinum-based chemotherapy, and anti-HER2 and a…
  pubmed Mirzabeigi Y, Youssef J, Gonzalez J, Martinez T 等 2026 Jul 22 置信度 0.82
• Mitochondrial and Epigenetic Drivers of Skeletal Muscle Dysfunction in Chronic Obstructive Pulmonary Disease.
  Skeletal muscle dysfunction (SMD) is a critical extrapulmonary comorbidity in chronic obstructive pulmonary disease (COPD), contributing to exercise intolerance, poor quality of life, and increased mortality. Building upon and extending the disuse model, this …
  pubmed Gao Q, Mao Y, Xie S, Wang W 等 2026 Jul 2 置信度 0.82
• Metabolic Reprogramming Associated with Ferroptosis Protection by an Indole-Based Antioxidant in Aβ(25-35)-Treated SH-SY5Y Cells.
  Ferroptosis has emerged as a critical mechanism linking iron dysregulation, oxidative stress, and neurodegeneration in amyloid-associated pathologies. Building on our previous work, which identified compound 20 as a promising antioxidant and neuroprotective ag…
  pubmed Vietri M, Napolitano E, Miranda MR, Marino C 等 2026 Jun 26 置信度 0.82
• Adaptive Digital Marketing: A Systematic Review of Bio-Inspired Reinforcement Learning, Multi-Agent Systems, and Agentic AI for Intelligent Optimisation.
  Digital marketing increasingly functions as a complex adaptive system characterised by non-stationary environments, strategic interaction, and multi-agent competition. Programmatic advertising exemplifies this complexity, where decisions must be made in real t…
  pubmed Adhikari TN, Sayers W, Zhang S 2026 Jul 8 置信度 0.82
• Redox-regulated cell death in gastric cancer: Molecular insights and therapeutic opportunities.
  Oxidative stress, resulting from the disruption of redox homeostasis, is increasingly recognized as a central driver of gastric cancer pathogenesis and a critical determinant of cell fate. An imbalance between reactive oxygen species (ROS) production and cellu…
  pubmed Qi H, Cao C, Li W, Zhu W 等 2026 Jul 25 置信度 0.82
• Breaking immune exclusion in cold tumors via TGF-β pathway inhibition.
  Immune exclusion in cold tumors is a major mechanism of immunotherapy resistance, and TGF-β signaling acts as a key orchestrator of this process. The clinical development of TGF-β/PD-(L)1 dual-targeting agents has seen both setbacks and breakthroug…
  pubmed Zhang M, Sun Y, Chen L, Xue D 等 2026 Jul 29 置信度 0.82
• Autophagy as a multi-scale architect of fungal development and pathogenicity: membrane dynamics, multilayer regulation, and cell wall integrity crosstalk.
  Autophagy is a conserved membrane-trafficking pathway traditionally viewed as a nonspecific nutrient recycling mechanism. However, recent advances across diverse fungal systems, from plant pathogens to human opportunistic fungi and entomopathogenic species, ha…
  pubmed Wang F, Li J, Chen H, Zheng Q 等 2026 置信度 0.82
• Agent-initiated socio-technical reconfiguration: a three-level taxonomy of autonomous AI governance and its recursive challenges.
  Autonomous AI agents are increasingly embedded in organizational workflows, operating as active participants within socio-technical systems. Drawing on Socio-Technical Systems (STS) theory, this paper introduces agent-initiated socio-technical reconfiguration.…
  pubmed Lahiri R 2026 置信度 0.82
• RAD51 in Breast Cancer: From Vulnerability to Resistance.
  Homologous recombination deficiency (HRD) has transformed the therapeutic landscape of breast cancer through the clinical success of poly(ADP-ribose) polymerase (PARP) inhibitors and platinum-based chemotherapy. Central to this vulnerability is radiation sensi…
  pubmed Anjum RS, Takabe K 2026 Aug 置信度 0.82
• Yiyi Fuzi Baijiang formula protects against DSS-induced colitis by orchestrating the gut barrier-microbiota-metabolism axis.
  Inflammatory bowel disease (IBD) is a relapsing inflammatory disorder of the gastrointestinal tract with increasing global incidence. Current therapies are often limited by side effects, loss of efficacy, and high cost, underscoring the need for safer and more…
  pubmed Bao Y, Ao Q, Wang M, Mao X 等 2026 Jul 23 置信度 0.82
• ASO Author Reflections: Artificial Intelligence Based Multi-Agent Oncology Care Orchestration.
  pubmed Park KU 2026 Jul 22 置信度 0.82
• 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…
  pubmed Hacıefendioğlu K, Aslan T, Başağa HB 2026 Jul 21 置信度 0.82
• Reprogramming tumor angiogenesis in breast cancer: Mechanisms, challenges, and future directions.
  Angiogenesis serves as a central hallmark of breast cancer progression by driving the formation of a dysfunctional vascular network that sustains tumor growth, enables metabolic adaptation, and facilitates metastasis. Hypoxia within the tumor microenvironment …
  pubmed Mishra B, Saha S, Kumari K, Mahapatra S 等 2026 Jul 14 置信度 0.82
• Leveraging Kinesin Family as Key Regulators of Malignant Progression and the Immunometabolic Niche for Precision Oncology.
  Malignant tumors impose a substantial burden on global health, with an urgent unmet need for effective targets to advance precision therapy. As evolutionarily conserved microtubule motor proteins, the kinesin family (KIF) orchestrates fundamental cellular proc…
  pubmed Li L, Li J, Zhao X, Zhang H 等 2026 Jan-Dec 置信度 0.82
• Evidence-to-decision: From exposome data to evidence to action through agentic AI.
  Public health decisions are uniquely difficult, weighing population benefits against harms, equity, resource constraints, and feasibility, often under deep uncertainty. The GRADE Evidence-to- Decision (EtD) framework, rooted in evidence-based medicine, offers …
  pubmed Hartung T 2026 置信度 0.82
• Copper-Catalyzed Cascades Enable Fused Pyrroles with Tunable Ring Sizes.
  A novel route for the preparation of fused pyrroles with tunable ring sizes is presented as a copper-catalyzed tandem [3+2] cyclization/Ullmann coupling. This protocol established a versatile and general platform for the controllable synthesis of fused pyrrole…
  pubmed Shan Y, Lv D, Wu C, Li J 等 2026 Jul 31 置信度 0.82