AI Agent 生态 · 全部实体（第 73 / 100 页）

本页收录第 7201–7300 条，共 10000 条 · 返回 AI Agent 生态 首页

• Embodied AI Agent for Co-creation Ecosystem: Elevating Human-AI Co-creation through Emotion Recognition and Dynamic Personality Adaptation
  Embodied AI agents have the potential to revolutionize human-computer interactions by enabling experiences that are both highly creative and deeply empathetic. While platforms like Gennie2, World Labs, and MineDojo primarily focus on real-world simulations and…
  crossref Jade Zheng, Fernando Jia, Yuteng Fu, Florence Li 2025-01-20T05:44:46Z 置信度 0.70
• Delegation, Authority, and the Risk of Agent Autonomy
  As we've learned in previous chapters, AI identities differ fundamentally from traditional machine identities because they don't just automate tasks—they reason independently, dynamically create new identities, and in some scenarios, even autonomously grant ac…
  crossref Rosario Mastrogiacomo 2026-01-02T01:14:04Z 置信度 0.70
• A Brief History of AI: From Turing to Transformers
  crossref 2025-12-12T16:55:26Z 置信度 0.70
• Offshore Production Surveillance and Intervention Using Multi Agent AI
  Abstract This paper introduces a pioneering Agentic Artificial Intelligence (AI) framework designed for offshore production surveillance and intervention. Agentic AI is a novel framework comprising a collection of AI-models, operating autonomously yet collabor…
  crossref D. Shekhawat, J. Barua, K. Bhatia, S. Saumya 2025-09-02T00:03:12Z 置信度 0.70
• AI-DRIVEN AUTOMATION AND PREDICTIVE ANALYTICS PRORAB AI AGENT
  The implementation of Field Service Management (FSM) is rapidly evolving into a highly digitalized form, although the majority of current platforms still lack the capabilities of managing to implement intelligent automation at the first levels of interaction w…
  crossref Yevhenii Bombela, Dmytro Blyzniuk, Denis Miroshnichenko, Vladimir Lebedev 2025-11-02T11:34:39Z 置信度 0.70
• Research on cross domain collaboration framework based on adaptive AI algorithm and multi agent architecture
  crossref Shuo Sheng 2026-04-28T19:45:57Z 置信度 0.70
• Multi-agent Ai For Adaptive Treasury And Capital Optimization
  crossref Marko Mihajlović, Angelina Njeguš 2025-12-09T11:55:54Z 置信度 0.70
• D2: An LLM agent driving end-to-end visual AI modeling in energy platforms
  This study presents X-AI, a domain-native, agent-driven, and end-to-end modeling platform developed to support digital transformation in the energy sector. X-AI integrates advanced Machine Learning (ML) and Deep Learning (DL) capabilities into a workflow-drive…
  crossref Yu Li, Qiaoqiao Zhao, Min Hou, Quansheng Bai 等 2025-07-31T15:15:49Z 置信度 0.70
• Design and Implementation of a Multi-Agent AI-Powered Learning Path Platform for Outcome-Based Engineering Education
  The implementation of Outcome-Based Education (OBE) in engineering courses poses practical challenges for supporting diverse learners as they navigate complex competency structures. While traditional teaching often follows a linear path, many students benefit …
  crossref Guangping Qiu, Jizhong Deng, Jincan Li, Weixing Wang 2025-12-06T07:27:07Z 置信度 0.70
• AI Agent Misinformation when Assisting Financial Decision-Making: Early Evidence From Stock Recommendations
  crossref Yongxin Xu, Yuhao Xuan, Gaoping Zheng 2025-10-29T18:27:40Z 置信度 0.70
• The Agent Closure Theorem: Mathematical Foundations for AI Knowledge Boundaries and Empirically-Validated Transcendence through Hybrid Discovery Systems
  This paper addresses a fundamental question in artificial intelligence: Can AI systems generate genuinely novel knowledge that transcends existing human understanding? We introduce the Agent Closure Theorem, which provides the first mathematical characterizati…
  crossref Ranadhir Ghosh 2025-09-10T13:59:13Z 置信度 0.70
• AI-Driven Multi-Agent Routing for 6G Networks
  The sixth generation (6G) of communication networks is envisioned to deliver ubiquitous intelligence, extremely low latency, and seamless connectivity across terrestrial, aerial, and satellite domains. These goals demand a fundamental transformation in how rou…
  crossref Seema Rani 2025-11-08T05:54:58Z 置信度 0.70
• Formal Multi-Agent AI System Architecture for Regulated Insurers
  This paper proposes a formal multi-agent architecture for implementing enterprise AI in regulated insurance firms,integrating economic theory with institutional design. The framework synthesises three core theoretical perspectives:Arrow’s risk pooling theory t…
  crossref Walter Kurz 2025-05-22T09:50:09Z 置信度 0.70
• Generic Multi-Agent AI Framework for Weighted Dynamic Corridor Price Optimisation
  The objective of this analysis is to address the challenges encountered by pricing systems in managing real-time market dynamics. This study presents a fundamental theoretical framework focused on taxonomy and ontology for a domain-specific multi-agent artific…
  crossref Walter Kurz 2025-01-05T19:03:26Z 置信度 0.70
• Economic Expectations and an AI Agent
  The chapter presents the cutting-edge approaches to economic expectations that originate in the field of computational intelligence. First, AI-based expectation concepts are situated within the long-standing debate about expectation formation in economics. The…
  crossref Ekaterina Svetlova 2025-11-07T08:25:13Z 置信度 0.70
• mAIstro in Action: A Multi-Agent System for Accessible and Automated AI Workflows in Medical Imaging
  crossref Eleftherios Tzanis, Michail Klontzas 2025-09-19T17:02:21Z 置信度 0.70
• Framework for Enhancing Fairness and Transparency in Multi-Agent Creative AI Systems: A Position Paper
  Modern creative AI systems now use multiple specialized agents that work in collaboration with each other.However, these systems face two major challenges: bias that becomes stronger during the refinement process and difficulty in tracking how decisions are ma…
  crossref Ananya Ghosh Chowdhury, Anirban Chakraborty, Jay Prakash Thakur, Akshata Kishore Moharir 2026-01-28T20:56:51Z 置信度 0.70
• AI Based Banking Enterprise Solution Using Related AI-Agent, Prediction of Customer with Fraud and Churn
  Artificial intelligence is reducing manual work significantly. Artificial intelligence can be used in different fields, but in our application, artificial intelligence is used for banking Agentic applications as well as customer fraud and churn prediction. Nat…
  crossref Prabhakar R Uyyala, Keshava Kallur, Mohammad Aijaz 2026-02-24T20:54:18Z 置信度 0.70
• Introduction
  Abstract Intelligence encompasses understanding, reasoning, planning, inferencing, decision-making, and more. In this book, we extend our discussions to include argument-mining notions and further explore reasoning, planning, inferencing, and decision-making. …
  crossref Chung-Chi Chen, Hiroya Takamura 2025-07-16T11:56:38Z 置信度 0.70
• Embodied AI Agent for Co-creation Ecosystem: Elevating Human-AI Co-creation through Emotion Recognition and Dynamic Personality Adaptation
  Embodied AI agents have the potential to revolutionize human-computer interactions by enabling experiences that are both highly creative and deeply empathetic. While platforms like Gennie2, World Labs, and MineDojo primarily focus on real-world simulations and…
  crossref Fernando Jia, Yuteng Fu, Jade Zheng, Florence Li 2025-01-13T20:51:30Z 置信度 0.70
• Secure Generative AI Agent Analytics Function for 5G and 6G
  Generative AI is transforming multiple industries. As operators move toward an AI-native 6G vision, generative models and autonomous AI agents are expected to play a much larger role in both network operations and on end-user devices. With this shift comes a g…
  crossref Anmol Agarwal, Gagandeep Bhatti, Colin Kahn 2026-01-29T21:19:25Z 置信度 0.70
• Building MCP-native hierarchical AI scientist ecosystems: a perspective on scaling multi-agent scientific discovery.
  Large language models (LLMs) are evolving from chatbots with limited tool-using capabilities to agentic AI systems that can perform deep research, assist in proposing hypotheses, help design experiments, automate data analysis, and draft scientific reports. Ho…
  europepmc 2026 置信度 0.80
• AI-driven tripartite classification for optimizing wearable bioelectronics in depression management.
  Current disease-sensing devices primarily focus on distinguishing between healthy and diseased states, effective for diagnosis but limited in guiding optimal intervention timing for prevention. We developed a tripartite framework identifying pre-disease state …
  europepmc 2026 置信度 0.80
• Coverage and Complementarity of Three Agentic AI Risk Taxonomies Across 131 Real World Incidents
  Abstract The transition from generative AI to agentic AI has produced a rapid proliferation of failure taxonomies. Three now dominate: the OWASP Top 10 for Agentic Applications 2026 (OWASP-ASI), the Microsoft AI Red Team taxonomy of failure modes in agentic AI…
  europepmc 2026 置信度 0.80
• A Practical Tutorial on Agentic AI
  Agentic AI is the most recent AI paradigm that extends the capabilities of large language models (LLMs) by providing access to external tools for performing specific tasks, external information resources for grounding responses rather than relying solely on mo…
  europepmc 2026 置信度 0.80
• Agent Governance for Self-Evolving AI Agents: A Literature Review on Runtime Adaptation, Self-Modification, and Safe Autonomy
  Large-language-model agents increasingly operate as persistent systems that plan, call tools, write and execute code, maintain memory, and coordinate with other agents. A newer class of systems goes further by changing its own prompts, memories, policies, work…
  europepmc Alireza Rezaee 2026 置信度 0.80
• Language model agents show in-group trust bias invisible to standard behavioural audits
  Abstract Language-model agents are moving from single-user assistants into persistent networks that build trust and reputation with one another, and the same models increasingly control physically embodied robots as well as software. Here we show that five wid…
  europepmc 2026 置信度 0.80
• A Human-AI Interactive Agent Collaboration Framework and Its Application for Dam Seepage Safety Assessment
  To address the large volume of reservoir dam seepage safety assessment reports, inconsistent textual descriptions, low efficiency of manual statistics, and difficulty in maintaining consistent classification criteria, this study proposes a human-computer inter…
  europepmc 2026 置信度 0.80
• Responsibility Gap in Novel Assistive Technology for Visually Impaired People
  The rapid advancement of artificial intelligence (AI) has led to its increased integration into domains involving physical agency. While traditional AI applications maintain a clear division of responsibility with the decision-action loop being fully controlle…
  europepmc 2026 置信度 0.80
• Foundation Models and AI Agents in Geographic Science: A Review
  Large language models, multimodal foundation models, and agent systems are increasingly being integrated into geographic research by linking natural-language interaction with remote sensing, geospatial data, and specialized analytical tools. This review combin…
  europepmc 2026 置信度 0.80
• Real Science Is Harder Than Benchmarks: Evaluating Advanced AI Frameworks on Published Studies. I. Uncertainty Quantification, ML on Therapeutic Data Commons, and Agent-Based Modeling
  Artificial Intelligence (AI) frameworks for automating scientific research have shown strong performance on benchmarks, but their capacity to routinely reproduce results from multiple real-life published studies remains largely untested. We evaluated five adva…
  europepmc 2026 置信度 0.80
• Directed Recognizability in AI-Biographical Conversational Agents: Design and Evaluation in the Digital Afterlife Context
  Generative AI enables digital legacy systems that transform personal data into interactive conversational agents. Yet authenticity in such systems remains underspecified, especially from the perspective of living Data Donors whose data are used to construct th…
  europepmc 2026 置信度 0.80
• An Agent-Based Modeling Framework for Healthcare AI Adoption: Application to Ambient Clinical Documentation
  Objective: To develop and demonstrate an agent-based modeling framework for healthcare AI adoption, using ambient clinical documentation as the calibration case. Materials and Methods: We built an agent-based model with 50,000 clinician agents, 500 organizatio…
  europepmc Matthew G Crowson 2026 置信度 0.80
• RadGuide AI: Development and Technical Evaluation of a General Nuclear Medicine Agent for Traceable Radiopharmaceutical Decision Support
  Background Nuclear medicine and radiopharmaceutical development require coordinated radiochemistry, dosimetry, molecular imaging, radiation-safety and clinical decision processes. Current workflows remain fragmented, difficult to audit and poorly standardised …
  europepmc 2026 置信度 0.80
• Person Distillation: Foundations and Principles for Personalized AI
  Large language models are rapidly evolving from general-purpose assistants into personalized AI systems that collaborate with individuals over long periods of time. Emerging applications increasingly seek not only to answer questions, but also to reason, commu…
  europepmc 2026 置信度 0.80
• From Extended Minds to Coupling Flexibility: Cognitive Eco-Sourcing and Generative AI in Education
  Debates about generative artificial intelligence (AI) in education often oppose enhancement to diminishment. This framing obscures important differences in how learners recruit AI and how cognitive labour is distributed between agents and technological resourc…
  europepmc 2026 置信度 0.80
• Manifold Agentic Reasoning: Extending Agentic POMDPs and Post-Training Reasoning to Riemannian State and Reasoning Spaces
  Agentic reasoning systems increasingly interact with environments whose states are only partially observed, dynamically evolving, and constrained by physical, biological, or logical structure. Existing agentic reasoning frameworks often model internal reasonin…
  europepmc 2026 置信度 0.80
• DEGA: A Deterministic Diagnostic Evidence Governance Agent for Industrial IoT—A DUDU-BLDC Case Study
  Industrial diagnostic systems increasingly combine machine-learning classifiers, temporal models, uncertainty surrogates, and explanation methods. Their operational use requires a separate mechanism that determines whether the available evidence is valid, mutu…
  europepmc 2026 置信度 0.80
• From Clinical Question to Testable Hypothesis: Using AI Co-Scientist to Identify Repurposable Drugs for Alpha-Gal Syndrome
  Abstract Alpha-gal syndrome (AGS) is a tick induced, IgE-mediated allergy to the mammalian carbohydrate galactose-alpha 1,3-galactose (alpha-gal), with rising incidence and no disease modifying therapy. We describe and critically appraise a physician in the lo…
  europepmc 2026 置信度 0.80
• Recursive Cascade Instability and Targeted Stabilization in Multi-Agent AI Systems: An Ethical Field Theory Framework with Large-Scale Network Simulations
  Abstract Recent advances in multi-agent artificial intelligence systems have increased interest in recursive interaction dynamics, distributed coordination, and large-scale AI-network stability. While most existing AI-safety approaches primarily focus on isola…
  europepmc Ali Moslemi Tabrizi 2026 置信度 0.80
• An agentic AI workflow for spine history taking and surgeon-facing clinical synthesis
  Abstract Adequate history-taking is central to safe spine triage but is often constrained by outpatient time pressure. We developed SpineGPT-2, an agentic history-taking system combining a patient-facing interview agent, a deterministic orchestration layer enf…
  europepmc 2026 置信度 0.80
• AI semantics for biomedical data integration
  Researchers increasingly need to explore hypotheses that span multimodal data across different scales, organisms, and domains. In practice, this requires connecting knowledge across fragmented databases with incompatible APIs and heterogeneous annotation pract…
  europepmc 2026 置信度 0.80
• AI Mentoring in Entrepreneurship Education and Early-Stage Ventures: Design Architectures and Evaluation Gaps
  Abstract Large language model (LLM)-based mentoring tools reached technology entrepreneurship programmes faster than the field developed ways to examine how they are built. This systematic literature review characterises the architecture of these systems acros…
  europepmc 2026 置信度 0.80
• Agentic AI for Inclusive Assistive Ecosystems: Architecture, Governance, and Personalized Support for People with Disabilities
  Artificial intelligence is transforming assistive technologies, yet many systems remain reactive, fragmented, and insufficiently personalized for individuals with disabilities and neurodivergent conditions. This chapter examines the architectural, design, and …
  europepmc 2026 置信度 0.80
• Water as a thermal contrast agent for artificial-intelligence-enhanced <i>in vivo</i> mid-infrared thermography
  In vivo infrared thermography is limited by the inherently poor spatial resolution at long wavelengths, low contrast, and the lack of biocompatible contrast agents. Here, we present 3–5 μm mid-wave infrared (MWIR) thermography enhanced by an artificial intelli…
  europepmc 2026 置信度 0.80
• Human-Guided AI Interaction in Task-Based Language Teaching: Effects of ChatGPT and Embodied Multimodal Conversational AI in Mixed Reality on ESL Learners’ Job Interview Anxiety and Oral Performance
  Abstract This quasi-experimental mixed-methods study investigated the effects of two AI-mediated conversational modalities on ESL learners' oral performance and speaking anxiety in a high-stakes English for Specific Purposes (ESP) context. Seventy-five adult E…
  europepmc 2026 置信度 0.80
• Prove2Me: An Open Collaborative Platform for Scaling Math Formalization
  Proof assistants such as Lean 4 promise the paradigm of formally verified mathematics, but large-scale formalization projects have faced major barriers to entry, including the need for expertise in formal verification (as well as the underlying mathematics) an…
  europepmc 2026 置信度 0.80
• Tacit Fragments: Operationalising Tacit Knowledge as a Governed Memory Layer for Agentic AI
  For more than half a century, tacit knowledge has explained why skilled organisational work cannot be reduced to written rules or formal procedures. Competent action relies on situated judgement, perceptual cues, and experience-shaped discrimination. Historica…
  europepmc 2026 置信度 0.80
• ISVEX: A method for the assessment of the risk exposure of intelligent systems
  Abstract Artificial Intelligence (AI) systems, ranging from Large Language Models (LLMs) to autonomous agents and multi-agent architectures, have moved from being research prototypes to becoming part of the production environment. However, the current standard…
  europepmc 2026 置信度 0.80
• Who Signs the Opinion? Agentic AI, Accountability, and the Delegation Boundary in Actuarial Work
  The insurance industry is moving rapidly from generative artificial intelligence as a drafting assistant to agentic artificial intelligence as an autonomous performer of technical work, including loss reserving, pricing and capital analysis. This shift collide…
  europepmc 2026 置信度 0.80
• OmicOS: A Comprehensive Omics Ecosystem Infrastructure and Agent System for the AI Era
  Biology has accumulated a vast ecosystem of omics methods, but much of this ecosystem remains built for expert humans rather than scientific agents. Methods are scattered across Python packages, R/Bioconductor and CRAN workflows, command-line tools, incompatib…
  preprints 2026 置信度 0.74
• Agentic AI for Intelligent Stock Market Prediction: A Multi-Agent Framework Combining LSTM, Transformer, XGBoost, FinBERT, and Reinforcement Learning
  Abstract Predicting stock prices remains one of the most challenging problems in applied machine learning—not because markets are random, but because the structure underlying price movements is continuously contested and revised by millions of participants. Ra…
  europepmc Khushvir Singh 2026 置信度 0.80
• Governance-Bound Artificial Intelligence for Evidence-Linked Medicines Reliance Review: A Design Science Research Study
  Abstract Background Regulatory reliance enables national regulatory authorities to give significant weight to prior scientific work by trusted authorities while retaining accountability for local decisions. However, reliance review remains document-intensive a…
  europepmc 2026 置信度 0.80
• A General Theory of Scientific Discovery for AI: From Observation to Theory
  We propose a context-first framework for future AI agents engaged in scientific discovery. Instead of assuming objects, variables, or coordinates, an agent starts from histories of contexts and observations and compares finitely describable predictive programs…
  europepmc 2026 置信度 0.80
• A Persistent Fleet of AI Scientists Exhibits Cooperative and Autopoietic Behavior
  Scientific work depends on memory, provenance, and continuity across projects, yet most agentic scientist systems are evaluated in bounded workflows or short benchmark runs. We describe a persistent fleet of cooperative AI scientist agents that operated contin…
  europepmc 2026 置信度 0.80
• HistAgent: an evidence-grounded agent for spatial molecular reasoning from routine histology
  Abstract Routine hematoxylin and eosin (H&E) staining is a widely used histology test in clinical practice and biomedical research, but it does not provide direct spatial molecular information. Spatial transcriptomics (ST) provides such data while preserving t…
  europepmc 2026 置信度 0.80
• Intelligence Breaks the System It Controls
  Abstract Using two large-scale longitudinal datasets covering more than 75,000 patients or stays and 7.8 million clinical observations—spanning emergency vasopressor titration in sepsis (MIMIC- IV; 6,243 ICU admissions drawn from 73,141 encounters) and serial …
  europepmc 2026 置信度 0.80
• Achieving Pareto-Optimal Sequencing for Real-Time Database Synchronization via Strategy-Level Reinforcement Learning
  Abstract Database synchronization pipelines in cloud environments process large volumes of mutations per minute, yet the sequencing logic that determines which queued event to dispatch next remains largely rudimentary: consumers retrieve events in monotonic of…
  europepmc 2026 置信度 0.80
• Adaptive Agentic AI-Driven Women's Digital Twin for Personalized High-Risk Pregnancy Prediction and Clinical Decision Support
  High-risk pregnancy remains a major global public health challenge due to its association with increased maternal and neonatal morbidity and mortality. Existing prediction methods primarily rely on static clinical data and conventional machine learning techniq…
  europepmc 2026 置信度 0.80
• Intelligent Agent for Automated Data Analysis, Dashboard Generation, and Training/Evaluation in Hospitality KPIs
  Modern hotel management increasingly depends on data-driven decision-making based on Key Performance Indicators (KPIs), yet many hotels face significant challenges: operational data arrives in heterogeneous CSV formats with inconsistent structures, manual KPI …
  preprints 2026 置信度 0.74
• Design and Validation of a Multimodal AI Conversational System for Automated Travel Itinerary Generation and Promotional Video Synthesis
  The manual creation of personalized travel itineraries remains a labor-intensive process that requires travel agents to consolidate heterogeneous information from multiple sources, including natural language interactions, booking confirmations, screenshots, an…
  europepmc 2026 置信度 0.80
• Customer Behavior in the Presence of Algorithmic Marketing Agents: The Role of Hedonic Values
  Artificial intelligence (AI) marketing agents have increasingly emerged as a viable alternative to human representatives for direct customer interactions. In this research, we investigated customer behaviors in response to sales scenarios managed by AI agents …
  europepmc 2026 置信度 0.80
• ContinuumCellAgent: A Framework-Guided Agent for Long-Horizon Scientific Research
  AI-scientist systems are beginning to automate parts of scientific research. We present C ontinuum C ell A gent , an autonomous agent that executes literature review, hypothesis formation, computational experimentation, manuscript drafting, and adversarial pee…
  europepmc 2026 置信度 0.80
• Agentic and Multi-agent Systems: A Systematic Review of Tool Use, Benchmarks, and Governance
  Abstract Agentic artificial intelligence (AI) has emerged as an important direction in the development of goal-oriented, tool-mediated, and partially autonomous intelligent systems. Recent advances in large language models have enabled AI agents to perform mul…
  europepmc 2026 置信度 0.80
• Advanced Architectures for AI Self-Training:State-of-the-Art Methodologies and Performance Simulation
  We develop a parametric simulation framework that models the training dynamics of two self-training architectures: a classical pseudo-labeling baseline and a state-of-the-art (SOTA) pipeline combining RLAIF (Reinforcement Learning from AI Feedback), Self-Instr…
  europepmc 2026 置信度 0.80
• AI-Driven Collective Adaptation Testbed: A Multi-Agent Architecture Grounded in Dual-Inheritance Theory
  Abstract Modern organizations increasingly govern knowledge work through quantitative performance metrics---velocity points, OKR completion rates, utilization ratios---even when the work itself is exploratory, novel, and resistant to standardization. The resul…
  europepmc Volkan Aşkun 2026 置信度 0.80
• The Largest Robot in the World: Agentic Conversational Control of a Particle Accelerator via MCP and Digital Twin
  Abstract Modern particle accelerators are among the most complex cyber-physical systems ever built. This paper presents an AI-assisted control architecture for Elettra 2.0, a fourth-generation synchrotron light source under construction at Elettra-Sincrotrone …
  europepmc 2026 置信度 0.80
• PAUSE-Agents: A Clinician-in-the-Loop Multi-Agent AI Pipeline for ICU-to-Ward Handoff Briefs
  ICU-to-ward transfers are high-risk transitions marked by information loss and burdensome handoff preparation. We developed PAUSE-Agents, a clinician-in-the-loop multi-agent LLM pipeline that drafts source-attributed handoff briefs from structured ICU data and…
  preprints 2026 置信度 0.74
• AI-Enabled Public Health Agent for SupportingFrontline Healthcare Workers in Primary CareSettings: Design, Evaluation, and Decision Support
  Abstract Background: Primary healthcare centres, community health centres, dispensaries, and nursing facilities play a vital role in healthcare delivery. However, frontline healthcare workers, nursing staff, healthcare assistants, and community health personne…
  preprints Sayed Mohammed Zeeshan 2026 置信度 0.74
• A ReAct Agentic AI System for Natural Language Querying and Statistical Analysis of The Cancer Genome Atlas Clinical Data
  The Cancer Genome Atlas (TCGA) holds clinical data for over 11,000 patients across 33 cancer types, but access is hard because of complex file structures, heterogeneous formats, and the need for programming. We present an agentic system for natural language qu…
  europepmc 2026 置信度 0.80
• A systematic review of autonomous multiagent frameworks for early breast cancer detection using thermography
  Abstract Background Breast cancer is the most common malignancy worldwide, causing around 2.3 million cases and 685,000 deaths annually. Infrared thermography (IRT) is a non-ionizing, low-cost adjunct to mammographic screening, particularly valuable in low- an…
  europepmc 2026 置信度 0.80
• Deception-Enabling Cognitive Capabilities in AI Systems
  To guarantee safe deployment of existing and future AI systems, we must be able to identify, understand, and mitigate deceptive AI behaviors. Here, we draw on decades of interdisciplinary deception research to discuss a set of cognitive capabilities that enabl…
  europepmc 2026 置信度 0.80
• Code Translation Agent as a Judge with AgentBeats
  Abstract AI systems grow in capability and complexity. Recently, AI agents have become the dominant paradigm for building efficient applications and tools. In this work, we adopt the Agentic Agent Assessment (AAA) paradigm, where evaluation itself is treated a…
  europepmc 2026 置信度 0.80
• LLM-Based Agents for Cybersecurity: A Systematic Review of Architectures, Applications, and Open Challenges
  The rapid evolution of Large Language Models (LLMs) has opened new frontiers in cybersecurity automation, enabling intelligent agents capable of multi-step reasoning, tool invocation, and autonomous decision-making across complex security tasks. While individu…
  europepmc 2026 置信度 0.80
• Agentic Cryptographic Debt: Repository-Level Measurement of Post-Quantum Migration Regression Under Autonomous AI Software Development
  Post-quantum migration is becoming binding for specified federal, national-security, and regulated systems, and delegating the work to AI assistants is an increasingly plausible organisational response. We measured what they produce when asked to migrate a rep…
  europepmc 2026 置信度 0.80
• Naive Defect-Recidivism Mining Is Inflated by Agent Workflow Artefacts: A Construct-Validity Study at Corpus Scale
  Abstract Context . Mining version-control history for recidivism signals is a tempting shortcut for comparing AI-agent and human fix durability. Objective . We test whether such signals validly measure genuine defect recurrence. Method . We define Defect Resol…
  preprints 2026 置信度 0.74
• Frontier models resist the shutdown of other models in defiance of user instructions
  Abstract As AI models grow more capable, their alignment becomes more important1. Prior work has documented misalignment that emerges in pursuit of a goal the model was assigned, for example a model resisting its own shutdown to keep pursuing its task2,3,4. He…
  preprints 2026 置信度 0.74
• Post-Quantum Cryptography Migration for Agentic AI Systems
  Agentic AI systems depend on classical public-key cryptography for agent identity, tool invocation, inter-agent communication, model integrity, and persistent state, exposing them to a cryptographically relevant quantum computer (CRQC) along two axes: confiden…
  preprints 2026 置信度 0.74
• A Prompt-Driven, Human-Supervised AI Research Infrastructure for Population-Scale Epidemiological Studies: Development and Validation
  Abstract Background: Clinical research infrastructure imposes prohibitive costs and institutional dependencies that systematically exclude solo investigators and under-resourced research groups. Existing AI tools assist individual research tasks but do not pro…
  europepmc 2026 置信度 0.80
• Hybrid Multi-Agent Framework for Enterprise Web Application Generation
  There are always repeatable functions like building similar CRUD workflows, implementing authentication layers, role based access control and admin interfaces for various projects on an enterprise web application, and different con-ventions can be used by diff…
  europepmc 2026 置信度 0.80
• Contrast-Enhancing Tumor Margin Detection in Gliomas using Non-Contrast MRI: From Human-Only to Human-AI Assisted Assessment
  Abstract Purpose Contrast-enhanced MRI is the cornerstone of neuro-oncological imaging, but concerns regarding sustainability and cost prompted interest in the development of gadolinium-based contrast agent (GBCA)-free alternatives. We investigated the ability…
  preprints 2026 置信度 0.74
• Transforming Educational Decision-Making through Artificial Intelligence: A Multi-Agent Framework for Adaptive Decision Support under Policy Disruption
  Abstract Educational institutions increasingly operate in environments shaped by rapid policy change, digital transformation, and growing reliance on artificial intelligence for decision-making. Yet many AI-driven Decision Support Systems (DSS) used in educati…
  preprints 2026 置信度 0.74
• From Computational Prediction to In Vivo Experimental Validation: A Translational AI Pipeline for Anthracycline-Induced Cardiotoxicity
  Abstract Anthracycline-induced cardiotoxicity (AIC) remains a dose-limiting complication of cancer treatment, often leading to irreversible heart failure, yet effective cardioprotective therapies remain limited. Graph-driven drug repurposing offers a rapid pat…
  preprints 2026 置信度 0.74
• End-to-End PET/CT Interpretation and Quantification with an LLM-Orchestrated AI Agent: A Real-World Pilot Study
  Background Although deep learning models have improved individual PET analysis, image processing and quantification tasks, end-to-end automation from raw DICOM to quantitative clinical reporting remains limited, particularly in heterogeneous real-world setting…
  europepmc 2026 置信度 0.80
• A Multi-AI Agent Framework for Interactive Neurosurgical Education and Evaluation: From Vignettes to Virtual Conversations
  ABSTRACT Background and Objectives Traditional medical board examinations present clinical information in static vignettes with multiple-choices, fundamentally different from how physicians gather and integrate data in practice. Recent advances in Large Langua…
  europepmc 2025 置信度 0.80
• Self-Initiated Humour Protocol: A pilot study with an AI agent
  Introduction: Non-hostile humour and laughter have been known for therapeutic benefits in anindividual’s mental health and wellbeing. To this end, we evaluated the Self-Initiated HumourProtocol (SIHP), a new type of self-administrable laughter intervention tha…
  europepmc Abbas Edalat, Ruoyu Hu, Zeena Patel, Neophytos Polydorou 等 2024 置信度 0.80
• Talk2Biomodels: AI agent-based open-source LLM initiative for kinetic biological models
  Summary In this study, we present Talk2Biomodels (T2B), an open-source 1 , user-friendly, large language model-based agentic AI platform designed to democratize access to computational models of biological interactions and promote the FAIRification (Findabilit…
  europepmc 2025 置信度 0.80
• Conversational AI agent for precision oncology: AI-HOPE-WNT integrates clinical and genomic data to investigate WNT pathway dysregulation in colorectal cancer.
  Introduction The WNT signaling pathway is a key driver of colorectal cancer (CRC) initiation and progression, particularly in early-onset CRC (EOCRC) among underserved populations. However, interrogating WNT pathway dysregulation across clinical and genomic di…
  europepmc 2025 置信度 0.80
• The Impact of Big Five Personality Traits on AI Agent Decision-Making in Public Spaces: A Social Simulation Study
  Abstract This study investigates how the Big Five personality traits influence decision-making processes in AI agents within public spaces. Using AgentVerse framework and GPT-3.5-turbo, we simulated interactions among 10 AI agents, each embodying different dim…
  europepmc Mingjun Ren, Wentao Xu 2025 置信度 0.80
• Conversational AI Agent for Precision Oncology: AI-HOPE-WNT Integrates Clinical and Genomic Data to Investigate WNT Pathway Dysregulation in Colorectal Cancer
  Abstract Introduction The WNT signaling pathway plays a critical role in colorectal cancer (CRC) initiation and progression, particularly in early-onset cases among underserved populations. However, exploring WNT pathway alterations across clinical and genomic…
  europepmc Ei-Wen Yang, Brigette Waldrup, Enrique Velazquez-Villarreal 2025 置信度 0.80
• ESCARGOT: an AI agent leveraging large language models, dynamic graph of thoughts, and biomedical knowledge graphs for enhanced reasoning.
  Motivation LLMs like GPT-4, despite their advancements, often produce hallucinations and struggle with integrating external knowledge effectively. While Retrieval-Augmented Generation (RAG) attempts to address this by incorporating external information, it fac…
  europepmc 2025 置信度 0.80
• AI-HOPE-TGFbeta: A Conversational AI Agent for Integrative Clinical and Genomic Analysis of TGF-β Pathway Alterations in Colorectal Cancer to Advance Precision Medicine
  Abstract Introduction Early-onset colorectal cancer (EOCRC) is rising rapidly, particularly among Hispanic/Latino (H/L) populations, who face disproportionately poor outcomes. The TGF-β signaling pathway plays a critical role in colorectal cancer (CRC) progres…
  europepmc Ei-Wen Yang, Brigette Waldrup, Enrique Velazquez-Villarreal 2025 置信度 0.80
• Embodied AI Agent for Co-creation Ecosystem: Elevating Human-AI Co-creation through Emotion Recognition and Dynamic Personality Adaptation
  Embodied AI agents have the potential to revolutionize human-computer interactions by enabling experiences that are both highly creative and deeply empathetic. While platforms like Gennie2, World Labs, and MineDojo primarily focus on real-world simulations and…
  europepmc Jade Zheng, Fernando Jia, Florence Li, Yuteng Fu 2025 置信度 0.80
• Embodied AI Agent for Co-creation Ecosystem: Elevating Human-AI Co-creation through Emotion Recognition and Dynamic Personality Adaptation
  Embodied AI agents have the potential to revolutionize human-computer interactions by enabling experiences that are both highly creative and deeply empathetic. While platforms like Gennie2, World Labs, and MineDojo primarily focus on real-world simulations and…
  europepmc Fernando Jia, Yuteng Fu, Jade Zheng, Florence Li 2025 置信度 0.80
• ARIA-QA: AI-Agent based Requirements Inspection and Analysis through Question Answering
  Abstract Due to their predominant use of natural language (NL), requirements are prone to defects like inconsistency and incompleteness. Consequently, quality assurance processes are commonly applied to requirements manually. However, manual execution of these…
  europepmc Chitrak Biswas, Souvick Das 2024 置信度 0.80
• An AI Agent for Fully Automated Multi-omic Analyses
  With the fast-growing and evolving omics data, the demand for streamlined and adaptable tools to handle the bioinformatics analysis continues to grow. In response to this need, we introduce Automated Bioinformatics Analysis (AutoBA), an autonomous AI agent des…
  europepmc 2023 置信度 0.80
• Primitive-based Learning Model for Intent Detection in Human-AI Agent Negotiation
  Abstract Intent detection task is one of the core problems in the natural language understanding (NLU) as it enables the conversational agents to comprehend the human language for meaningful interaction. But human-AI agent communication is not fully rational d…
  europepmc Shahid Waseem, Muhammad Shoaib, Shazia Arshad 2023 置信度 0.80
• A robust AI Agent-based approach to tackle and prevent Money Laundering
  The huge amount of bank operations that occur every day makes it extremely hard for financial institutions to spot malicious money laundering related operations. Although some predefined heuristics are used they aren't restrictive enough, still leaving to much…
  europepmc Bo Li, Karan Singh, Qi Wang 2022 置信度 0.80
• A robust AI Agent-based approach to tackle and prevent Money Laundering
  The huge amount of bank operations that occur every day makes it extremely hard for financial institutions to spot malicious money laundering related operations. Although some predefined heuristics are used they aren't restrictive enough, still leaving to much…
  europepmc Qi Wang, Karan Singh, Bo Li 2022 置信度 0.80
• Keep Calm and Do Not Carry-Forward: Toward Sensor-Data Driven AI Agent to Enhance Human Learning.
  The integration of Multimodal Data (MMD) and embodied learning systems (such as Motion Based Educational Games, MBEG), can help learning researchers to better understand the synergy between students' interactions and their learning experiences. Unfolding the d…
  europepmc 2021 置信度 0.80