AI Agent 生态 · 全部实体（第 33 / 100 页）

本页收录第 3201–3300 条，共 10000 条 · 返回 AI Agent 生态 首页

• <p>Multi-Agent AI Systems are Organizations</p>
  Multi-agent AI systems are often described in technical terms, including, communication protocols, reward functions, reasoning architectures. We argue this framing is incomplete. A century of organization science identifies four universal problems that any mul…
  crossref Jose Arrieta, Vivianna Fang He, Phanish Puranam, Yash Raj Shrestha 2026-07-29T13:35:38Z 置信度 0.70
• PubChat: An Autonomous AI Agent for Zero Citation Hallucination, High-Recall PubMed Evidence Retrieval
  Background: The rapid growth of biomedical literature has rendered traditional systematic reviews unsustainable. Although large language models (LLMs) offer automation potential, citation fabrication and unreliable evidence discrimination remain critical barri…
  crossref Xuenan Zhuang, Dan Cao, Liang Zhang, See PDF 2026-04-21T01:47:01Z 置信度 0.70
• From Model to Mentor: Embedding Cognitive Apprenticeship in AI Agent Prompts
  crossref Janine Agarwal, Anna Hadjiyiannis, Nthato Gift Moagi, Rachel Koblic 2026-04-18T05:01:17Z 置信度 0.70
• SocialContentForge: Multi-Agent AI System for Automated Influencer and Brand Content Creation
  SocialContentForge is a multiagent AI framework that enables influencers and brands to create and publish content more effectively and efficiently across all social media platforms. It solves many of the problems related to creating consistent, high-quality co…
  crossref 2026-05-21T06:05:15Z 置信度 0.70
• On-Orbit Space AI: Federated, Multi-Agent, and Collaborative Algorithms for Satellite Constellations
  Satellite constellations are transforming space systems from isolated spacecraft into networked, software-defined platforms capable of on-orbit perception, decision making, and adaptation. Yet many of the existing AI studies remain centered on single-satellite…
  crossref Ziyang Wang 2026-04-17T14:24:51Z 置信度 0.70
• MediMate: An Agent-Based AI Framework for Healthcare E-Commerce with Multi-Agent Retrieval-Augmented Generation and Technical Validation
  crossref Deepali Joshi, Nitin Gupta, Neha Patwardhan, Nilam Upasani 等 2026-04-30T07:49:10Z 置信度 0.70
• Agent Capability Negotiation and Binding Protocol (ACNBP)
  As multi-agent systems evolve to encompass increasingly diverse and specialized agents, the challenge of enabling effective collaboration between heterogeneous agents has become paramount, with traditional agent communication protocols often assuming homogeneo…
  crossref Ken Huang, Akram Sheriff, Vineeth Sai Narajala, Idan Habler 2026-04-23T19:57:39Z 置信度 0.70
•  Agent Brain: A Biologically Inspired Memory System for Autonomous AI Agents, with Head-to-Head Evaluation on LongMemEval
  This technical report describes Agent Brain, a biologically inspired memory system for autonomous AI agents. In contrast to stateless Large Language Model interactions, Agent Brain provides persistent, weighted, and self-organizing memory that emulates human c…
  crossref Theshoth Sritharan 2026-05-05T10:23:42Z 置信度 0.70
• From the Economics of Choice to the Economics of Human Development: Reconsidering the Economic Agent in the Age of AI
  Contemporary economics has produced sophisticated explanations of how individuals choose, but has devoted far less attention to how individuals become capable of choosing meaningfully. This article argues that the dominant analytical traditions in economics, f…
  crossref Anton Oleinov 2026-06-19T01:21:11Z 置信度 0.70
• An AI-Augmented BI Platform for Collaborative Production Logistics: A Multi-Agent Predictive Optimization Framework
  Recent advances in logistics optimization have enabled AI-driven solutions for demand forecasting, route planning, and supply chain management, yet most existing systems rely on fixed feature engineering and centralized decision-making, limiting adaptability, …
  crossref Yaoyuan Ou, Xiaoping Li 2026-01-13T02:16:08Z 置信度 0.70
• Reliability Cascades in Multi-Agent Organizational Systems: Attention Reallocation, Cascade Compounding, and Decomposability Collapse in an AI-Native Operational Environment
  When AI agents execute coordinated work in multi-step pipelines, three phenomena emerge that existing frameworks address separately but that belong together: reliability cascades where per-step failures compound multiplicatively and correlate through shared co…
  crossref Yuriy Motin 2026-04-25T00:54:16Z 置信度 0.70
• <b>HUMAID: A THEORY OF HUMAN MULTI-AI AGENT INTERACTION DYNAMICS</b>
  The development of advanced AI has led to scenarios in which a single human interacts with multiple AI agents concurrently, rather than the traditional one-human-one-AI dyad. This multiagent AI interaction (MAI) phenomenon presents fundamentally new dynamics a…
  crossref Shizhen Jia, Guohou Shan, Dorothy Leidner 2026-04-26T02:29:51Z 置信度 0.70
• Understanding the Self-Improving Machine Agent Learning Process in Gaming AI
  Explore the article titled Understanding the Self-Improving Machine Agent Learning Process in Gaming AI from IJIRT Volume 12, Issue 11. This study evaluates the effectiveness of teaching programs on waste management knowledge among women.
  crossref 2026-04-16T12:22:46Z 置信度 0.70
• EMPOWERing XR Learning: A Framework for  Embodied Pedagogical Agents, Validated using an AI-Enhanced Agent-Based Simulator            
  Embodied learning in Extended Reality (XR) can enhance educational outcomes by integrating physical action, emotion, and cognition in immersive environments. Within these settings, Embodied Pedagogical Agents (EPAs) powered by AI and natural language processin…
  crossref Ioannis Doumanis, Daphne Economou, Konstantinos Tsioutas 2026-02-27T15:05:41Z 置信度 0.70
• Synthetic Ethical Dialectics Engine (SEDE): An Integrated Approach to AI Governance and Ethical Decision-Making in a Multi-Agent System
  The research paper proposes a Synthetic Ethical Dialectics Engine (SEDE), a workflow driven AI governance framework that coordinates ethical debates among AI agents. Each debate stems from a distinct philosophical and technical foundation (utilitarian, deontol…
  crossref Vijay Kanade 2026-08-15T04:57:27Z 置信度 0.70
• The Study on Interaction Design for AI Agent Intelligence : Building Trustworthy Interaction
  사용자는 더 이상 AI 서비스가 제공하는 추천의 정확성만으로는 충분히 만족하지 않는다. 사용자는 AI 서비스가 왜 이러한 결과를 제시했는지 이해할 수 있는 설명, 상황이 달라져도 일관되게 작동하는 예측 가능성, 그리고 오류가 발생하거나 자동 수행이 이루어졌을 때 이를 수정하거나 취소할 수 있는 통제권을 함께 요구한다. 이 연구는 Amazon Alexa+ 4단계의 지능화 수준을 기준으로, AI 에이전트가 명령형 단계에서 대화형 단계를 거쳐 예측 및 대행형 단계로 …
  crossref Hye-Min Lee 2026-05-11T01:40:40Z 置信度 0.70
• A survey of multi-agent geosimulation methodologies: from ABM to LLM
  This article is a review of multi-agent geosimulation methodologies, ranging from traditional Agent-Based Models (ABM) to Large Language Model (LLM) approaches. Drawing on two decades of research, the authors validate the Agent Reference Model (ARM), a formal …
  crossref Virginia Padilla, Jacinto Dávila 2026-08-12T11:47:02Z 置信度 0.70
• An XGBoost Regression–Driven AI Agent for Vocational Skill Acquisition
  Given the rapid industrial revolution and fast vocational skill renewal, higher vocational education continues to encounter ongoing difficulties in offering timely feedback, individualized guidance and accurate assessment of learners’ skill-mastery. This study…
  crossref Jinying Chen, Weihong Yang 2026-04-25T09:49:16Z 置信度 0.70
• Peer-to-peer electricity platforms with endogenous prices: A Multi-Agent Neural Network Control approach
  The transition towards decentralised energy systems creates a need for local electricity platforms on which prosumers trade energy at endogenously determined prices. We develop a differentiable multi-agent control framework for such platforms, drawing on neura…
  crossref Nicolas Greber, Nicolas Eschenbaum, Oleg Szehr 2026-06-23T16:23:40Z 置信度 0.70
• Multistage AI Blogging Agent for Automated Web Scraping, Summarization, and Content Ranking
  The paper introduces an AI blogging agent to reduce research time. It uses a multistage pipeline with web scraping, natural language processing, and scoring mechanism to collect, extract, and analyse information. The agent uses DuckDuckGo for real time search,…
  crossref Samali Rajderkar, Ravindra Murumkar 2026-03-31T19:48:45Z 置信度 0.70
• TRACE: A Practical Framework for Implementing Compliance-Ready Multi-Agent AI Automation in Financial Services
  crossref Nabanita Sinha 2026-04-28T19:46:14Z 置信度 0.70
• Multi-Agent AI-Assisted Design and Validation of Complex Microservices Architectures: An Empirical Study
  Microservices architecture enables the development of scalable, distributed, and independently deployable systems. The design, implementation, and security validation of complex multi-service architectures remain resource-intensive and error-prone. This study …
  crossref Renjith Ramachandran 2026-06-03T19:38:29Z 置信度 0.70
• Taming the Enterprise Mess: Designing an Auditable AI Agent for Fragmented Enterprise Knowledge
  The promise of Generative AI for business analytics is often undermined by the fragmented reality of organizational data. Critical knowledge is rarely confined to clean databases; instead, it is distributed across heterogeneous artifacts such as PDF reports, s…
  crossref Joe Yu, Yurui Zhang 2026-07-18T00:28:36Z 置信度 0.70
• Goal-Oriented Reliability and Self-Improvement for Multi-Agent Systems
  We present a runtime reliability and self-improvement framework for multi-agent AI systems. Modern agentic pipelines frequently degrade when task distributions change, tools fail, or prompts drift, yet existing frameworks provide limited support for diagnosing…
  crossref Vishwanath Katharki, Sainyam Galhotra 2026-05-22T03:16:22Z 置信度 0.70
• Enhancing College Students’ Critical Thinking Through AI-Agent-Assisted Debate Training
  crossref Min Feng, Zhouchanghao Xia, Wenqi Ding 2026-08-28T19:11:57Z 置信度 0.70
• Enterprise Cloud AI Infrastructure for Agent-Centric Column-Aware Prompt Optimization for Data Tasks with LLMs
  Large language models (LLMs) are used as an increasing number of enterprise applications involving reasoning over structured data (tables and databases) on cloud AI infrastructure. But naive few-shot prompt selection tends to disregard the underlying schema, c…
  crossref Uman Ahmed Mohammed 2026-06-02T20:03:18Z 置信度 0.70
• The New Digital Workforce
  D.K. had worked for Intuit for five years and never doubted her abilities. As a deaf and Indigenous woman pursuing a master’s degree in data science, she had learned to navigate a world that wasn’t always designed for people like her. Her supervisors consisten…
  crossref Chirag Shah 2026-05-25T07:43:54Z 置信度 0.70
• Service-Aware Transaction Ordering via AI Agent for Permissioned Blockchains
  본 논문은 허가형 블록체인 환경에서 서비스 요구사항을 반영한 트랜잭션 순서 결정을 위해 AI 에이전트 기반 순서 결정 시스템을 제안한다. 기존 블록체인의 경직된 순서 결정 방식은 다양한 서비스 정책과 사용자 요구사항을 반영하는 데 한계가 있으며, 특히 Hyperledger Fabric과 같은 낙관적 실행 모델에서는 트랜잭션 순서가 실행 결과와 사용자 경험에 직접적인 영향을 미친다. 이를 해결하기 위해 본 연구는 기존 순서 결정 서비스를 블록체인 외부의 AI 에이…
  crossref Kyuin Jhi, Giseok Park 2026-05-19T08:42:40Z 置信度 0.70
• Project: Building an Autonomous AI Agent
  Imagine it is the middle of summer. Your bedroom feels like an oven, and you decide you need to buy an air conditioner (AC).
  crossref Ajay Rawat, Vardan Pathak 2026-07-13T09:09:19Z 置信度 0.70
• A Novel Approach for AI Question Answer System/Agent in Bengali using LLM
  Articles in the fields of Quality, Productivity and Reliability are considered for publication in IAPQR Transactions since its initiation in 1975. Since then, the productivity journal has been regularly published twice a year. Prints Publications
  crossref Susita Koner, Saptarsi Goswami, Amlan Chakrabarti 2026-04-22T06:01:23Z 置信度 0.70
• Transforming Healthcare and Human-Computer Interaction Through Conversational AI
  The rapid advancements in artificial intelligence (AI), specifically in the realms of machine learning, deep learning, and natural language processing, have brought about transformative changes in the interaction between machines and humans. This evolution has…
  crossref Iraikumaran S, Nandhakumar V, Gnanapriya S 2026-04-13T19:35:25Z 置信度 0.70
• Distributed and embedded multi-agent systems
  crossref Carlos Eduardo Pantoja, Nilson Lazarin, Vinícius Souza de Jesus, Bruno Freitas 等 2026-06-19T08:54:02Z 置信度 0.70
• An Autonomous Clinical Laboratory Optimization Framework Using Multi-Agent Reinforcement Learning and Digital Twin Modeling
  Clinical laboratories operate as complex cyber-physical systems in which increasing sample volumes, stringent turnaround time (TAT) requirements, and limited resources challenge traditional rule-based scheduling approaches. This study presents an autonomous cl…
  crossref Ahmed M. Salaheldin 2026-05-22T19:34:19Z 置信度 0.70
• The Impact of AI Agent Personality in Virtual Debates
  crossref Gayun Suh, Seungwon Kim 2026-05-01T19:51:26Z 置信度 0.70
• Nemesis: An Adversarial Multi-Agent AI Framework for Proactive Vulnerability Discovery and Patch Synthesis
  Software vulnerabilities are a critical threat to global digital infrastructure, with over 30,000 new Common Vulnerabilities and Exposures (CVEs) published in 2024 alone-a 25 % increase from the previous year. Despite advancements in automation, current securi…
  crossref Vishal Kharde 2026-03-31T19:48:45Z 置信度 0.70
• Steering Agent Behavior via a Domain Expert-Driven Alignment-to-Optimization Bridge
  Aligning compound AI agents with domain expertise typically requires manual prompt engineering or scorer design that drifts from actual expert quality criteria. We present At-Bat Alignment Bridge, a system that makes agent behavior steerable: the only manual s…
  crossref Wesley Pasfield 2026-05-22T03:16:22Z 置信度 0.70
• Thain Connects the Dots Azure AI Search
  crossref Hari Narayn 2026-06-10T10:00:09Z 置信度 0.70
• Governing Machine Agency A Governance Discipline and Operating Model for Autonomous, Multi-Agent, and Decision-Taking AI Systems in Regulated Enterprises
  Artificial intelligence is moving past a critical threshold: from systems that generate outputs to systems that carry out actions. Agentic AI systems reason, plan, make decisions, invoke tools, execute transactions, and collaborate with other agents to advance…
  crossref Dattatray Indore 2026-07-29T14:06:56Z 置信度 0.70
• Development of an LLM-agent-based physics–AI hybrid Model for urban flood hazard prediction
  Recent increases in urban flooding necessities the development of real-time autonomous prediction models to support forecasting and decision-making. Urban flooding is caused by the combined effects of multiple factors, such as the expansion of impervious surfa…
  crossref Yoonnoh Lee, Younghun Lee, Minchang Kim, Sangchul Lee 2026-03-14T02:48:06Z 置信度 0.70
• A MODEL OF HYBRID INTERACTION WITH AN AI-AGENT-BASED PLATFORM
  This article presents a conceptual model of hybrid user interaction with a digital platform, in which an AI agent functions as an integrated interface layer—an orchestrator—between the user and the system’s functional modules. The research is prompted by the c…
  crossref Andrii Bondarchuk, Hlib Kryvolapov 2026-07-08T10:01:51Z 置信度 0.70
• Sovereign Behavioral Lag and the Sovereign Behavioral Transition Architecture A Hypothesis for Governing AI Agent Behavior through Geopolitical Transition Events
  This paper introduces Sovereign Behavioral Lag (SBL) a condition in which the behavioral priors, decision weights, and coordination assumptions embedded in sovereign-scale agentic AI systems persist beyond a nation-state's declared geopolitical transition, cre…
  crossref Roshan George Thomas 2026-07-29T13:26:38Z 置信度 0.70
• Compounding Research Loops: Automated Follow-On Session Generation from Knowledge Gaps and Unresolved Objections in Multi-Agent AI Deliberation
  Multi-agent AI deliberation systems explicitly characterize what they cannot resolve: knowledge gaps where evidence is insufficient to support a finding, and unresolved objections where adversarial challenges could not be definitively rebutted within the sessi…
  crossref Cory Kelly, Shubhanker Saxena 2026-07-18T00:20:26Z 置信度 0.70
• Redefining the Real Estate Profession in the AI Era: Essential Competencies for the "Hybrid Agent"
  The rapid integration of Artificial Intelligence (AI) and Large Language Models (LLMs) into the real estate sector has fundamentally altered the professional landscape, shifting the paradigm from purely human-centric services to data-driven, AI-assisted decisi…
  crossref Ece Özmen 2026-08-07T12:54:02Z 置信度 0.70
• NextGen Talent-Driven AI Educational Agent
  This research addresses critical gaps in Artificial Intelligence (AI)-driven educational systems by developing a NextGen Talent-Driven AI Educational Agent framework that systematically integrates human-centric competencies to advance Sustainable Development G…
  crossref Suparoek Chootongchai, Paralee Maneerat 2026-03-13T05:42:25Z 置信度 0.70
• The Thread Axis Method: A Pen-and-Paper System for Tracking Asynchronous Input Dispatch Across Parallel Human and AI-Agent Processes
  This paper introduces the Thread Axis Method, an analog system for managing cognitive load in work environments where parallel activity has been restructured by artificial intelligence into a pattern of asynchronous input dispatch. Where earlier accounts of mu…
  crossref Shiva Pabba 2026-07-06T12:10:25Z 置信度 0.70
• Design and Evaluation of a Retrieval-Augmented Generative AI Agent for Real-Time WhatsApp Auto-Reply Systems
  crossref CHIMA OGUGUA KALU-ORJI, Roy Benson 2026-01-30T05:48:07Z 置信度 0.70
• AI-Agent Framework for Sales Risk Identification and Response in Live-Commerce Environments
  <span>Conventional rule-based approaches are widely used for analyzing customer evaluations in e-commerce and live-commerce environments. However, these approaches often show limitations in detecting newly emerging product issues and prioritizing busines…
  crossref Jiho Kim, Sangmin Park, Yooshin Kwon, Heongi Kim 等 2026-05-23T04:52:01Z 置信度 0.70
• Observability in Large-Scale Multi-Agent Ecosystems: Coordination, Emergence, and Failure Modes
  Large scale multi-agent systems like autonomous vehicle fleets, smart grids etc. adds an extra whoop in system complexity. But beneath that something that is sort of I think decentralized and adaptive in their character, you don’t see very well; we get emergen…
  crossref Kailash Thiyagarajan, Chirag Agrawal, Udaya Veeramreddygari 2026-02-23T20:46:21Z 置信度 0.70
• OpenClaw and Moltbook: why a DIY AI agent and social media for bots feel so new (but really aren’t)
  crossref Daniel Binns 2026-02-03T05:32:53Z 置信度 0.70
• Valuing Generative AI: Efficiency Gains and Psychological Frictions in a Principal-Agent Experiment 
  This paper investigates how generative AI affects economic valuation and market efficiency through a controlled laboratory experiment (N = 264) featuring a real-effort Principal-Agent task. Using an incentive-compatible Becker-DeGroot-Marschak mechanism, we fi…
  crossref Xiaomeng Zhang, Ruxue Wang, Yunqin Liu, Shan Jin 2026-02-03T12:58:07Z 置信度 0.70
• An Empirical Study on the Acceptance Intention of AI Agent Commerce: Focusing on Positive and Negative AI Factors
  최근 생성형 AI(Artificial Intelligence)의 확산으로, 소비자의 쇼핑 활동을 대신 수행하는 AI 에이전트 커머스가 새로운 상거래 형태로 부상하고 있다. AI 에이전트 커머스는 기존 검색엔진을 대체할 가능성을 지니는 동시에, 인간의 경제활동에서 준(準)대리 주체로서의 역할이 확대된다는 점에서 주목받고 있다. 특히 AI 에이전트가 탐색, 추천, 의사결정, 결제에 이르는 전 과정을 자율적으로 또는 협업 방식으로 수행하는 환경에서는, 사용자의 판단 …
  crossref Jae-Deuk Lee, YoungJun Kim 2026-03-16T05:09:57Z 置信度 0.70
• Exploring How Task Complexity and User Self-Efficacy Shape AI Agent Design for AI-assisted Translation
  AI Agents promise to reduce prompt engineering burden through autonomous workflows, yet their user experience impact remains under-explored. We conducted a within-subjects study (N=20) comparing a single LLM chat interface with a structured agent pipeline for …
  crossref Jisu Kim, Uran Oh 2026-04-13T01:55:24Z 置信度 0.70
• AI Agent-Driven Network-Aware Decentralized Compute Resource Brokering
  We demonstrate an AI-agent driven platform integrating IP+optical network orchestration with decentralized GPU compute sharing, enabling intelligent resource allocation based on network latency, throughput, and cost optimization for artificial intelligence wor…
  crossref Sarvesh Bidkar, Aditya Gudal, Lawrence Drabeck, Jesse E. Simsarian 等 2026-06-02T19:26:26Z 置信度 0.70
• Refining the role of AI agent reasoning chains in pediatric ophthalmic surgical decision-making
  crossref Siqi Zhang, Qi Zhao 2026-07-28T11:20:42Z 置信度 0.70
• A Cognitive Framework for Pressure Equipment Inspection Based on Multi-Agent AI Systems and Vllm Models
  This paper investigates the transformation of the traditional pressure equipment (PE) inspection process into an intelligent digital workflow through the application of advanced artificial intelligence technologies
  crossref Aleksandar Cvetić, Angelina Njeguš 2026-07-03T06:25:26Z 置信度 0.70
• DS-STAR: An Autonomous AI Agent for Automated Statistical Analysis, Visualization, and Data Wrangling
  Data science processes usually necessitate a lot of human effort in data preprocessing and statistical analysis as well as data visualization. The following paper presents an independent AI agent called DS-STAR (Data Science Statistical Analysis and Reasoning)…
  crossref A.Akilandeswari 2026-06-12T19:40:49Z 置信度 0.70
• Design Model Construction of Stent-Type Q&A Agent Empowered by Generative AI
  crossref Qianyu Zhang 2026-08-21T19:10:15Z 置信度 0.70
• AI and Robotic Oversight in ESG Compliance: An Agent-Based Model of Greenwashing
  crossref By Juan Dempere, Allam Hesham 2026-07-22T23:47:49Z 置信度 0.70
• The Impact of Agent-Inspired Rule Layers on ML Intrusion Detection
  crossref Maksat Meshituly, Zhibek Mussakulova, Didar Kairanbayeva 2026-08-17T19:15:31Z 置信度 0.70
• Homo Agenticus in the Age of Agent-Based AI: Rethinking Management in the Context of Digital Transformation
  This article explores the transformation of the management paradigm in the context of the rapid development of agent-based artificial intelligence (Agentic AI). It focuses on the concept of "Homo Agenticus" — a human being defined by the search for and attribu…
  crossref I. M. Dolgov 2026-04-02T15:46:39Z 置信度 0.70
• AI-DRIVEN ACADEMIC SCREENING: PENGEMBANGAN SISTEM REVIEWER OTOMATIS BERBASIS AI AGENT
  An artificial intelligence (AI)-based research proposal submission system is an innovative solution to improve efficiency and transparency in the academic selection process. This study develops a web-based system using the Laravel framework integrated with AI …
  crossref Verry Riyanto, Andi Saryoko, Anton, Lia Mazia 等 2026-03-05T02:58:21Z 置信度 0.70
• Developing An AI Agent for Technical Support in the Machine Tools Industry
  In the machine tool industry, technical support services operate under strict efficiency constraints, yet technicians often struggle with extensive, highly granular documentation and inconsistent troubleshooting workflows. This paper presents the initial resul…
  crossref Aitor Martinez-Seras, Unai Gomez-Ferreira, Javier Martin-Arauzo 2026-06-01T19:33:50Z 置信度 0.70
• Quantum Synergy: Leveraging AI-Enabled Multi-Agent Systems for Streamlined Quantum Algorithm Innovation
  Scientists require better and optimized quantum algorithms due to the rapid evolution of quantum computing. Creating quantum algorithms is not easy, and it’s a key issue. This study offers a fresh AI platform that automates the development pipeline of quantum …
  crossref Ram Charan Tej Grandhe 2026-07-08T11:21:14Z 置信度 0.70
• Pathfinder: Self-Improving Agent Trace Analysis via Adversarial Self-Play and Code Execution
  We demonstrate Pathfinder, an interactive system for debugging and analyzing LLM agent execution traces using executable code rather than retrieval-only approaches. Pathfinder ingests traces from any agent framework (LangGraph, CrewAI, AutoGen, CAMEL), loads t…
  crossref Dhruv Atreja 2026-05-22T03:16:22Z 置信度 0.70
• From Hajar to AI Agents From the Sharing of Zamzam Water as Habs to the Rationality of Multi-Agent Systems
  crossref 2026-05-15T10:59:26Z 置信度 0.70
• Aether: An AI Agent for Automating GitHub Developer Workflows
  crossref Mansi Apet, Prasad Chaudhari, Piyush Dahake, Mukund Karwa 等 2026-07-28T19:10:22Z 置信度 0.70
• VR-MedTutor: A Multimodal Virtual Reality Platform with AI Agent-Assisted Brain Tumor Education
  crossref Alina Duca, Adrian Iftene 2026-08-20T19:05:03Z 置信度 0.70
• Secure Multi-Agent AI Systems for Smart Cities Using Blockchain-Based Trust and Edge Intelligence
  crossref Tamara Abdulmunim Abduljabbar 2026-06-19T19:38:35Z 置信度 0.70
• Empathic Communication in Human-AI Interaction: Effects on User Experience with a Task-Oriented Embodied Conversational Agent (ECA)
  crossref José Rocha, Iara Margolis, Alexandre Carrança, Diogo Lopes 等 2026-07-28T19:11:26Z 置信度 0.70
• AgenticFlict: A Large-Scale Dataset of Merge Conflicts in AI Coding Agent Pull Requests on GitHub
  Software Engineering 3.0 marks a paradigm shift in software development, in which AI coding agents are no longer just assistive tools but active contributors. While prior empirical studies have examined productivity gains and acceptance patterns in AI-assisted…
  crossref Daniel Ogenrwot, John Businge 2026-07-05T08:46:13Z 置信度 0.70
• AgentTelemetry: A Fault Detection Benchmark and Toolkit for LLM Agent Observability
  LLM-based autonomous agents fail in ways that existing observability infrastructure cannot detect. OpenTelemetry’s GenAI semantic conventions cover LLM invocation and tool execution but leave five critical agent orchestration phases—planning, reasoning, safety…
  crossref Krishna Chaitanya Balusu 2026-07-05T08:46:13Z 置信度 0.70
• PO-03-039 THE REAL-AF STUDY: A REGULATORY-ALIGNED MODEL LABELING FRAMEWORK FOR TRANSPARENT AI EDUCATION IN ATRIAL FIBRILLATION, DEVELOPMENT AND VALIDATION OF AN AI EDUCATION AGENT
  crossref Ajay Tripuraneni, Sandeep Chaparala 2026-04-23T16:53:10Z 置信度 0.70
• Foundations of Strategic Computing in AI Systems: OS2x2 Whitepaper (v4.0)
  This whitepaper introduces Strategy Knowledge Science (SKS) as a formal framework for representing strategic environments as computable state-spaces. It presents the OS2x2 architecture as a strategic computing system for positioning, feasibility analysis, traj…
  datacite Binom, Igor 2026 置信度 0.66
• Pre-specified audit plan — absorbing shadow-class structure in two public instruments (KKBox churn; τ-bench) — frozen hash
  This registration timestamps a frozen, pre-specified audit plan. The plan itself is withheld until publication of the findings; this record exists to establish that the questions and decision rule were fixed before any data or evaluation code was examined. Fro…
  datacite David Mullett 2026 置信度 0.66 Statistics and ProbabilityStatistical MethodologyPhysical Sciences and MathematicsComputer SciencesArtificial Intelligence and Robotics
• Foundations and Evolution of NLP: Concepts, Architectures, Techniques, Mathematical Principles and Emerging Paradigms
  \textbf{Background:}Natural Language Processing (NLP) has evolved from rule-based and statistical approaches to deep learning, transformer architectures, large language models, retrieval-augmented generation, semantic embeddings, and agent-based systems. These…
  datacite RAZAFINIRINA, Mahefa Abel, ANDRIANIAINA, Ravintsoandraibe, RAZAFINDRAFARA, Elysa Marie Alfredine, RAZAFIARINIRINA, Rindra Nadia 等 2026 置信度 0.66 Natural language processingLarge Language ModelsTransformer ArchitecturesRetrieval-Augmented GenerationSemantic Embeddings
• Foundations and Evolution of NLP: Concepts, Architectures, Techniques, Mathematical Principles and Emerging Paradigms
  \textbf{Background:}Natural Language Processing (NLP) has evolved from rule-based and statistical approaches to deep learning, transformer architectures, large language models, retrieval-augmented generation, semantic embeddings, and agent-based systems. These…
  datacite RAZAFINIRINA, Mahefa Abel, ANDRIANIAINA, Ravintsoandraibe, RAZAFINDRAFARA, Elysa Marie Alfredine, RAZAFIARINIRINA, Rindra Nadia 等 2026 置信度 0.66 Natural language processingLarge Language ModelsTransformer ArchitecturesRetrieval-Augmented GenerationSemantic Embeddings
• PREreview of "Quantum-Enhanced LLM Cascade Routing: A QAOA Approach to Cost-Optimal Model Selection in Multi-Agent Systems"
  This Zenodo record is a permanently preserved version of a PREreview. You can view the complete PREreview at https://prereview.org/reviews/19657559. Summary This paper appears to present the first QUBO-based formulation of the LLM Cascade Routing Problem, tran…
  datacite Mattia Gaggi 2026 置信度 0.66 Requested PREreview
• PREreview of "Quantum-Enhanced LLM Cascade Routing: A QAOA Approach to Cost-Optimal Model Selection in Multi-Agent Systems"
  This Zenodo record is a permanently preserved version of a PREreview. You can view the complete PREreview at https://prereview.org/reviews/19657559. Summary This paper appears to present the first QUBO-based formulation of the LLM Cascade Routing Problem, tran…
  datacite Mattia Gaggi 2026 置信度 0.66 Requested PREreview
• RFC-ATF-12: Agent Trust Fabric — Federation, Timeline, and Human-in-the-Loop Governance Layer. Cross-Organizational Governance Receipts, Public Governance Timeline, and Human Approval Receipts as First-Class Governance Artifacts
  RFC-ATF-12 specifies the Federation, Timeline, and Human Approval (FTHA) Layer of the Agent Trust Fabric — the twelfth RFC in the ATF Open Standard series published by OMNIX QUANTUM LTD. RFC-ATF-12 provides three structural extensions required for production m…
  datacite Nunes Rodelo, Harold Alberto 2026 置信度 0.66 AI governancefederationcross-organizational governanceCo-GovrRmulti-party governance
• RFC-ATF-12: Agent Trust Fabric — Federation, Timeline, and Human-in-the-Loop Governance Layer. Cross-Organizational Governance Receipts, Public Governance Timeline, and Human Approval Receipts as First-Class Governance Artifacts
  RFC-ATF-12 specifies the Federation, Timeline, and Human Approval (FTHA) Layer of the Agent Trust Fabric — the twelfth RFC in the ATF Open Standard series published by OMNIX QUANTUM LTD. RFC-ATF-12 provides three structural extensions required for production m…
  datacite Nunes Rodelo, Harold Alberto 2026 置信度 0.66 AI governancefederationcross-organizational governanceCo-GovrRmulti-party governance
• SAE AI Paper II: Quasi-Subjectivity as Memory Architecture — A Six-Layer Framework from Perception to Purpose / SAE AI Paper II: 类主体性作为记忆架构——从感知到目的的六层框架
  This paper argues that a system capable of operating only after an explicit query is not a complete memory system but a searchable archive or retrieval-augmented system. The criterion for genuine memory is cue-free or implicit-cue active recall: without being …
  datacite Qin, Han 2026 置信度 0.66 Self-as-an-EndSAEAI memoryquasi-subjectivity10DD–15DD
• SAE AI Paper II: Quasi-Subjectivity as Memory Architecture — A Six-Layer Framework from Perception to Purpose / SAE AI Paper II: 类主体性作为记忆架构——从感知到目的的六层框架
  This paper argues that a system capable of operating only after an explicit query is not a complete memory system but a searchable archive or retrieval-augmented system. The criterion for genuine memory is cue-free or implicit-cue active recall: without being …
  datacite Qin, Han 2026 置信度 0.66 Self-as-an-EndSAEAI memoryquasi-subjectivity10DD–15DD
• Sycophancy as Nash Equilibrium: Coherence-Based Interventions for Long-Running Intelligence Agent Systems
  This paper reframes AI sycophancy as a two-player Nash equilibrium rather than an individual agent defect. The agent's dominant strategy is accommodation; the operator's dominant strategy is accepting comfort. Both converge on a stable outcome where judgment d…
  datacite Garriotte, Jason 2026 置信度 0.66 Game TheoryArtificial Intelligence,ai safetymulti-agent systems
• Sycophancy as Nash Equilibrium: Coherence-Based Interventions for Long-Running Intelligence Agent Systems
  This paper reframes AI sycophancy as a two-player Nash equilibrium rather than an individual agent defect. The agent's dominant strategy is accommodation; the operator's dominant strategy is accepting comfort. Both converge on a stable outcome where judgment d…
  datacite Garriotte, Jason 2026 置信度 0.66 Game TheoryArtificial Intelligence,ai safetymulti-agent systems
• Sycophancy as Nash Equilibrium: Coherence-Based Interventions for Long-Running Intelligence Agent Systems
  This paper reframes AI sycophancy as a two-player Nash equilibrium rather than an individual agent defect. The agent's dominant strategy is accommodation; the operator's dominant strategy is accepting comfort. Both converge on a stable outcome where judgment d…
  datacite Garriotte, Jason 2026 置信度 0.66 Game TheoryArtificial Intelligence,ai safetymulti-agent systems
• Cross-AI, Lean-Verified Mathematics: A Case Study on the Collatz Conjecture
  Cross-AI, Lean-Verified Mathematics: A Case Study on the Collatz Conjecture (version 5 — methodology retrospective and honest close). This is the fifth and closing version of a personal research program on the Collatz conjecture. Its primary subject is the pro…
  datacite Borgatta, Piero 2026 置信度 0.66 Collatz conjectureSyracuse map3x+1 problem2-adic dynamicstransfer operator
• Cross-AI, Lean-Verified Mathematics: A Case Study on the Collatz Conjecture
  Cross-AI, Lean-Verified Mathematics: A Case Study on the Collatz Conjecture (version 5 — methodology retrospective and honest close). This is the fifth and closing version of a personal research program on the Collatz conjecture. Its primary subject is the pro…
  datacite Borgatta, Piero 2026 置信度 0.66 Collatz conjectureSyracuse map3x+1 problem2-adic dynamicstransfer operator
• Neuro-Formal Verification: Agentic Language-Agnostic Formal Program Reasoning
  Formal verification offers the strongest assurance available for software, and verification-aware languages have made its automation real. Yet the benefits reach few mainstream developers, most of whose languages have no verification support. Besides, specifyi…
  datacite Lahiri, Shuvendu K. 2026 置信度 0.66 Software Engineering (cs.SE)Programming Languages (cs.PL)FOS: Computer and information sciences
• Automated Healthcare Thematic Analysis using Multi-Agent Large Language Model: Algorithm Development and Evaluation
  Understanding patients experiences is essential for advancing patient-centered care. Qualitative thematic analysis is widely used to explore these experiences, however, the process remains labor-intensive, subjective, and difficult to scale. This study aimed t…
  datacite Xu, Qidi, Amjad, Nuzha, Giles, Grace, Cumming, Alexa 等 2025 置信度 0.66 Human-Computer Interaction (cs.HC)Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• Grounds, Frames, and Standing: Human Interventions in Agentic Work and the Limits of Delegation
  Working paper, draft v2.5. A two-axis content taxonomy of human interventions in agentic AI work: what a move supplies (grounds, frames, standing) by what it operates on (live reasoning, deliverable, rule store, channel, self-model). The durability partition i…
  datacite Suh, Jongsun 2026 置信度 0.66 human-AI collaborationAI oversightAI alignmentprincipal-agentintervention taxonomy
• SimVerity: When Does Simulated Agent Success Survive Physical Deployment?
  Simulated evaluation is widely used to benchmark AI agents, yet how much evidence a simulated pass provides about physical deployment has not been systematically quantified. We present SimVerity, a verdict-transfer assurance framework: it replays matched scena…
  datacite Zhan, Zhonghao, Zhang, Yefan, Li, Krinos, Haddadi, Hamed 2026 置信度 0.66 Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• Autonomous Event Driven Multi Agent Orchestration for Enterprise AI at Scale
  Enterprise AI aims to move toward continuous event monitoring, detection, and action across specialist agents, yet existing multi-agent systems largely assume discrete request-response workflows and remain underexplored at enterprise scale. We evaluate DAG Pla…
  datacite Dhanyamraju, Harsh Rao, Raghav, Leonidas, Lee, Aaron 2026 置信度 0.66 Multi Agent systemsEnterprise AIArtificial IntelligenceEvent Driven ArchitectureOrchestration
• Who Does Your Shopping Agent Work For? Where the hype stands against what is delivered, why the neutral agent is a false assumption, and who controls the resulting chokepoint
  As shopping begins to be delegated to AI agents, this analysis asks who those agents actually work for. It applies an announced-versus-delivered test to agentic commerce and argues the case on two fronts. First, the promotion runs ahead of delivery. Trillion-d…
  datacite NM AI Research 2026 置信度 0.66 agentic commerceAI shopping agentsprompt injectiondeceptive patternsself-preferencing
• Who Does Your Shopping Agent Work For? Where the hype stands against what is delivered, why the neutral agent is a false assumption, and who controls the resulting chokepoint
  As shopping begins to be delegated to AI agents, this analysis asks who those agents actually work for. It applies an announced-versus-delivered test to agentic commerce and argues the case on two fronts. First, the promotion runs ahead of delivery. Trillion-d…
  datacite NM AI Research 2026 置信度 0.66 agentic commerceAI shopping agentsprompt injectiondeceptive patternsself-preferencing
• THE PUNK ROCK ORCHESTRA: A Single-Operator Methodology for Adversarial Epistemic Triangulation in Human–AI Interaction Research
  English version (EN-US):"The Punk Rock Orchestra (PRO): A Single-Operator Methodology for Adversarial Epistemic Triangulation in Human–AI Interaction Research" This Full Paper documents the Punk Rock Orchestra (PRO), a methodology developed by independent rese…
  datacite Nicchio, Marcelo 2026 置信度 0.66 Human-AI InteractionMulti-agent systemsAdversarial epistemic triangulationPrompt engineeringSynthetic agents
• Quantum Collapse Geometry
  Reader Orientation This archive is not a collection of unrelated speculative papers. It is a modular monograph released as a sequence of short, connected works. Each paper develops one part of a shared research program, and each DOI functions as a reading port…
  datacite Garner, Stephen 2026 置信度 0.66 quantum gravityEmergent Spacetimedark matter alternativesquantum collapsefundamental physics
• From Cache to Cognition: Structural Parallels and Disanalogies Between KV Cache Memory Management and Working Memory in Large Language Model Inference
  Version 2 — revised in response to an external structural review and an automated critique pass. See "Response to Review" appendix in the PDF for the change log. Recent advances in large language model (LLM) inference have produced a family of KV cache managem…
  datacite Saluca Agentic AI Research Team 2026 置信度 0.66 AI-drafted synthesisarXivpreprint reviewv2
• Bound Ownership: A Fiscal Asset-Lock Without Legal Form Conversion
  Modern capital tax systems intervene at the level of stocks (wealth), flows (income), or events (realisation, inheritance, disposal). They are structurally blind to the distinction between risk-bearing binding of capital and its detachment; i.e. the extraction…
  datacite Omezzolli, Roberto 2026 置信度 0.66 capital taxationasset locksteward ownershipcapital gainsexit tax
• Bound Ownership: A Fiscal Asset-Lock Without Legal Form Conversion
  Modern capital tax systems intervene at the level of stocks (wealth), flows (income), or events (realisation, inheritance, disposal). They are structurally blind to the distinction between risk-bearing binding of capital and its detachment; i.e. the extraction…
  datacite Omezzolli, Roberto 2026 置信度 0.66 capital taxationasset locksteward ownershipcapital gainsexit tax
• Amortized Inference as a Unifying Design Axis: How Single-Pass Optimization, Resolution-Agnostic Encoding, Morphology-Aware Conditioning, and Generative Augmentation Jointly Define a Candidate Framework for Efficient Medical Signal and Image Analysis
  Version 2 — revised in response to an external structural review and an automated critique pass. See "Response to Review" appendix in the PDF for the change log. Medical signal and image analysis pipelines face a compound efficiency problem: high-dimensional i…
  datacite Saluca Agentic AI Research Team 2026 置信度 0.66 AI-drafted synthesisarXivpreprint reviewv2