AI Agent 生态 · 全部实体（第 80 / 100 页）

本页收录第 7901–8000 条，共 10000 条 · 返回 AI Agent 生态 首页

• Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative Models
  Recent advancements in visual generative models have enabled high-quality image and video generation, opening diverse applications. However, evaluating these models often demands sampling hundreds or thousands of images or videos, making the process computatio…
  arxiv Fan Zhang, Shulin Tian, Ziqi Huang, Yu Qiao 等 2024-12-10T18:52:39Z 置信度 0.78 cs.CVcs.AIcs.CL
• Agent-UniRAG: A Trainable Open-Source LLM Agent Framework for Unified Retrieval-Augmented Generation Systems
  This paper presents a novel approach for unified retrieval-augmented generation (RAG) systems using the recent emerging large language model (LLM) agent concept. Specifically, Agent LLM, which utilizes LLM as fundamental controllers, has become a promising app…
  arxiv Hoang Pham, Thuy-Duong Nguyen, Khac-Hoai Nam Bui 2025-05-28T16:46:31Z 置信度 0.78 cs.CLcs.AIcs.DBcs.IR
• The Observability Gap: Why Output-Level Human Feedback Fails for LLM Coding Agents
  Large language model (LLM) multi-agent coding systems typically fix agent capabilities at design time. We study an alternative setting, earned autonomy, in which a coding agent starts with zero pre-defined functions and incrementally builds a reusable function…
  arxiv Yinghao Wang, Cheng Wang 2026-03-27T19:32:18Z 置信度 0.78 cs.HC
• Adaptive LLM Agents: Toward Personalized Empathetic Care
  Current mental-health conversational systems are usually based on fixed, generic dialogue patterns. This paper proposes an adaptive framework based on large language models that aims to personalize therapeutic interaction according to a user's psychological st…
  arxiv Priyanka Singh, Sebastian Von Mammen 2025-11-25T08:52:02Z 置信度 0.78 cs.HC
• AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents
  Large Language Model (LLM) Agents have demonstrated remarkable capabilities in task automation and intelligent decision-making, driving the widespread adoption of agent development frameworks such as LangChain and AutoGen. However, these frameworks predominant…
  arxiv Jiabin Tang, Tianyu Fan, Chao Huang 2025-02-09T16:53:56Z 置信度 0.78 cs.AIcs.CL
• A Flexible Multi-Agent LLM-Human Framework for Fast Human Validated Tool Building
  We introduce CollabToolBuilder, a flexible multiagent LLM framework with expert-in-the-loop (HITL) guidance that iteratively learns to create tools for a target goal, aligning with human intent and process, while minimizing time for task/domain adaptation effo…
  arxiv Daull Xavier, Patrice Bellot, Emmanuel Bruno, Vincent Martin 等 2025-12-01T09:19:18Z 置信度 0.78 cs.AI
• ClawTrace: Cost-Aware Tracing for LLM Agent Skill Distillation
  Skill-distillation pipelines learn reusable rules from LLM agent trajectories, but they lack a key signal: how much each step costs. Without per-step cost, a pipeline cannot distinguish adding a missing step to fix a bug from removing an expensive step that ne…
  arxiv Boqin Yuan, Yue Su, Renchu Song, Sen Yang 等 2026-04-26T19:44:10Z 置信度 0.78 cs.AI
• From Prompts to Contracts: Harness Engineering for Auditable Enterprise LLM Agents
  Enterprise large language model (LLM) applications often begin as prototypes whose behavior is carried by prompts and retrieval context. Productization adds requirements for source boundaries, entity routing, answer contracts, and reproducible traces. We prese…
  arxiv Joongho Ahn, Moonsoo Kim 2026-07-09T01:08:33Z 置信度 0.78 cs.AIcs.CLcs.SE
• A Concurrent Modular Agent: Framework for Autonomous LLM Agents
  We introduce the Concurrent Modular Agent (CMA), a framework that orchestrates multiple Large-Language-Model (LLM)-based modules that operate fully asynchronously yet maintain a coherent and fault-tolerant behavioral loop. This framework addresses long-standin…
  arxiv Norihiro Maruyama, Takahide Yoshida, Hiroki Sato, Atsushi Masumori 等 2025-08-26T13:58:31Z 置信度 0.78 cs.AI
• LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey
  Recent advances in large language models (LLMs) have sparked growing interest in building fully autonomous agents. However, fully autonomous LLM-based agents still face significant challenges, including limited reliability due to hallucinations, difficulty in …
  arxiv Henry Peng Zou, Wei-Chieh Huang, Yaozu Wu, Jizhou Guo 等 2025-05-01T08:29:26Z 置信度 0.78 cs.CLcs.LG
• A Framework for Formalizing LLM Agent Security
  Security in LLM agents is inherently contextual. For example, the same action taken by an agent may represent legitimate behavior or a security violation depending on whose instruction led to the action, what objective is being pursued, and whether the action …
  arxiv Vincent Siu, Jingxuan He, Kyle Montgomery, Zhun Wang 等 2026-03-19T21:01:49Z 置信度 0.78 cs.CRcs.AI
• From Agent Loops to Structured Graphs:A Scheduler-Theoretic Framework for LLM Agent Execution
  The dominant paradigm for building LLM based agents is the Agent Loop, an iterative cycle where a single language model decides what to do next by reading an ever growing context window. This paradigm has three structural weaknesses: implicit dependencies betw…
  arxiv Hu Wei 2026-04-13T12:16:45Z 置信度 0.78 cs.AIeess.SY
• Who Gets the Reward & Who Gets the Blame? Evaluation-Aligned Training Signals for Multi-LLM Agents
  Large Language Models (LLMs) in multi-agent systems (MAS) have shown promise for complex tasks, yet current training methods lack principled ways to connect system-level evaluation with agent- and message-level learning. We propose a theoretical framework that…
  arxiv Chih-Hsuan, Yang, Tanwi Mallick, Le Chen 等 2025-11-11T22:21:08Z 置信度 0.78 cs.MAcs.AIcs.CLcs.GT
• Affordance-Compiled Intelligence: Observable-Only Cognitive Impedance Matching for No-Meta LLM-Integrated Systems
  Affordance-Compiled Intelligence develops Cognitive Impedance Matching Theory (CIMT), an observable-only and no-meta protected compiler theory for LLM-integrated systems. The paper studies how a fixed model-policy can exhibit different operational capability w…
  openalex Patrick Lewis, Ethan Perez, Aleksandara Piktus, Fabio Petroni 等 2026-05-11 置信度 0.72 Artificial intelligenceComputer scienceNatural language processingInformation retrieval
• Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation
  This paper introduces a novel approach using Large Language Models (LLMs) integrated into an agent framework for flexible and effective personal mobility generation. LLMs overcome the limitations of previous models by effectively processing semantic data and o…
  openalex Jiawei Wang, Renhe Jiang, Chuang Yang, Zengqing Wu 等 2024-01-01 置信度 0.72 Computer scienceAction (physics)Human–computer interactionKnowledge managementKey (lock)
• A Survey of Large Language Models
  Abstract The rapid evolution of large language models (LLMs) has driven a transformative shift in artificial intelligence (AI), reshaping both research paradigms and practical applications. Distinguished from their predecessors by unprecedented scale and advan…
  openalex Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang 等 2026-05-09 置信度 0.72 Language modelComputer scienceMainstreamScale (ratio)Artificial intelligence
• Conversational Health Agents: A Personalized LLM-Powered Agent Framework
  Conversational Health Agents (CHAs) are interactive systems that provide healthcare services, such as assistance and diagnosis. Current CHAs, especially those utilizing Large Language Models (LLMs), primarily focus on conversation aspects. However, they offer …
  openalex Mahyar Abbasian, Iman Azimi, Amir M. Rahmani, Ramesh Jain 2023-10-03 置信度 0.72 Computer scienceConversationHealth careFocus (optics)Human–computer interaction
• LLM agent framework for intelligent change analysis in urban environment using remote sensing imagery
  openalex Zixuan Xiao, Jun Ma 2025-06-19 置信度 0.72 Remote sensingChange detectionComputer scienceArtificial intelligenceComputer vision
• Application of LLM Agents in Recruitment: A Novel Framework for Automated Resume Screening
  The automation of resume screening is a crucial aspect of the recruitment process in organizations. Automated resume screening systems often encompass a range of natural language processing (NLP) tasks. This paper introduces a novel Large Language Models (LLMs…
  openalex Chengguang Gan, Qinghao Zhang, Tatsunori Mori 2024-01-01 置信度 0.72 Computer scienceData science
• RAH! RecSys–Assistant–Human: A Human-Centered Recommendation Framework With LLM Agents
  The rapid evolution of the web has led to an exponential growth in content. Recommender systems play a crucial role in human–computer interaction (HCI) by tailoring content based on individual preferences. Despite their importance, challenges persist in balanc…
  openalex Yu‐Bo Shu, Haonan Zhang, Hansu Gu, Peng Zhang 等 2024-06-26 置信度 0.72 Computer science
• CellAgent: LLM-Driven Multi-Agent Framework for Natural Language-Based Single-Cell Analysis
  Abstract Single-cell RNA sequencing (scRNA-seq) and spatial transcriptomics (ST) data analysis are pivotal for advancing biological research, enabling precise characterization of cellular heterogeneity. However, existing analysis approaches require extensive m…
  preprints Yihang Xiao, Jinyi Liu, Yan Zheng, Shaoqing Jiao 等 2024 置信度 0.74 Computer science
• STRIDE: A Tool-Assisted LLM Agent Framework for Strategic and Interactive Decision-Making
  Large Language Models (LLMs) like GPT-4 have revolutionized natural language processing, showing remarkable linguistic proficiency and reasoning capabilities. However, their application in strategic multi-agent decision-making environments is hampered by signi…
  openalex Chuanhao Li, Runhan Yang, Tiankai Li, Milad Bafarassat 等 2024-05-25 置信度 0.72 STRIDEComputer scienceHuman–computer interactionProcess managementBusiness
• DatawiseAgent: A Notebook-Centric LLM Agent Framework for Adaptive and Robust Data Science Automation
  Existing large language model (LLM) agents for automating data science show promise, but they remain constrained by narrow task scopes, limited generalization across tasks and models, and over-reliance on state-of-the-art (SOTA) LLMs.We introduce DatawiseAgent…
  openalex Ziming You, Yumiao Zhang, Dexuan Xu, Yiwei Lou 等 2025-01-01 置信度 0.72 Computer scienceAutomationContext (archaeology)Systems engineeringEngineering
• A MODULAR BENCHMARKING FRAMEWORK FOR EVALUATING LLM-BASED AGENT APPLICATIONS
  openalex Karthik Perikala 2026-01-06 置信度 0.72 Computer scienceModular designBenchmarkingSystems engineeringSoftware engineering
• Dual-model synergy for audit opinion prediction: A collaborative LLM agent framework approach
  By combining the capabilities of Moonshot and DeepSeek-R1, which respectively evaluate risk scores based on MD&A text information and financial data, we exploit the complementary strengths of long-context and reasoning large language models (LLMs) to help eval…
  openalex Louise Yi Lu, Jin-Xing Hao, Xuesong Tang 2025-09-23 置信度 0.72 AuditExploitLogistic regressionBoosting (machine learning)Gradient boosting
• Toward LLM-agent-based modeling of transportation systems: A conceptual framework
  In transportation system demand modeling and simulation, agent-based models and microsimulations are current state-of-the-art approaches. However, existing agent-based models still have some limitations on behavioral realism and resource demand that limit thei…
  openalex Tianming Liu, Jirong Yang, Yafeng Yin 2025-06-02 置信度 0.72 Conceptual frameworkConceptual modelComputer scienceSystems engineeringManagement science
• Large language models (LLMs): survey, technical frameworks, and future challenges
  Artificial intelligence (AI) has significantly impacted various fields. Large language models (LLMs) like GPT-4, BARD, PaLM, Megatron-Turing NLG, Jurassic-1 Jumbo etc., have contributed to our understanding and application of AI in these domains, along with na…
  openalex Pranjal Kumar 2024-08-18 置信度 0.72 Computer scienceManagement scienceData scienceRisk analysis (engineering)Business
• Metaopenfoam: An Llm-Based Multi-Agent Framework for Cfd
  Remarkable progress has been made in automated problem solving through societies of agents based on large language models (LLMs). Computational fluid dynamics (CFD), as a complex problem, presents unique challenges in automated simulations that require sophist…
  openalex Yuxuan Chen, Xu Zhu, Hua Zhou, Zhuyin Ren 2024-01-01 置信度 0.72 Computational fluid dynamicsComputer scienceEngineeringAerospace engineering
• Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools
  We introduce Agentic Reasoning, a framework that enhances large language model (LLM) reasoning by integrating external tool-using agents.Agentic Reasoning dynamically leverages web search, code execution, and structured memory to address complex problems requi…
  openalex Junde Wu, Jia Zhu, Yuan Liu, Min Xu 等 2025-01-01 置信度 0.72 Computer scienceModel-based reasoningAnalytic reasoningQualitative reasoningKnowledge management
• AI Hiring with LLMs: A Context-Aware and Explainable Multi-Agent Framework for Resume Screening
  Resume screening is a critical yet time-intensive process in talent acquisition, requiring recruiters to analyze vast volume of job applications while remaining objective, accurate, and fair. With the advancements in Large Language Models (LLMs), their reasoni…
  openalex Frank P.-W. Lo, Jianing Qiu, Zeyu Wang, Haibao Yu 等 2025-06-11 置信度 0.72 Computer scienceRelevance (law)Bridging (networking)Process (computing)Knowledge management
• Why Johnny Can’t Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts
  Pre-trained large language models (“LLMs”) like GPT-3 can engage in fluent, multi-turn instruction-taking out-of-the-box, making them attractive materials for designing natural language interactions. Using natural language to steer LLM outputs (“prompting”) ha…
  openalex J.D. Zamfirescu-Pereira, Richmond Y. Wong, Bjoern Hartmann, Qian Yang 2023-04-19 置信度 0.72 Computer scienceArtificial intelligence
• Enhancing LLMs for Power System Simulations: A Feedback-Driven Multi-Agent Framework
  The integration of experimental technologies with large language models (LLMs) is transforming scientific research. It positions AI as a versatile research assistant rather than a mere problem-solving tool. In the field of power systems, however, managing simu…
  openalex Mengshuo Jia, Zeyu Cui, Gabriela Hug 2025-07-18 置信度 0.72 Power (physics)Computer scienceEnvironmental economicsBusinessControl theory (sociology)
• Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate
  Modern large language models (LLMs) like ChatGPT have shown remarkable performance on general language tasks but still struggle on complex reasoning tasks, which drives the research on cognitive behaviors of LLMs to explore human-like problem-solving strategie…
  openalex Liang Tian, Zhiwei He, Wenxiang Jiao, Xing Wang 等 2024-01-01 置信度 0.72 Computer scienceCognitive sciencePsychology
• ALAS: A Stateful Multi-LLM Agent Framework for Disruption-Aware Planning
  Large language models (LLMs) excel at rapid generation of text and multimodal content, yet they falter on transaction-style planning that demands ACID-like guarantees and real-time disruption recovery. We present Adaptive LLM Agent System (ALAS), a framework t…
  openalex Edward Y. Chang, Geng, Longling 2025-05-18 置信度 0.72 Stateful firewallComputer scienceScheduling (production processes)ScalabilityContext (archaeology)
• MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
  Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Existing LLM-based multi-agent systems can already solve simple dialogue tasks. Solutions to more complex tasks, however, are comp…
  openalex Sirui Hong, Zhuge, Mingchen, Chen, Jiaqi, Xiawu Zheng 等 2023-08-01 置信度 0.72 Computer scienceWorkflowSoftware engineeringDomain (mathematical analysis)Chaining
• UXAgent: An LLM Agent-Based Usability Testing Framework for Web Design
  openalex Yuxuan Lu, Bingsheng Yao, Hansu Gu, Jing‐Zhi Huang 等 2025-04-23 置信度 0.72 Computer scienceUsabilityWeb usabilityUsability labUsability engineering
• ChainStream: A Stream-based LLM Agent Framework for Continuous Context Sensing and Sharing
  This paper introduces ChainStream, an LLM-based framework for building and serving context-aware AI agents. Driven by the goal to enable context awareness of LLM agents and flexible information sharing between them, we adopt a stream-based design, in which the…
  openalex J. Liu, Wenxing Xu, Yuanchun Li 2024-06-03 置信度 0.72 Computer scienceContext (archaeology)Multi-agent systemDistributed computingArtificial intelligence
• SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models
  In this work, we introduce SMART-LLM, an innovative framework designed for embodied multi-robot task planning. SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models (LLMs), harnesses the power of LLMs to convert high-level task instructi…
  openalex Shyam Sundar Kannan, Vishnunandan L. N. Venkatesh, Byung‐Cheol Min 2024-10-14 置信度 0.72 Computer scienceTask (project management)RobotHuman–computer interactionArtificial intelligence
• Book Review: Truth from Trash
  crossref Larry M. Stephens 2002-12-23T00:56:42Z 置信度 0.70
• Coordination for Internet Application Development
  crossref Andrea Omicini, Franco Zambonelli 2002-12-23T00:56:42Z 置信度 0.70
• Adaptive Web Site Agents
  crossref Michael J. Pazzani, Daniel Billsus 2002-12-28T21:20:03Z 置信度 0.70
• Socially Conscious Decision-Making
  crossref Alyssa Glass, Barbara J. Grosz 2003-04-07T22:16:51Z 置信度 0.70
• Coordination Mechanisms for Web Agents
  crossref Paolo Ciancarini, Robert Tolksdorf 2002-12-23T00:56:42Z 置信度 0.70
• A method for real-time dynamic fleet mission planning for autonomous mining
  This paper introduces a method for dynamic fleet mission planning for autonomous mining (in loop-free maps), in which a dynamic fleet mission is defined as a sequence of static fleet missions, each generated using a modified genetic algorithm. For the case of …
  crossref Mattias Wahde, Mauro Bellone, Sina Torabi 2019-06-12T19:02:22Z 置信度 0.70
• M&M's: Building Binary Software Components for Supporting Mobile-Agent Enabled Applications
  crossref Paulo Marques, Luis Silva, João Gabriel Silva 2002-12-23T21:58:59Z 置信度 0.70
• Agent Programming in 3APL
  crossref Koen V. Hindriks, Frank S. De Boer, Wiebe Van der Hoek, John-Jules Ch. Meyer 2002-12-23T00:56:42Z 置信度 0.70
• Constraints Enabled Autonomous Agent Marketplace: Discovery and Matchmaking
  crossref Debmalya Biswas 2024-02-29T05:30:53Z 置信度 0.70
• Functional Validation in Grid Computing
  crossref Guofei Jiang, George Cybenko 2004-01-13T14:19:10Z 置信度 0.70
• Simulating Autonomous Agent in Connected Virtual Environments
  Simulation d’Agents Autonomes dans des Environnements Virtuels Connectés Comprendre le comportement humain est essentiel pour développer des systèmes adaptatifs tels que des environnements connectés. Des données réelles sont alors nécessaires, mais elles sont …
  crossref Lysa Gramoli 2026-04-08T14:43:22Z 置信度 0.70
• Towards a Reference Model for Surveying Mobile Agent Systems
  crossref Alberto Rodrigues Silva, Artur Romão, Dwight Deugo, Miguel Mira da Silva 2002-12-23T10:16:33Z 置信度 0.70
• Multi-Agent Fuzzy Reinforcement Learning for Autonomous Vehicles
  This thesis investigates how the evader in a pursuit-evasion differential game can learn its control strategies using the fuzzy actor-critic learning algorithm. The evader learns its control strategies while being chased by a pursuer that is also learning its …
  crossref Esther Akinwumi 2020-03-05T16:14:56Z 置信度 0.70
• Computational Markets to Regulate Mobile-Agent Systems
  crossref Jonathan Bredin, David Kotz, Daniela Rus, Rajiv T. Maheswaran 等 2003-04-07T22:16:51Z 置信度 0.70
• Autonomous agent technology
  The first question addressed in the paper is "Why and how agent technology supports the design and implementation of Autonomous Decentralised Systems?" Subsequently, based on the main characteristics of the intelligent and mobile agents we assess the specific …
  crossref S. Covaci 2003-01-22T10:57:59Z 置信度 0.70
• Using Domain-Independent Exception Handling Services to Enable Robust Open Multi-Agent Systems: The Case of Agent Death
  crossref Mark Klein, Juan-Antonio Rodriguez-Aguilar, Chrysanthos Dellarocas 2003-09-12T21:56:22Z 置信度 0.70
• MARP: A Multi-Agent Routing Protocol for Mobile Wireless Ad Hoc Networks
  crossref Romit Roy Choudhury, Krishna Paul, Somprakash Bandyopadhyay 2003-12-19T10:34:45Z 置信度 0.70
• Coordinating Mutually Exclusive Resources using GPGP
  crossref Keith Decker, Jinjiang Li 2002-12-23T00:56:42Z 置信度 0.70
• Forecasting Agentic Commerce: How Compute Tokenization Reshapes Transaction Mechanisms in Autonomous Agent-to-Agent Economies
  Forecasts of agentic commerce increasingly emphasize the capability trajectory of large AI models, yet realized economic value also depends on whether autonomous agents can discover counterparties, compare offers, authorize transactions, verify performance, an…
  crossref Jie Gao 2026-06-17T00:38:17Z 置信度 0.70
• Building Agile Systems with Mobile Code
  crossref Todd Papaioannou, John Edwards 2002-12-23T14:27:29Z 置信度 0.70
• Utilitarian Desires
  crossref Jérôme Lang, Leendert van der Torre, Emil Weydert 2002-12-28T23:59:19Z 置信度 0.70
• DRC-Coder: Automated DRC Checker Code Generation Using LLM Autonomous Agent
  In the advanced technology nodes, the integrated design rule checker (DRC) is often utilized in place and route tools for fast optimization loops for power-performance-area. Implementing integrated DRC checkers to meet the standard of commercial DRC tools dema…
  europepmc 2024 置信度 0.80
• Counterfactual learning in enhancing resilience in autonomous agent systems.
  Resilience in autonomous agent systems is about having the capacity to anticipate, respond to, adapt to, and recover from adverse and dynamic conditions in complex environments. It is associated with the intelligence possessed by the agents to preserve the fun…
  europepmc 2023 置信度 0.80
• Detection of Static and Mobile Targets by an Autonomous Agent with Deep Q-Learning Abilities.
  This paper addresses the problem of detecting multiple static and mobile targets by an autonomous mobile agent acting under uncertainty. It is assumed that the agent is able to detect targets at different distances and that the detection includes errors of the…
  europepmc 2022 置信度 0.80
• An autonomous agent for negotiation with multiple communication channels using parametrized deep Q-network.
  Agent-based negotiation aims at automating the negotiation process on behalf of humans to save time and effort. While successful, the current research considers communication between negotiation agents through offer exchange. In addition to the simple manner, …
  europepmc 2022 置信度 0.80
• Cryptographic Governance for Autonomous AI Agents in Decentralized Systems: A Policy-Enforced Identity and Accountability Framework
  Autonomous artificial intelligence agents increasingly act across decentralized systems, yet existing authorization models provide limited mechanisms for constraining delegated authority, proving policy compliance, and assigning accountability for machine-init…
  europepmc 2026 置信度 0.80
• TopoMLP++: Towards Strong and Scalable Lane Topology Reasoning in Autonomous Driving.
  Driving topology reasoning is an important perception task in autonomous driving, which requires detecting road centerlines (lane) and traffic elements, further reasoning their topology relationship. However, deploying this in real-world scenarios faces two si…
  europepmc 2026 置信度 0.80
• AI Native Manufacturing Operating System for Autonomous Smart Factories Using Digital Twins, Multi Agent Artificial Intelligence, Physics Informed Machine Learning, and Reinforcement Learning.
  Abstract Smart factories accumulate large volumes of process data, yet the software governing them remains a set of loosely federated applications: an execution system for order release, a supervisory layer for equipment, isolated condition monitoring services…
  europepmc MD AZIZUL HAKIM ABIR 2026 置信度 0.80
• Consumer Perception and Policy Intervention in Large-scale Implementation of Advanced Autonomous Driving: A Dynamic Evolutionary Study Based on Agent-Based Modeling
  Abstract Despite continuous technological advancements and robust policy support mechanisms, consumer perceptions of autonomous driving systems remain cautious or even conflicting. Advanced autonomous driving bridges the gap between the “technological feasibil…
  europepmc 2026 置信度 0.80
• Autonomous Agents for Auditable Cardiovascular Artificial Intelligence Development
  ABSTRACT Clinical artificial intelligence (AI) models are usually reported as finished artifacts, but each model reflects a limited human search across a much larger space of architectures, inputs, losses, optimizers, and training recipes. We tested whether au…
  europepmc 2026 置信度 0.80
• RECON: A Recipe-Driven, Evidence-Fused, Neuro-Symbolic Multi-Agent Architecture for Autonomous Document Compliance Auditing across Heterogeneous Enterprise Repositories
  Abstract Document compliance review in regulated organisations stays slow, uneven and hard to defend, because human reviewers disagree on borderline clauses and rarely record a verifiable account of why a document passed or failed (Morande & Shah, 2020; Lipton…
  europepmc 2026 置信度 0.80
• GeoMind: An Autonomous Multi-Agent Framework for Verified Geospatial Analysis
  Abstract The rapid growth of the Earth observation satellite constellation has started to shift the paradigm to autonomous geospatial computing. But until now, using general-purpose Large Language Models (LLMs) as independent GIS coding agents has been hampere…
  europepmc 2026 置信度 0.80
• Artificial intelligence agent for delirium screening among patients in oncology and cardiac intensive care units: a proof-of-concept study.
  Aims This study aims to develop and initially test an autonomous artificial intelligence (AI) agent to support nurse-led delirium screening and guideline-concordant prevention and management. Methods and results We constructed a delirium-specific knowledge gra…
  europepmc 2026 置信度 0.80
• Autonomous ground vehicles for MEDEVAC: capability assessment based on agent-based modelling.
  Introduction Medical evacuation (MEDEVAC) is a crucial component of military healthcare, and the time during which evacuation of the wounded, injured and ill individuals happens is one of the most critical factors. The article focuses on the initial phase of g…
  europepmc 2026 置信度 0.80
• Strategies for resilient climate in smart cities mediated by Nash equilibrium and autonomous decision-makers.
  Recently, smart cities are facing pressing challenges due to global warming. Rising greenhouse gas emissions driven by population growth, increased mobility, and the increasing industrial demand for production and maintenance of technological infrastructure ha…
  europepmc 2026 置信度 0.80
• Governing Autonomous Enterprises: A Transaction Cost Perspective on Multi-Agent AI Systems in Supply Chain Operations
  Abstract Problem definition : The rapid proliferation of autonomous multi-agent AI systems (MAS) in enterprise environments creates novel governance challenges that existing business frameworks have not addressed. Relevance : As organizations deploy agent-to-a…
  europepmc Garv Sharma 2026 置信度 0.80
• CodePori: Large-Scale System for Autonomous Software Development Using Multi-Agent Technology
  Abstract Context: Existing Large Language Model (LLM)-based multi-agent systems are capable of executing tasks and providing data-driven recommendations, thereby enabling automation and decision support that assist practitioners in software development. Howeve…
  europepmc 2026 置信度 0.80
• Beyond Human-Designed Objectives: Autonomous Goal Generation in AI Through Intrinsic Motivation and Self-Directed Agency
  Current artificial intelligence systems remain fundamentally constrained by their dependence on human-designed objectives and reward functions, limiting their capacity for genuine autonomy and open-ended development. This paper proposes Autonomous Goal Generat…
  europepmc 2026 置信度 0.80
• A computational framework for Kármán gaiting in robotic fish: spatio-temporal perception and CPG-based reinforcement learning.
  Navigating in unsteady wake flows, such as Kármán vortex streets, presents a formidable challenge for biomimetic autonomous underwater vehicles. Biological fish achieve this by utilizing their lateral line sensory systems to perceive local flow gradients and a…
  europepmc 2026 置信度 0.80
• AutoLabs: cognitive multi-agent systems with self-correction for autonomous chemical experimentation.
  The automation of chemical research through self-driving laboratories (SDLs) promises to accelerate scientific discovery, yet the reliability and granular performance of the underlying AI agents remain critical, under-examined challenges. In this work, we intr…
  europepmc 2026 置信度 0.80
• Towards autonomous scheduling agents for water distribution networks: Self-evolving data-centric AI via continuous data-model coevolution.
  Urban water distribution networks (WDNs) require adaptive scheduling strategies to handle dynamic demand fluctuations. Scientific pump scheduling ensures reliable water supply while minimizing energy consumption and carbon emissions. Data-centric AI (DCAI) ena…
  europepmc 2026 置信度 0.80
• Emergent Inter-Agent Conflict in Multi-Agent AI Systems: An Experimental Study of Objective Divergence
  Abstract The rapid emergence of multi-agent artificial intelligence ecosystems has introduced a critical systems-level problem that contemporary alignment research has largely failed to address: inter-agent objective divergence. While existing literature remai…
  europepmc Som Subhro Nath 2026 置信度 0.80
• MRISce: an interactive autonomous driving test scenario generation method based on multi-agent reinforcement learning.
  Road safety remains the primary objective in the development and validation of autonomous driving systems. Scenario-based simulation testing provides an efficient and controllable method for safety verification. However, the lack of dynamic interaction between…
  europepmc 2026 置信度 0.80
• Agentic AI for Code Quality: A Four-Agent Machine Learning System for Repository Refactoring, Public RAG, Groq Reasoning, and Reinforcement Learning
  Abstract Background: Software repositories continuously accumulate technical debt in the form of code smells, duplicated logic, high complexity, and poor maintainability. Although static analysis tools can identify these issues, they typically stop at diagnosi…
  europepmc Abhishek Prithvi Tejs 2026 置信度 0.80
• An Agentic LLM Framework for Autonomous Surgical Continuum Monitoring: ReAct-Driven Tool-Use Agents for Presurgical, Intraoperative, and Postsurgical Cardiopulmonary Care.
  Background Rule-based multi-agent system (MAS) architectures for healthcare coordination rely on hardcoded decision trees that cannot generalise to novel clinical scenarios or self-correct reasoning errors. These limitations are acute in surgical continuum car…
  europepmc 2026 置信度 0.80
• PLGA - encapsulated harmine derivative H-2-168: A promising therapeutic agent for mitigating liver damage in hepatic hydatid disease.
  Harmine (HM), a bioactive alkaloid, exhibits remarkable antiparasitic potency. Nevertheless, its translational potential is substantially constrained by neurotoxicity, necessitating the development of safer analogs. H-2-168, a rationally designed derivative sy…
  europepmc 2026 置信度 0.80
• Agentic AI and Large Language Models for Autonomous IoT Cybersecurity: A Systematic Survey, Taxonomy, and Research Roadmap
  Conventional signature-based defenses no longer protect the heterogeneous, large-scale infrastructures that the Internet of Things (IoT) now constitutes. Large language models (LLMs) and agentic artificial intelligence (AI)—systems that autonomously perceive, …
  europepmc 2026 置信度 0.80
• Autonomous computational prioritisation of colorectal cancer vulnerabilities via multi-scale AI swarms
  The acceleration of automated scientific discovery has been fundamentally bottlenecked by the epistemic gap between the semantic reasoning of large language models (LLMs) and the complex, non-linear reality of mammalian biology. While recent multi-agent framew…
  europepmc 2026 置信度 0.80
• Nail It! A learning framework for autonomous surgical suturing and teleoperation on the dVRK.
  Purpose Reliable automation of surgical suturing requires accurate and flexible simulation tools to effectively learn robot autonomous skills that match clinical practice. Yet, high-fidelity, ready-to-use learning frameworks remain scarce even for popular plat…
  europepmc 2026 置信度 0.80
• Federated Autonomous Cyber Agents for Privacy-Preserving Intrusion Detection in Distributed Smart Grids
  Abstract Distributed smart grids increasingly rely on interconnected cyber-physical infrastructures, edge intelligence, microgrids, distributed energy resources, and real-time demand-response mechanisms. Although this integration improves flexibility and opera…
  europepmc 2026 置信度 0.80
• Cognitive Supply Chain Twins in Geopolitical Turbulence: A Multi-Agent Reinforcement Learning Architecture for Autonomous Resilience in Emerging Economies
  Abstract Global supply chains are experiencing structurally intensified vulnerability to geopolitical shocks, manifested in port blockades, trade embargoes, and maritime corridor disruptions. Traditional risk management frameworks, anchored in static contingen…
  europepmc 2026 置信度 0.80
• AAL: In-Band Source Annotations for Just-In-Time Context Injection in Autonomous Agentic Workflows
  Abstract As LLM-driven autonomous agents integrate directly into the software development life cycle, modern IDEs face a severe performance bottleneck: context pollution. Existing paradigms rely on global, out-of-band system files (e.g., .cursorrules) that con…
  europepmc 2026 置信度 0.80
• SC-Mamba: Causal Disentanglement of Driver Intent and Style for Autonomous Driving Motion Forecasting
  Predicting where a traffic agent will go and how it will get there are fundamentally different questions, yet most learning-based forecasters conflate them. When a model entangles agent intent (e.g., turning left) with driving style (e.g., cautious versus aggr…
  europepmc 2026 置信度 0.80
• Achieving Audit Log Completeness in Agentic RAG Systems: A Framework for SAP Financial Workflows
  The integration of Agentic Retrieval-Augmented Generation (RAG) systems into enterprise financial workflows, particularly within complex SAP environments, introduces transformative efficiencies alongside critical governance challenges. Chief among these is the…
  europepmc 2026 置信度 0.80
• Structure-Preserving Learning and Prediction in Optimal Control of Collective Motion
  The widespread adoption of autonomous vehicle technologies requires accurate predictions of coordinated multi-agent motion. While predicting such motion under arbitrary control mechanisms is generally intractable, we focus on certain classes of optimal control…
  europepmc 2026 置信度 0.80
• ZSM²RL: A Mathematical Framework for Zero-Shot Stochastic Meta Multi-Agent Reinforcement Learning under Uncertainty and Partial Observability
  Abstract This paper presents the Zero-Shot Self-Modeling Multi-Agent Reinforcement Learning (ZSM 2 RL) framework, a novel approach designed to achieve robust generalization and rapid policy adaptation across unseen environments without retraining. The primary …
  europepmc 2026 置信度 0.80
• Quantum Game-Theoretic Reinforcement Learning for Autonomous Vehicle Navigation and Communication in Vehicular Networks
  Abstract Autonomous vehicle (AV) navigation and communication in highly dynamic vehicular networks require fast decision-making, reliable coordination, and energy-efficient connectivity. However, traditional Reinforcement Learning (RL) and game-theoretic appro…
  europepmc 2026 置信度 0.80
• SECREFLECT: Reliable Context Evolution for Autonomous Cyber Agents via Pre-Memory Reflection Validation
  Abstract Autonomous cyber agents powered by large language models (LLMs) increasingly rely on iterative self-reflection to accumulate contextual knowledge across multi-step attack chains. While frameworks such as Reflexion [Shinn et al., 2023] and Agentic Cont…
  europepmc 2026 置信度 0.80
• A Review of Ship Path Planning for Autonomous Navigation: From Model-Driven Methods to Deep Reinforcement Learning
  Ship path planning is a central challenge in autonomous navigation for unmanned surface vehicles and maritime autonomous surface ships. It is not simply a shortest-path problem, but a constrained sequential decision process that must reconcile collision risk, …
  europepmc 2026 置信度 0.80
• Laboratory Toxicity and Field Efficacy of Four Microbial-Derived Pesticides Combined with Two Adjuvants Against <i>Lygus pratensis</i> (Hemiptera: Miridae).
  Systematic field data on adjuvant-amended microbial-derived pesticides against L. pratensis in arid, high-ultraviolet cotton regions remain scarce. This study systematically evaluated the laboratory toxicity and field efficacy of four kinds of microbial-derive…
  europepmc 2026 置信度 0.80
• TeLLAgent: a dual-agent framework for reliable scientific discovery with tool-enhanced LLMs.
  Large language model agents hold immense promise for automating scientific discovery, yet their real-world application is hindered by an inability to reliably orchestrate tools and execute complex, multi-step plans without encountering hallucinations or logica…
  europepmc 2026 置信度 0.80
• From Learning Analytics to Autonomous Agents: A Context-Aware Multimodal DRL Framework for Personalized Education
  Abstract This paper introduces the Context-Aware Multi-Agent Deep Reinforcement Learning (CA-MA-DRL) framework, a transformative approach to personalized digital education that shifts the paradigm from passive learning analytics to autonomous, decision-making …
  europepmc 2026 置信度 0.80