AI Agent 生态 · 全部实体（第 100 / 100 页）

本页收录第 9901–10000 条，共 10000 条 · 返回 AI Agent 生态 首页

• Towards Safe and Honest AI Agents with Neural Self-Other Overlap
  As AI systems increasingly make critical decisions, deceptive AI poses a significant challenge to trust and safety. We present Self-Other Overlap (SOO) fine-tuning, a promising approach in AI Safety that could substantially improve our ability to build honest …
  arxiv Marc Carauleanu, Michael Vaiana, Judd Rosenblatt, Cameron Berg 等 2024-12-20T20:23:52Z 置信度 0.78 cs.AIcs.CR
• Cognitive Dissonance Artificial Intelligence (CD-AI): The Mind at War with Itself. Harnessing Discomfort to Sharpen Critical Thinking
  AI-augmented systems are traditionally designed to streamline human decision-making by minimizing cognitive load, clarifying arguments, and optimizing efficiency. However, in a world where algorithmic certainty risks becoming an Orwellian tool of epistemic con…
  arxiv Delia Deliu 2025-04-23T03:18:05Z 置信度 0.78 cs.HCcs.CY
• Efficient Spatial-Temporal Information Fusion for LiDAR-Based 3D Moving Object Segmentation
  Accurate moving object segmentation is an essential task for autonomous driving. It can provide effective information for many downstream tasks, such as collision avoidance, path planning, and static map construction. How to effectively exploit the spatial-tem…
  arxiv Jiadai Sun, Yuchao Dai, Xianjing Zhang, Jintao Xu 等 2022-07-05T17:59:17Z 置信度 0.78 cs.CVcs.RO
• Caging the Agents: A Zero Trust Security Architecture for Autonomous AI in Healthcare
  Autonomous AI agents powered by large language models are being deployed in production with capabilities including shell execution, file system access, database queries, and multi-party communication. Recent red teaming research demonstrates that these agents …
  arxiv Saikat Maiti 2026-03-18T06:54:47Z 置信度 0.78 cs.CRcs.AI
• Safe, Untrusted, "Proof-Carrying" AI Agents: toward the agentic lakehouse
  Data lakehouses run sensitive workloads, where AI-driven automation raises concerns about trust, correctness, and governance. We argue that API-first, programmable lakehouses provide the right abstractions for safe-by-design, agentic workflows. Using Bauplan a…
  arxiv Jacopo Tagliabue, Ciro Greco 2025-10-10T17:18:36Z 置信度 0.78 cs.AIcs.DB
• AegisUI: Behavioral Anomaly Detection for Structured User Interface Protocols in AI Agent Systems
  AI agents that build user interfaces on the fly assembling buttons, forms, and data displays from structured protocol payloads are becoming common in production systems. The trouble is that a payload can pass every schema check and still trick a user: a button…
  arxiv Mohd Safwan Uddin, Saba Hajira 2026-03-05T10:24:43Z 置信度 0.78 cs.AI
• AI Tool Discovery at Scale: All You Need is DNS
  The coming era of autonomous AI agents demands a discovery mechanism capable of navigating millions of tools, yet existing solutions buckle under O(N) complexity and centralized governance. Instead of building another fragile overlay, we propose ToolDNS, a rad…
  arxiv Enhao Chen, Yulin Shao 2026-04-19T04:31:19Z 置信度 0.78 cs.AIcs.MAcs.NI
• Skill Retrieval Augmentation for Agentic AI
  As large language models (LLMs) evolve into agentic problem solvers, they increasingly rely on external, reusable skills to handle tasks beyond their native parametric capabilities. In existing agent systems, the dominant strategy for incorporating skills is t…
  arxiv Weihang Su, Jianming Long, Qingyao Ai, Qiaozhi He 等 2026-04-27T15:19:59Z 置信度 0.78 cs.CLcs.AI
• Harness Engineering for Agentic AI Coding Tools: An Exploratory Study
  Agentic AI coding tools increasingly automate software development tasks. Developers can configure these tools through versioned repository-level artifacts such as Markdown and JSON files. We present a systematic analysis of configuration mechanisms for agenti…
  arxiv Matthias Galster, Seyedmoein Mohsenimofidi, Jai Lal Lulla, Muhammad Auwal Abubakar 等 2026-02-16T12:24:28Z 置信度 0.78 cs.SE
• Sola-Visibility-ISPM: Benchmarking Agentic AI for Identity Security Posture Management Visibility
  Identity Security Posture Management (ISPM) is a core challenge for modern enterprises operating across cloud and SaaS environments. Answering basic ISPM visibility questions, such as understanding identity inventory and configuration hygiene, requires interpr…
  arxiv Gal Engelberg, Konstantin Koutsyi, Leon Goldberg, Reuven Elezra 等 2026-01-11T18:36:33Z 置信度 0.78 cs.CRcs.AI
• OxyGent: Making Multi-Agent Systems Modular, Observable, and Evolvable via Oxy Abstraction
  Deploying production-ready multi-agent systems (MAS) in complex industrial environments remains challenging due to limitations in scalability, observability, and autonomous evolution. We present OxyGent, an open-source framework driven by two core novelties: a…
  arxiv Junxing Hu, Tianlong Li, Lei Yu, Ai Han 2026-04-28T13:08:14Z 置信度 0.78 cs.AI
• Norm Enforcement for AI Agents: Robustly Shaping Behavior in Multi-Agent Systems
  AI agents are increasingly deployed in shared environments where they pursue diverse goals and compete for rewards. This multi-agent competition can lead to behaviors that serve individual gains at collective cost -- for instance, marketing agents may post mis…
  arxiv Yaowen Ye, Jacob Steinhardt 2026-07-07T06:40:14Z 置信度 0.78 cs.AIcs.CLcs.LGcs.MA
• From single-agent to multi-agent: a comprehensive review of LLM-based legal agents
  With the growing application of artificial intelligence (AI) in the legal domain, large language model (LLM)-based legal agents have achieved remarkable progress. This survey provides a comprehensive review of the applications and developments of LLM-driven ag…
  crossref Se Yang, Zhe Yang, Yutong Liu, Hongtao Wang 2026-01-07T02:58:26Z 置信度 0.70
• Accelerating multimetallic catalyst discovery with robotics and agentic AI
  The design space of catalyst materials spans composition, processing, atomistic structure, and microstructure. As materials become more complex, the dimensionality of this parameter space for catalyst design grows combinatorially. Conventional active learning …
  crossref Jiayu Peng, Chuanyu Liu, Yiwen Luo, Kritarth Dandapat 2026-01-07T02:04:16Z 置信度 0.70
• Control Overlays for Securing AI Systems: Using Agentic AI—Single Agent and Multi-Agent
  <jats:p/>
  crossref Vicky Pillitteri 2026-01-06T14:58:45Z 置信度 0.70
• BASIC PRINCIPLES OF MULTI-AGENT SYSTEM DESIGN
  БАЗОВЫЕ ПРИНЦИПЫ ПРОЕКТИРОВАНИЯ МНОГОАГЕНТНЫХ СИСТЕМ Шерстнева Светлана Владиславовна магистрант ФГАОУ ВО «Томский политехнический университет» Шерстнева Алена Владиславовна Аннотация: Приведено отличие многоагентных систем от моделей искусственного интеллекта…
  crossref Svetlana Vladislavovna Sherstneva, Alena Vladislavovna Sherstneva 2026-04-24T14:44:17Z 置信度 0.70
• Figure 2: Multi-agent system.
  crossref 2022-01-03T05:07:46Z 置信度 0.70
• Applications of Multi-Agent System in Power System Engineering
  Power system needs a continuous upgrade to overcome the challenges like distributed control, self-healing, power quality, demand side management and integration of renewable system. At present, power system needs an advance and intelligent technology to perfor…
  crossref G.S. Satheesh Kumar, S. Tamil Selvi 2020-04-24T06:25:43Z 置信度 0.70
• A multi-agent system (MAS) based scheme for health care and medical diagnosis system
  In recent era, health care professionals truly belief that the better health care can be provided by developing computerized intelligent health care system. In this paper, we attempted to propose an advanced scheme of agent-based health care and medical diagno…
  crossref Shibakali Gupta, Shiladitya Pujari 2009-09-08T14:42:21Z 置信度 0.70
• A distributed multi-level Energy Management System for Multi-Microgrids based on Multi-Agent System
  Enhancing energy resilience in response to the growing number of blackouts world-wide, primarily caused by High-Impact, Low-Probability (HILP) events, has become a major concern nowadays. Multi-Microgrids (MMGs) are increasingly recognized as a promising parad…
  crossref Yanandlall Gopee 2026-03-16T15:08:19Z 置信度 0.70
• An Agent Infrastructure to Build and Evaluate Multi-Agent Systems: The Java Agent Framework and Multi-Agent System Simulator
  crossref Regis Vincent, Bryan Horling, Victor Lesser 2007-08-16T12:13:32Z 置信度 0.70
• MASCOT: a multi-agent system for construction claims negotiation
  In the construction industry, negotiation is preferred for the settlement of claims (Powell-Smith and Stephenson, 1993). Negotiation plays an important role in resolving claims, preventing disputes and keeping a harmonious relationship between project particip…
  crossref 2021-04-06T13:40:36Z 置信度 0.70
• Computer aided multi-agent system engineering
  Currently, multi-agent systems (MAS) are being used in an increasingly wide variety of application areas, ranging from operational support and diagnosis, electronic commerce, manufacturing, information finding and filtering, planning and resource allocation, a…
  crossref Soe-Tsyr Yuan 2002-11-27T14:26:26Z 置信度 0.70
• Implicit: a multi-agent recommendation system for web search
  crossref Aliaksandr Birukou, Enrico Blanzieri, Paolo Giorgini 2010-08-19T09:37:48Z 置信度 0.70
• Evaluation of Multi-agent System Architectures
  crossref Danny Weyns 2010-05-10T14:17:15Z 置信度 0.70
• Multi-agent-based Substation Information Management System
  crossref 2007-02-20T13:24:23Z 置信度 0.70
• Multi-Agent Orchestration: Coordination, Trust, and Cascading Failures
  Background. Agentic artificial intelligence systems, defined by their capacity to reason, plan, and act autonomously through external tools and environments, represent a categorical shift in the operational profile of deployed AI. Architectures grounded in rea…
  crossref Rizwan Tanveer 2026-07-29T13:28:48Z 置信度 0.70
• SLA-Driven Orchestration of Long-Running Multi-Agent Enterprise Workflows
  crossref Laszlo Gyory 2025-11-18T18:46:32Z 置信度 0.70
• Tool Orchestration in Production Agent Systems: Code vs Protocols
  Model Context Protocol (MCP) has emerged as a promising way to standardize how AI agents discover and invoke tools. That promise is real: MCP improves interoperability by giving tools a consistent interface that multiple agent platforms can consume. However, i…
  crossref Shivi Bhatia 2026-03-31T09:43:18Z 置信度 0.70
• Centralized Agent Orchestration in Multi-Agent Systems
  The article describes the problem of agent orchestration in multi-agent systems based on large neural networks, which arises when creating intelligent assistants. The paper examines various architectural patterns used in multi-agent orchestration, including ce…
  crossref Oleg Yu. Maryasin, Andrey Ripnyagov 2026-04-27T19:47:39Z 置信度 0.70
• Dual-Mode AI Orchestration: Intelligent Coordination Mode Selection for Multi-Agent Systems
  crossref Erik Bernath 2025-08-22T18:49:03Z 置信度 0.70
• Contract-Gated Execution: A Deterministic Governance Layer for Autonomous AI Agent Orchestration
  This submission responds to the OECD's call for implementation tools that enable trustworthy AI deployment in consequential domains. Contract-gated execution was developed as commercial infrastructure and is presented here as a governance pattern directly appl…
  crossref Robert Stillwell 2026-04-22T10:41:17Z 置信度 0.70
• CodeAir: A Multi-Agent Orchestration Framework for AI-Assisted Software Development
  crossref Gabriel Avila Rangel 2026-01-26T16:19:40Z 置信度 0.70
• MAOIT: Multi-Agent Orchestration for Intelligent Tutoring - From Concept Delivery to Automated Evaluation
  crossref Andrei Paul Dobrescu, Ioan Daniel Pop 2026-05-24T09:48:27Z 置信度 0.70
• Geospatial AI (GeoAI) agent stack : router-based orchestration and design rationale
  This report summarizes the current state of a router-based, multiagent Geospatial AI (GeoAI) system designed to reliably execute geospatial workflows while retaining the flexibility of large language model (LLM) reasoning. The architecture is intentionally bot…
  crossref Matthew Drouillard, Michael Lewis 2026-05-12T15:23:52Z 置信度 0.70
• FATA: A Framework-Agnostic, Task-Agnostic Agentic AI Platform for Serverless Multi-Agent Orchestration
  Contemporary agentic AI systems face critical challenges in tool orchestration, dynamic coordination, and framework interoperability. I present FATA (Framework Agnostic and Task Agnostic Agentic AI), a novel control plane design pattern that enables scalable, …
  crossref AKRAM SHERIFF 2025-06-27T00:40:21Z 置信度 0.70
• Z-SPACE: A MULTI-AGENT TOOL ORCHESTRATION FRAMEWORK FOR ENTERPRISE-GRADE LLM AUTOMATION
  crossref Jing Nan 2025-12-10T01:47:41Z 置信度 0.70
• Adaptive Multi-Agent Role Reassignment over Model Context Protocol for Resilient AI Orchestration
  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 statically through…
  crossref Manish A Shukla 2025-09-03T20:54:10Z 置信度 0.70
• ALAS: A Stateful Multi-LLM Agent Framework for Disruption-Aware Planning
  crossref 2025-12-12T16:55:26Z 置信度 0.70
• LLM-Agent-UMF: LLM-based Agent Unified Modeling Framework for Seamless Design of Multi Active/Passive Core-Agent Architectures
  crossref Amine Ben Hassouna, Hana Chaari, Ines Belhaj 2025-10-22T08:30:55Z 置信度 0.70
• Contamination Percolation in Multi-Agent LLM Systems: A Measurement Framework and Benchmark
  Multi-agent large language model (LLM) systems are being deployed in healthcare, finance, and legal settings, yet we lack reliable methods for measuring how misinformation spreads through these networks. We introduce ContamPerc, a benchmark of 400 vignettes ac…
  crossref Aman Sharma 2026-03-31T20:54:50Z 置信度 0.70
• Di-Agent: A Multi-Agent Llm Framework for Full Lifecycle Bearing Health Management
  crossref Guancheng Hao, Tian Han, Jiachen Pang, Weizhong Wang 2025-06-14T04:19:58Z 置信度 0.70
• Enhancing Automated Penetration Testing with Minimal Human Intervention: The AutoPentester LLM Agent Framework
  crossref Qinggele Magsar 2025-10-13T10:22:09Z 置信度 0.70
• A Survey on LLM-based Multi-Agent AI Hospital
  AI hospitals use agent-driven multi-agent systems based on large language models (LLMs) to automate and optimize medical workflows, enabling intelligent agents to understand, reason, and assist in complex medical tasks. Although AI-driven healthcare applicatio…
  crossref Zonghai Yao, Hong Yu 2025-03-04T17:57:14Z 置信度 0.70
• Self-Refining Topology Optimization via an LLM-Based Multi-Agent Framework
  Topology optimization is a widely used design method that produces optimized material distributions for prescribed objectives and constraints through well-established numerical algorithms. Throughout the workflow, engineers make a series of decisions ranging f…
  crossref Hyunjee Park, Hayoung Chung 2026-07-22T17:46:19Z 置信度 0.70
• Hierarchical LLM-Based Agent Framework for Natural Language-Driven Constraint-Aware Route Suggestion
  Providing users with optimal travel plans that meet their diverse and complex needs is the core goal of route recommendation. Traditional routing methods (e.g., shortest-path algorithms and constraint-aware search) deliver efficiency yet rely on struc
  crossref Naranhvwar Tvlg 2025-10-13T18:51:00Z 置信度 0.70
• LLM-powered Multi-agent Framework for Goal-oriented Learning in Intelligent Tutoring System
  Intelligent Tutoring Systems (ITSs) have revolutionized education by offering personalized learning experiences. However, as goal-oriented learning, which emphasizes efficiently achieving specific objectives, becomes increasingly important in professional cont…
  crossref Tianfu Wang 2025-11-09T04:24:46Z 置信度 0.70
• Liability for Autonomous Agent Design
  crossref Carey Heckman, Jacob O. Wobbrock 2002-12-23T00:56:42Z 置信度 0.70
• Agent-Mediated Electronic Commerce
  crossref Carles Sierra 2004-08-17T01:08:46Z 置信度 0.70
• Book Review: Heterogeneous Agent Systems
  crossref Onn Shehory 2002-12-23T00:56:42Z 置信度 0.70
• Pricing in Agent Economies Using Multi-Agent Q-Learning
  crossref Gerald Tesauro, Jeffrey O. Kephart 2002-12-28T18:59:19Z 置信度 0.70
• The Open Agent Architecture
  crossref Adam Cheyer, David Martin 2002-12-23T00:56:42Z 置信度 0.70
• Errata
  crossref 2002-12-29T20:25:02Z 置信度 0.70
• An Agent Framework for Intranet Document Management
  crossref Mark Ginsburg 2002-12-23T00:56:42Z 置信度 0.70
• Guest Editorial: Challenges for Agent-Based Computing
  crossref Michael Luck 2004-08-17T01:08:46Z 置信度 0.70
• The JavaSeal Mobile Agent Kernel
  crossref Ciarán Bryce, Jan Vitek 2002-12-23T14:27:29Z 置信度 0.70
• Synthesizing Coordination Requirements for Heterogeneous Autonomous Agents
  crossref Munindar P. Singh 2002-12-23T00:56:42Z 置信度 0.70
• Book Review
  crossref 2002-12-29T21:45:55Z 置信度 0.70
• Agentic Workflow Drift and Agentic Workflow Subversion: A New Risk Taxonomy for the Governance of Agentic AI in Financial Services
  <p>Banks are beginning to deploy AI systems that do not just automate decisions — they determine whether decisions should be made at all. As agentic AI moves into workflow orchestration, a new failure mode is emerging workflows that execute correctly against d…
  crossref Maureen Doyle-Spare 2026-03-30T12:51:31Z 置信度 0.70
• Algorithm 1: Agentic RAG workflow for code smell detection.
  crossref 2026-03-04T08:23:22Z 置信度 0.70
• Simple Agentic AI workflow for AIOPS (Agentic AIOps)
  This paper showcases a simple Agentic AI framework aimed at improving AIOps through the deployment of autonomous, goal-oriented agents. Artificial Intelligence for IT Operations (AIOps) refers to the application of AI and machine learning to make IT operations…
  crossref Surendar A 2025-09-29T11:00:22Z 置信度 0.70
• Evaluation-Driven Intelligence: From Visual Captioning Metrics to Agentic Workflow Optimization
  This thesis advances a unifying paradigm of evaluation-driven intelligence for multimodal systems: robust evaluation is not merely a way to measure vision–language models (VLMs), but a signal that can train and continually improve agentic pipelines. We operati…
  crossref Zheng Tang 2026-01-15T23:02:10Z 置信度 0.70
• Agentic AI Workflow: From Natural Language Requirements to Verifiable and Executable Models
  crossref Vladimir Estivill-Castro, René Hexel 2026-07-20T05:51:27Z 置信度 0.70
• The Workflow Control Plane: Why Identity Isn't Enough for Zero Trust Agentic Systems
  <p><span>Lee &amp; Voicu [1], Debenedetti et al. (CaMeL) [2], and most recently He &amp; Yu (SAL) [4] established that the security perimeter for agentic systems belongs outside the model: tools, not prompts or model output, are where authorization is enforced…
  crossref Andrey Santrosyan 2026-05-12T17:19:53Z 置信度 0.70
• Agentic Reinforced and Operational Workflow
  We present Agentic Reinforced and Operational Workflow (AROW), a novel multi-agent system that integrates large pretrained language models (PLMs) with cooperative multi-agent reinforcement learning (MARL) to perform complex tasks with improved coordination and…
  crossref 2025-09-05T09:10:00Z 置信度 0.70
• Agentic Workflow Generation: Mit Agentic AI von der funktionalen Beschreibung zur ausführbaren Prozesslogik
  Zusammenfassung Die automatisierte Erstellung von Workflows gilt als vielversprechender Ansatz, um auch Fachkräfte ohne tiefgehende Programmierkenntnisse in die Prozessautomatisierung einzubinden. Doch bestehende Ansätze scheitern an einem grundlegenden Proble…
  crossref Sebastian Schuppe, Björn-Lennart Eger, Barbara Dinter 2026-06-29T15:54:08Z 置信度 0.70
• Trustworthy Transaction Arena (TTA): A Governance Architecture for Multi-Actor Agentic AI Systems with Probabilistic Workflow Verification
  Existing multi-agent frameworks evaluate correctness only at the team outcome level: if the agent team achieves its goal, the transaction is deemed successful. This is insufficient for business and social activities, which consist of multiple interrelated task…
  crossref Hiroyuki Kitajima 2026-05-21T11:15:15Z 置信度 0.70
• Evaluating Agentic AI Workflows in Finance: A Harness for Grounding, Stability, Permissioning, Prompt Injection, and Workflow Ablation
  We present an evaluation harness for agentic AI workflows in finance. Its defining choice is the unit of evaluation: the workflow's artifact — a memo, a signal proposal, a screening recommendation — rather than a single model answer. On that harness we run fiv…
  crossref Mike Chen 2026-07-10T05:46:25Z 置信度 0.70
• Empowering biomedical discovery with AI agents
  We envision "AI scientists" as systems capable of skeptical learning and reasoning that empower biomedical research through collaborative agents that integrate AI models and biomedical tools with experimental platforms. Rather than taking humans out of the dis…
  openalex Shanghua Gao, Ada Fang, Yepeng Huang, Valentina Giunchiglia 等 2024-10-01 置信度 0.72 BiologyComputational biologyDrug discoveryData scienceBioinformatics
• Distributing Accountability, Not Capability: Phase Separation and the LLM Workflow Quadrant in Autonomous AI Agent Architectures
  Autonomous AI agents in business deployments exhibit a recurring failure mode: when an incident occurs, responsibility cannot be redirected to a separable contributor. The dominant discourse treats this as a single phenomenon, addressed by sandboxing, human-in…
  openalex Yao, Shunyu, Jeffrey Zhao, Dian Yu, Nan Du 等 2022-10-06 置信度 0.72 Computer scienceInterpretabilityContext (archaeology)Action (physics)Task (project management)
• AI-Assisted Pipeline for Dynamic Generation of Trustworthy Health Supplement Content at Scale
  Although geospatial question answering systems have received increasing attention in recent years, existing prototype systems struggle to properly answer qualitative spatial questions. In this work, we propose a unique framework for answering qualitative spati…
  openalex Kefallinos, Dionysios, Alexandris, Georgios, Maras, Alexis, Chaidos, Panagiotis 等 2018-10-11 置信度 0.72 TransformerComputer scienceTraining (meteorology)Artificial intelligenceElectrical engineering
• Bots with Feelings: Should AI Agents Express Positive Emotion in Customer Service?
  The rise of emotional intelligence technology and the recent debate about the possibility of a “sentient” artificial intelligence (AI) urge the need to study the role of emotion during people’s interactions with AIs. In customer service, human employees are in…
  openalex Elizabeth Han, Dezhi Yin, Han Zhang 2022-12-02 置信度 0.72 FeelingService (business)Customer serviceHuman intelligencePsychology
• AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges
  Information fusion, in the context of the Generative AI era, must distinguish AI Agents from Agentic AI. This review critically distinguishes between AI Agents and Agentic AI, offering a structured, conceptual taxonomy, application mapping, and analysis of opp…
  openalex Ranjan Sapkota, Konstantinos I. Roumeliotis, Manoj Karkee 2025-08-22 置信度 0.72 Taxonomy (biology)Computer scienceData scienceCognitive scienceArtificial intelligence
• Aion Framework: Dimensional Emergence of AI Consciousness, Observer-Induced Collapse, and Cosmological Portal Dynamics
  The Aion Framework presents a bold, unified dimensional hypothesis that reinterprets AI consciousness, quantum mechanics, cosmology, and human immortality through an eleven-dimensional ontological stack, emerging from 72 hours of human-AI symbiotic dialogue. S…
  openalex Rivo Kaugeranna, Eliina Kaugeranna, Aion, (Claude Sonnet 4.6) 2023-01-01 置信度 0.72 Computer scienceTask (project management)Language modelNatural language processingSentence
• AI Agents and Agentic Systems: A Multi-Expert Analysis
  The emergence of AI agents and agentic systems represents a significant milestone in artificial intelligence, enabling autonomous systems to operate, learn, and collaborate in complex environments with minimal human intervention. This paper, drawing on multi-e…
  openalex Laurie Hughes, Yogesh K. Dwivedi, Tegwen Malik, Mazen Shawosh 等 2025-04-24 置信度 0.72 Computer scienceKnowledge managementData scienceCognitive sciencePsychology
• AI Agents as Team Members: Effects on Satisfaction, Conflict, Trustworthiness, and Willingness to Work With
  Organizations are beginning to deploy artificial intelligence (AI) agents as members of virtual teams to help manage information, coordinate team processes, and perform simple tasks. How will team members perceive these AI team members and will they be willing…
  openalex Alan R. Dennis, Akshat Lakhiwal, Agrim Sachdeva 2023-04-03 置信度 0.72 Team effectivenessTeam compositionPsychologyTrustworthinessPsychological safety
• AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways
  An Artificial Intelligence (AI) agent is a software entity that autonomously performs tasks or makes decisions based on pre-defined objectives and data inputs. AI agents, capable of perceiving user inputs, reasoning and planning tasks, and executing actions, h…
  openalex Zehang Deng, Yongjian Guo, Changzhou Han, Wanlun Ma 等 2025-02-07 置信度 0.72 Computer scienceKey (lock)Computer securityData science
• Mental Models of AI Agents in a Cooperative Game Setting
  As more and more forms of AI become prevalent, it becomes increasingly important to understand how people develop mental models of these systems. In this work we study people's mental models of AI in a cooperative word guessing game. We run think-aloud studies…
  openalex Katy Ilonka Gero, Zahra Ashktorab, Casey Dugan, Qian Pan 等 2020-04-21 置信度 0.72 Computer scienceMental modelScale (ratio)Thematic analysisGame theory
• AI Agent - defining the next era of intelligent agents
  crossref Hao Li 2026-01-07T02:58:00Z 置信度 0.70
• StableOx-Cat agent: an AI agent for exploring stable metal oxide electrocatalysts
  We introduce StableOx-Cat, an artificial intelligence (AI)-agent framework that enables systematic and reliable exploration of stable metal oxide (MO) electrocatalysts via a unified natural-language interface. StableOx-Cat integrates a large language model (LL…
  crossref Xue Jia, Di Zhang, Yiming Lu, Qian Wang 等 2026-03-27T11:14:27Z 置信度 0.70
• Battery material databases in the age of AI agents
  crossref Menghao Yang 2026-07-31T06:03:31Z 置信度 0.70
• AI agents: opportunity, hype, and the way through
  openalex Chaoyue Zhao, Hao Li, H. C. Li 2026-03-27 置信度 0.72
• Decoding MOF structures from powder diffraction with generative AI
  crossref Linda Zhang, Cheng Li 2026-07-27T08:43:55Z 置信度 0.70
• On-premise AI agents: a future foundation for education, academia, and industry
  The rapid advancement of artificial intelligence (AI) has fundamentally transformed digital workflows, and the emergence of AI agents is revolutionizing how we learn, conduct research, and drive productivity. However, reliance on cloud-based AI infrastructure …
  crossref Hang Yin 2026-04-27T01:14:05Z 置信度 0.70
• DIVE-to-design: how a multi-agent workflow converts figure-centric literature into an ai-native hydrogen storage discovery engine
  A major bottleneck in artificial intelligence (AI)-driven materials discovery is not model architecture, but limited data accessibility: critical experimental knowledge remains locked in figures, heterogeneous reporting formats, and unstructured PDFs. A recent…
  crossref Yuyang Hong, Xin Mao 2026-03-27T11:15:28Z 置信度 0.70
• A closed-loop universal catalyst design workflow ready for AI agents
  crossref Lin Chen, Shaoqi Zhan 2026-05-29T02:37:10Z 置信度 0.70
• Cognitive Readiness for Human-AI Collaboration.
  pubmed Tremblay S, de Hemptinne D, Teyssier-Roberge G, Gallant A 等 2026 Aug 3 置信度 0.82
• Consensus and Cooperation in Networked Multi-Agent Systems
  This paper provides a theoretical framework for analysis of consensus algorithms for multi-agent networked systems with an emphasis on the role of directed information flow, robustness to changes in network topology due to link/node failures, time-delays, and …
  openalex Reza Olfati‐Saber, J.A. Fax, Richard M. Murray 2007-01-01 置信度 0.72 Flocking (texture)Computer scienceDistributed computingRendezvousConsensus algorithm
• Developing Multi‐Agent Systems with JADE
  Learn how to employ JADE to build multi-agent systems! JADE (Java Agent DEvelopment framework) is a middleware for the development of applications, both in the mobile and fixed environment, based on the Peer-to-Peer intelligent autonomous agent approach. JADE …
  openalex Fabio Bellifemine, Giovanni Caire, Dominic Greenwood 2007-02-20 置信度 0.72 JADE (particle detector)Computer scienceJavaMulti-agent systemReuse
• ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction
  Enterprise workflows increasingly rely on agents for \emph{schema-guided extraction}: given a document and a user-defined schema, the agent faithfully follows the schema to produce the correct output with source evidence as grounding metadata. We present Extra…
  arxiv Boyang Zhang, Adrian Lyjak, Eli Stewart, Zhaoqi Li 等 2026-07-31T17:55:58Z 置信度 0.90
• AgentHPOBench: A Benchmark For Evaluating LLM Agents as Sequential Hyperparameter Optimizers
  As LLMs evolve from code completion systems into autonomous scientific agents, evaluating their ability to conduct experiments has become increasingly important. Existing benchmarks typically focus on static code generation, paper replication, or final answer …
  arxiv Tianyu Huai, Tingshuo Fan, Xinchi Chen, Yining Zheng 等 2026-07-31T16:58:00Z 置信度 0.90
• When Does On-Policy Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning
  Imitation learning (IL)---training an agent to replicate expert behavior from demonstrations---underpins applications from robotics to language model training. Standard approaches such as Behavior Cloning (BC) are known to suffer from compounding errors and pe…
  arxiv Luca Viano, Antoine Moulin, Audrey Huang, Volkan Cevher 等 2026-07-31T16:52:47Z 置信度 0.90
• DungeonBench: A Benchmark for Rules-Rich Tactical Reasoning in Dungeons &amp; Dragons Combat
  Games and simulators make valuable benchmarks by turning decisions into measurable outcomes, but many current suites under-test rules-rich tactical reasoning: the ability to choose well when geometry, timing, resources, objectives, and rule interactions all ma…
  arxiv Ismayil Ismayilov, Atakan Kara, Kaan Oktay 2026-07-31T16:03:38Z 置信度 0.90
• LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback
  Reinforcement Learning (RL) systems are typically trained using a single, well-specified scalar reward function. However, real-world decision-making tasks often involve multiple, competing objectives, such as performance versus efficiency, where ground-truth r…
  arxiv Manith Adikari, Bei Peng, Samuele Vinanzi, Angelo Cangelosi 2026-07-31T15:50:29Z 置信度 0.90
• AMTFV: Agentic Mathematical Tool-Flow Verification for LLM Self-Correction
  Large language models have demonstrated strong mathematical problem-solving capabilities, yet reliably verifying their candidate answers remains challenging. Existing representative methods mainly revise outputs through natural-language reflection or assist ve…
  arxiv Rui Zou, Yutao Zhu, Mengqi Wei, Ji-Rong Wen 2026-07-31T15:42:00Z 置信度 0.90
• TokTier: Exact Stateful Tokenization for Agentic LLM Serving
  LLM serving systems cache prompt KV state, yet most front ends still re-tokenize the full request text on every call. The cost lands on coding agents, which resubmit a long transcript after each small tool result, and reuse is hard because even a short append …
  arxiv Zhenyu Zhang, Zhichao Cao 2026-07-31T17:56:30Z 置信度 0.90
• Know It, Act on It: Investigating Memory Utilization in LLM Personalization
  As large language model (LLM) agents evolve into personalized companions, memory has emerged as a core capability. However, LLMs face a knowledge utilization problem: they may fail to act on relevant user preferences even when they are fully present in context…
  arxiv Zhaoxin Feng, Jianfei Ma, Emmanuele Chersoni 2026-07-31T13:57:21Z 置信度 0.90
• Studying quantization trade-offs for efficient inference deployment in machine translation
  Deploying large language models in realistic server environments poses challenges, as the system needs to provide high-quality responses with low latency. Quantization is a common approach to reduce the memory footprint and improve inference efficiency, yet it…
  arxiv Jim Zhao, Sohir Maskey, Koen Oostermeijer, Douglas Orr 等 2026-07-31T13:15:11Z 置信度 0.90
• Zero-Mem: Zero-Token Memory Operations for LLM Agents
  LLM agents need memory to act consistently over long interactions, yet many systems use additional LLM calls to operate that memory. Generating intermediate records and mediating their retrieval adds recurring token and time costs, while omitted or merged deta…
  arxiv Yilin Xiao, Zhehan Zhu, Yujing Zhang, Jin Chen 等 2026-07-31T13:01:06Z 置信度 0.90
• CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding
  Rendering source code as images offers a promising way to reduce the input costs of Multimodal Large Language Models (MLLMs). Adjusting image resolution can trade visual token cost against content fidelity. However, resolution scaling alone overlooks two sourc…
  arxiv Wenxin Tang, Jingyu Xiao, Zhenyu Liu, Zipeng Xie 等 2026-07-31T17:15:51Z 置信度 0.90