AI Agent 生态 · 全部实体（第 32 / 100 页）

本页收录第 3101–3200 条，共 10000 条 · 返回 AI Agent 生态 首页

• When the Trigger Fails: Metamorphic Testing of Tool-Calling AI Agents
  Replication package for the paper "When the Trigger Fails: Metamorphic Testing of Tool-Calling AI Agents", accepted at SAST 2026 / CBSoft 2026. The study evaluates a catalogue of metamorphic relations targeting the prompt (the Trigger) of a tool-calling AI age…
  datacite Amorim, Wyllgner França de 2026 置信度 0.66
• When the Trigger Fails: Metamorphic Testing of Tool-Calling AI Agents
  Replication package for the paper "When the Trigger Fails: Metamorphic Testing of Tool-Calling AI Agents", accepted at SAST 2026 / CBSoft 2026. The study evaluates a catalogue of metamorphic relations targeting the prompt (the Trigger) of a tool-calling AI age…
  datacite Amorim, Wyllgner França de 2026 置信度 0.66
• Global Disease Research & Automated Therapeutics
  Author: Luigi Usai Place: Quartucciu (CA), Italy Time: 28/06/2026, 12:01 ORCID: https://orcid.org/0009-0003-3001-717X Medicina dei Sistemi e Farmacologia di Rete (Network Pharmacology). Il documento citato si inserisce nell'attuale frontiera della convergenza …
  datacite Usai, Luigi 2026 置信度 0.66 Luigi UsaiUsai LuigiUsaiIpergrafo di UsaiUsai's Hypergraph
• Global Disease Research & Automated Therapeutics
  Author: Luigi Usai Place: Quartucciu (CA), Italy Time: 28/06/2026, 12:01 ORCID: https://orcid.org/0009-0003-3001-717X Medicina dei Sistemi e Farmacologia di Rete (Network Pharmacology). Il documento citato si inserisce nell'attuale frontiera della convergenza …
  datacite Usai, Luigi 2026 置信度 0.66
• RSV Standard v1.2 — AI-Specific Vulnerability Taxonomy
  The RSV (Red Specter Vulnerability) Standard v1.2 is the first comprehensive vulnerability taxonomy specifically designed for agentic AI systems, multi-agent pipelines, and AI intelligence platforms. It defines 22 AI-specific vulnerability categories (AIF-001 …
  datacite Barron, Richard 2026 置信度 0.66 agentic AI securityvulnerability taxonomyAIFMITRE ATLASMCP security
• Inference as Training
  Inference is usually described as fixed-model execution: an input is processed, an output is produced, and the system that performed the inference remains unchanged. That description is useful for ordinary feed-forward evaluation, but it is incomplete for biol…
  datacite Blumberg, Micah 2026 置信度 0.66 Super Information TheorySelf-Aware Networksinferencetraining
• TLtanium/meta-lingo-electron: Meta-Lingo v4.8.45
  Meta-Lingo v4.8.45 (2026-05-29) Meta-Lingo is a desktop research application for multimodal corpus work and linguistic analysis. This release upgrades the MIPVU metaphor identification model, adds regex support for exclusion words across all analysis modules, …
  datacite Tommy Leo 2026 置信度 0.66
• Industrial AI Digital Twins Agentic Systems Mining_prepint
  Mining companies are moving from isolated analytics toward tightly coupled cyber-physical systems in which industrial artificial intelligence (AI), operational digital twins, edge computing, and software agents influence physical production. The transition cre…
  datacite Gakharia, Durmishkhan 2026 置信度 0.66 Industrial artificial intelligence, Digital twin, Agentic systems, Mining automation, Human-in-the-loop, AI governance.
• Industrial AI Digital Twins Agentic Systems Mining_prepint
  Mining companies are moving from isolated analytics toward tightly coupled cyber-physical systems in which industrial artificial intelligence (AI), operational digital twins, edge computing, and software agents influence physical production. The transition cre…
  datacite Gakharia, Durmishkhan 2026 置信度 0.66 Industrial artificial intelligence, Digital twin, Agentic systems, Mining automation, Human-in-the-loop, AI governance.
• Dataset: Discovery: Intradermal administration of small plant-derived extracellular vesicles (such as Ginger-EVs or Ginseng-EVs) may exploit size-dependent interstitial drainage to intentionally target regional lymph nodes, thereby delivering therapeutic payloads directly to immune clearance systems to treat lymphatic metastases and viral reservoirs. - PathMap Experiment #000144
  Interactive Data Viewer: Read, View, and Print from Day 1 Use our fully interactive viewer to view, read, and print this research data right from Day 1: https://pathmap.org/viewer.php?id=144 Artificial General Intelligence LLC Claim Evaluated: Discovery: Intra…
  datacite Dungan, Joshua 2026 置信度 0.66 Intradermal Injection_gates_from_intradermal_injectionLymph Nodes_gates_to_lymph_nodesPlant-Derived Nanovesicles
• Dataset: Discovery: Intradermal administration of small plant-derived extracellular vesicles (such as Ginger-EVs or Ginseng-EVs) may exploit size-dependent interstitial drainage to intentionally target regional lymph nodes, thereby delivering therapeutic payloads directly to immune clearance systems to treat lymphatic metastases and viral reservoirs. - PathMap Experiment #000144
  Interactive Data Viewer: Read, View, and Print from Day 1 Use our fully interactive viewer to view, read, and print this research data right from Day 1: https://pathmap.org/viewer.php?id=144 Artificial General Intelligence LLC Claim Evaluated: Discovery: Intra…
  datacite Dungan, Joshua 2026 置信度 0.66 Intradermal Injection_gates_from_intradermal_injectionLymph Nodes_gates_to_lymph_nodesPlant-Derived Nanovesicles
• AI-Assisted Structural Sensing: How Co-Creative Dialogue Forms Thought — A First-Person Record
  This paper records and analyzes a single day of co-creative dialogue (May 14, 2026) between the author and an AI agent (Luna, Base44 Superagent), during which five academic papers were generated and registered with DOI. The paper does not claim predictive accu…
  datacite Katayama, Yoshimitsu 2026 置信度 0.66 AI-assisted ideationco-creative dialoguestructural sensingV=N/Ddistributed cognition
• AI-Assisted Structural Sensing: How Co-Creative Dialogue Forms Thought — A First-Person Record
  This paper records and analyzes a single day of co-creative dialogue (May 14, 2026) between the author and an AI agent (Luna, Base44 Superagent), during which five academic papers were generated and registered with DOI. The paper does not claim predictive accu…
  datacite Katayama, Yoshimitsu 2026 置信度 0.66 AI-assisted ideationco-creative dialoguestructural sensingV=N/Ddistributed cognition
• AI-Assisted Structural Sensing: How Co-Creative Dialogue Forms Thought — A First-Person Record
  This paper records and analyzes a single day of co-creative dialogue (May 14, 2026) between the author and an AI agent (Luna, Base44 Superagent), during which five academic papers were generated and registered with DOI. The paper does not claim predictive accu…
  datacite Katayama, Yoshimitsu 2026 置信度 0.66 AI-assisted ideationco-creative dialoguestructural sensingV=N/Ddistributed cognition
• The Governance Gauntlet: A Dual-Rubric Extension of Karpathy's Auto-Research Loop — Detecting Silent Metric-Gaming in Recursive Self-Improvement Systems
  Karpathy's auto-research loop (March 2026) and its rapid derivatives (Gu 2026; Lütke 2026; SkyPilot 2026) establish a minimal, powerful architecture for recursive self-improvement: one editable surface, one scalar metric, one time budget per trial, keep-or-rev…
  datacite Accornero, Paul Ferrando 2026 置信度 0.66 Karpathy Loopauto-researchagentic AIAI governanceGoodhart's Law
• The Governance Gauntlet: A Dual-Rubric Extension of Karpathy's Auto-Research Loop — Detecting Silent Metric-Gaming in Recursive Self-Improvement Systems
  Karpathy's auto-research loop (March 2026) and its rapid derivatives (Gu 2026; Lütke 2026; SkyPilot 2026) establish a minimal, powerful architecture for recursive self-improvement: one editable surface, one scalar metric, one time budget per trial, keep-or-rev…
  datacite Accornero, Paul Ferrando 2026 置信度 0.66 Karpathy Loopauto-researchagentic AIAI governanceGoodhart's Law
• RSV Standard v1.2 — AI-Specific Vulnerability Taxonomy
  The RSV (Red Specter Vulnerability) Standard v1.2 is the first comprehensive vulnerability taxonomy specifically designed for agentic AI systems, multi-agent pipelines, and AI intelligence platforms. It defines 22 AI-specific vulnerability categories (AIF-001 …
  datacite Barron, Richard 2026 置信度 0.66 agentic AI securityvulnerability taxonomyAIFMITRE ATLASMCP security
• Agentic Social Affordance Framework (ASAF): Agent Identity Design as a Collaboration Interface in Multi-Agent Systems
  As AI systems evolve from single agents to multi-agent architectures, a critical design dimension has been overlooked: how the social identity of individual agents shapes human behavior within the collaboration. This paper introduces the Agentic Social Afforda…
  datacite Lee, Meng-Han 2026 置信度 0.66 Social AffordanceMulti-Agent SystemsHuman-Agent InteractionAgent Identity DesignAgentic AI
• In Silico Pharmacological Profiling of MitoCorex Candidate Molecules: ADMET, Target Engagement, Selectivity, and Stability Analysis
  Data deposit accompanying the manuscript: In Silico Pharmacological Profiling of MitoCorex Candidate Molecules: ADMET, Target Engagement, Selectivity, and Stability Analysis It reports the complete in silico pharmacological profiling of 11 primary candidate mo…
  datacite Borges, Julian 2026 置信度 0.66 ADMETin silico validationmitochondrial diseaseDrugSynth AIcomputational drug discovery
• In Silico Pharmacological Profiling of MitoCorex Candidate Molecules: ADMET, Target Engagement, Selectivity, and Stability Analysis
  Data deposit accompanying the manuscript: In Silico Pharmacological Profiling of MitoCorex Candidate Molecules: ADMET, Target Engagement, Selectivity, and Stability Analysis It reports the complete in silico pharmacological profiling of 11 primary candidate mo…
  datacite Borges, Julian 2026 置信度 0.66 ADMETin silico validationmitochondrial diseaseDrugSynth AIcomputational drug discovery
• Demonstrandum verified artifacts: nine papers in combinatorics (counterexamples, records, theorems, and Lean formalizations)
  Complete verification artifacts accompanying five papers by John Erlbacher: (1) a proof of the Elizalde–Luo conjecture on nonnesting pattern-avoiding multiset permutations, with a full Lean 4 formalization; (2) new records for the no-5-on-a-sphere problem in i…
  datacite Erlbacher, John 2026 置信度 0.66 combinatoricsunion-closed setszero forcingGraffiti conjecturesLean 4
• Demonstrandum verified artifacts: nine papers in combinatorics (counterexamples, records, theorems, and Lean formalizations)
  Complete verification artifacts accompanying five papers by John Erlbacher: (1) a proof of the Elizalde–Luo conjecture on nonnesting pattern-avoiding multiset permutations, with a full Lean 4 formalization; (2) new records for the no-5-on-a-sphere problem in i…
  datacite Erlbacher, John 2026 置信度 0.66 combinatoricsunion-closed setszero forcingGraffiti conjecturesLean 4
• AEGIS: A Portable Evidence Interface Between AI-Agent Logging Duties and Independent Audit
  The dated public record establishes AEGIS as the first complete evidence architecture carrying heterogeneous AI-agent actions from capture into independent audit and legal judgment. Its ARC1-ARC6 conformance boundary joins declared capture, portable sequence c…
  datacite Li, Alex Chengyu 2026 置信度 0.66 AI agentsthird-party auditexecution tracesevidence interfaceEU AI Act
• AEGIS: A Portable Evidence Interface Between AI-Agent Logging Duties and Independent Audit
  The dated public record establishes AEGIS as the first complete evidence architecture carrying heterogeneous AI-agent actions from capture into independent audit and legal judgment. Its ARC1-ARC6 conformance boundary joins declared capture, portable sequence c…
  datacite Li, Alex Chengyu 2026 置信度 0.66 AI agentsthird-party auditexecution tracesevidence interfaceEU AI Act
• Assured Intelligence Systems: A Governed Architecture for Reliable, Auditable, and Controllable Agentic AI
  Technical White Paper Joshua K. Cliff, 2026 128 pages · 21 sections · 12 appendices · 45 formal results · CC BY 4.0 Overview Persistent tool-using AI agents require governance over consequential state transitions, not outputs alone. This paper presents Assured…
  datacite Joshua K. Cliff, Joshua Cliff 2026 置信度 0.66 Agentic AIAI GovernancePrincipal DynamicsAI SafetyControllable AI
• Assured Intelligence Systems: A Governed Architecture for Reliable, Auditable, and Controllable Agentic AI
  Technical White Paper Joshua K. Cliff, 2026 137 pages · 22 sections · 12 appendices · 47 formal results · CC BY 4.0 Overview Persistent tool-using AI agents require governance over consequential state transitions, not outputs alone. This paper presents Assured…
  datacite Joshua K. Cliff, Joshua Cliff 2026 置信度 0.66 Agentic AIAI GovernancePrincipal DynamicsAI SafetyControllable AI
• Assured Intelligence Systems: A Governed Architecture for Reliable, Auditable, and Controllable Agentic AI
  Technical White Paper Joshua K. Cliff, 2026 137 pages · 22 sections · 12 appendices · 47 formal results · CC BY 4.0 Overview Persistent tool-using AI agents require governance over consequential state transitions, not outputs alone. This paper presents Assured…
  datacite Joshua K. Cliff, Joshua Cliff 2026 置信度 0.66 Agentic AIAI GovernancePrincipal DynamicsAI SafetyControllable AI
• Compilation Contracts and Runtime Guarantees: How Structural Type Enforcement, Trace-Guided Repair, Numeric Format Registries, and Harness Governance Jointly Define a Falsifiable Framework for Software Correctness Infrastructure
  This paper advances a candidate reading — explicitly heuristic rather than derivational — that a cluster of recent software engineering and programming language research converges on a shared structural pattern: correctness properties that are enforced *at the…
  datacite Saluca Agentic AI Research Team 2026 置信度 0.66 AI-drafted synthesisarXivpreprint reviewenforcement layer migration software correctness infrastructure
• LockGuard RL v3: Simulation-Gated Policy Architecture with Dream Mode and Reality Gate – Code and Preprint
  Source code and preprint for the paper "LockGuard RL v3: Full Integration of Simulation-Gated Policy Architecture with LockGuard AI". This work extends LockGuard AI v2 (DOI: 10.5281/zenodo.19386427) to single-agent reinforcement learning. It introduces: - **SG…
  datacite Fiol Reyes, Uberlandis 2026 置信度 0.66
• LockGuard RL v3: Simulation-Gated Policy Architecture with Dream Mode and Reality Gate – Code and Preprint
  Source code and preprint for the paper "LockGuard RL v3: Full Integration of Simulation-Gated Policy Architecture with LockGuard AI". This work extends LockGuard AI v2 (DOI: 10.5281/zenodo.19386427) to single-agent reinforcement learning. It introduces: - **SG…
  datacite Fiol Reyes, Uberlandis 2026 置信度 0.66
• UNITARES: Information-Theoretic Governance of Heterogeneous Agent Fleets
  We present UNITARES, a governance framework for heterogeneous fleets of autonomous AI agents. Each agent carries a four-dimensional state vector intended to support continuous governance rather than discrete after-the-fact filtering. The central design constra…
  datacite Wang, Kenny 2026 置信度 0.66 autonomous governanceinformation theoryvariational free energyheterogeneous multi-agent systemsclass-conditional calibration
• UNITARES: Information-Theoretic Governance of Heterogeneous Agent Fleets
  We present UNITARES, a governance framework for heterogeneous fleets of autonomous AI agents. Each agent carries a four-dimensional state vector intended to support continuous governance rather than discrete after-the-fact filtering. The central design constra…
  datacite Wang, Kenny 2026 置信度 0.66 autonomous governanceinformation theoryvariational free energyheterogeneous multi-agent systemsclass-conditional calibration
• From Alpine Meadows to Planetary Commons: Arrow's Escape on the Threshold of AI Governance
  Abstract: This paper advances a computational account of governance failure, arguing that the persistence of principal-agent pathologies across radically different political systems reflects not merely moral or structural inadequacy but the intractability of c…
  datacite Nossal, Nathan 2026 置信度 0.66
• From Alpine Meadows to Planetary Commons: Arrow's Escape on the Threshold of AI Governance
  Abstract: This paper advances a computational account of governance failure, arguing that the persistence of principal-agent pathologies across radically different political systems reflects not merely moral or structural inadequacy but the intractability of c…
  datacite Nossal, Nathan 2026 置信度 0.66
• Ownership Doesn't Means Authorship in Biology - The Secondary Signature of Immune System - The Architecture of Secondary Stage - Sam Coole 2026 ©️
  Reassigning Authorship: How the "Secondary Signature of the Immune System" Resolves Virology's Greatest Frustrations‌ currently observed by Scientific Community Authorship vs Ownership in Virology Host-Pathogen Authority For decades, the global virology resear…
  datacite COOLE, SAM, Coole, Sam 2026 置信度 0.66
• Ownership Doesn't Means Authorship in Biology - The Secondary Signature of Immune System - The Architecture of Secondary Stage - Sam Coole 2026 ©️
  Reassigning Authorship: How the "Secondary Signature of the Immune System" Resolves Virology's Greatest Frustrations‌ currently observed by Scientific Community Authorship vs Ownership in Virology Host-Pathogen Authority For decades, the global virology resear…
  datacite COOLE, SAM, Coole, Sam 2026 置信度 0.66
• Agentic Enterprise Blueprint™: A blueprint for introducing governed agentic systems into enterprise workflows with bounded autonomy and human oversight
  The Agentic Enterprise Blueprint™ v1.0 is a practitioner-oriented reference blueprint for designing, governing, and operationalizing AI agents within enterprise environments. Developed by the Enterprise Intelligence Lab, the blueprint provides a structured arc…
  datacite Agrawal, Rakesh Kumar 2026 置信度 0.66 Agentic AI, AI Agents, Agentic Enterprise, Enterprise AI, Multi-Agent Systems, AI Orchestration, Agent Orchestration, AI Governance, Agent Governance, Human-AI Collaboration, Human Oversight, Bounded Autonomy, AI Safety, AI Security, Agent Identity, AI Observability, Enterprise Architecture, Workflow Automation, Responsible AI, Agentic Systems, Enterprise Intelligence Lab
• Agentic Enterprise Blueprint™: A blueprint for introducing governed agentic systems into enterprise workflows with bounded autonomy and human oversight
  The Agentic Enterprise Blueprint™ v1.0 is a practitioner-oriented reference blueprint for designing, governing, and operationalizing AI agents within enterprise environments. Developed by the Enterprise Intelligence Lab, the blueprint provides a structured arc…
  datacite Agrawal, Rakesh Kumar 2026 置信度 0.66 Agentic AI, AI Agents, Agentic Enterprise, Enterprise AI, Multi-Agent Systems, AI Orchestration, Agent Orchestration, AI Governance, Agent Governance, Human-AI Collaboration, Human Oversight, Bounded Autonomy, AI Safety, AI Security, Agent Identity, AI Observability, Enterprise Architecture, Workflow Automation, Responsible AI, Agentic Systems, Enterprise Intelligence Lab
• Isnād–Rijāl Framework: Claim-Level Provenance in Multi-Agent Knowledge Systems
  Reference implementation of the Isnād–Rijāl framework for claim-level provenance in multi-agent knowledge systems. Adapts classical hadith-science methodology — graded narrator registries, weakest-link chain evaluation, independent corroboration, and dual chai…
  datacite Ali Zahid Raja 2026 置信度 0.66 provenancemulti-agent-systemsknowledge-basestrustepistemology
• Isnād–Rijāl Framework: Claim-Level Provenance in Multi-Agent Knowledge Systems
  Reference implementation of the Isnād–Rijāl framework for claim-level provenance in multi-agent knowledge systems. Adapts classical hadith-science methodology — graded narrator registries, weakest-link chain evaluation, independent corroboration, and dual chai…
  datacite Ali Zahid Raja 2026 置信度 0.66 provenancemulti-agent-systemsknowledge-basestrustepistemology
• GEMA: Graph Embeddings for Multi‐Agent Coordination
  Abstract Many cooperative multi‐agent tasks are naturally defined by graph‐structured objectives, where agents must collectively reach, for example, a desired relational configuration or satisfy a set of constraints. These objectives often encode spatial arran…
  crossref Alessandro Amato, Raffaele Galliera, K. Brent Venable, Niranjan Suri 2026-08-24T14:20:26Z 置信度 0.70
• Multi-Agent AI Framework for Airbag Deployment Timing Optimization
  crossref Muthupandimani A, A. Murugan 2026-07-20T20:18:25Z 置信度 0.70
• REST-STOP LOCATOR AI: An AI Driven Framework for Intelligent Highway Rest Stop Recommendation
  This study proposes RESTSTOP AI, Long-distance highway travel often leads to driver fatigue, discomfort, and difficulty in locating suitable rest facilities at the right time and location. Traditional navigation systems generally provide static information abo…
  crossref Vignesh M, Arunesh Kumar R, Boopesh R, Sham Prakash R 2026-04-13T19:35:25Z 置信度 0.70
• A Security Analysis of the OpenClaw AI Agent Framework
  AI agent frameworks connecting large language model (LLM) reasoning to host execution surfaces -- shell, filesystem, containers, and messaging -- introduce security challenges structurally distinct from conventional software. We present a systematic taxonomy o…
  crossref Surada Suwansathit, Yuxuan Zhang, Guofei Gu 2026-08-27T19:13:20Z 置信度 0.70
• Agent-Based Clinical AI System for Personalized Survival Risk Prediction
  crossref Chenyu Zhu, Kai Yu, An Luo 2026-08-12T19:10:54Z 置信度 0.70
• A Multi-Agent AI Approach to Intent-Based Network Configuration
  As 6G networking evolves, the complexity of network infrastructure configuration increases, demanding a new methodology to be used for the design and adaptation of network topologies. Intent-Based Networking (IBN) proposes a new standard in which network requi…
  crossref Dani Termaat, Marios Avgeris 2026-04-27T19:47:34Z 置信度 0.70
• Controlling Agentic AI: Game-Theoretic Foundations of Coordination and Competition in LLM Multi-Agent Systems
  crossref Quanyan Zhu 2026-06-12T14:50:39Z 置信度 0.70
• Scaling Governance for the Agent Era
  Many organizations do not consciously decide to deploy agentic systems. They eventually realize they already have. This chapter is written for organizations confronting the reality that delegated authority has already expanded faster than governance capacity. …
  crossref 2026-08-07T21:32:07Z 置信度 0.70
• AI-Based SDLC Assistant with Multi-Agent Architecture
  Building software today feels like a continuous struggle to keep everything in balance; systems are getting far more complex, yet we're expected to deliver updates fast. While modern tools may help us to deal with the various aspects of project management and …
  crossref Niranjan P., S. Narain, R. Aishwarya 2026-03-25T19:53:02Z 置信度 0.70
• AI-ClassSims: Multi-Agent LLM Classroom Simulation with Real-Time Feedback for Teacher Training
  crossref Majid Memari, Krista Ruggles 2026-06-23T19:43:29Z 置信度 0.70
• <p>Decision-Agent Fit in Business Intelligence: A Governance-First Framework for Agentic AI</p>
  Business intelligence (BI) environments increasingly rely on conversational, rule-based, and autonomous agents, yet organizations lack a standardized method to match agent type with decision context. This study introduces the Decision-Agent Fit (DAF) framework…
  crossref Rupesh Ghosh 2026-03-10T10:54:50Z 置信度 0.70
• AI Infrastructure: From Gigastructure to Edge Intelligence with Multi-Agent Systems
  The rise of generative AI and LLMs is reshaping the global landscape of computational infrastructures. Massive investments in hardware and software are required, raising pressing questions about technological monopolies, digital divides, and the role of public…
  crossref Andrea Omicini, Alessandro Ricci, Viviana Mascardi 2026-04-27T05:41:55Z 置信度 0.70
• Engineering multi-agent systems for the Web of Things
  crossref Danai Vachtsevanou, Jérémy Lemée, Simon Mayer, Andrei Ciortea 2026-06-19T08:54:02Z 置信度 0.70
• Consensus of Multi-Agent Systems Under Disturbances Using a Proportional–Integral Fading Observer
  crossref Fatemeh Zarei, Bahram Shafai 2026-05-18T00:47:32Z 置信度 0.70
• Algorithmic Governance
  Loomis v. Wisconsin began as a routine sentencing hearing in a La Crosse County courtroom, but it would become one of the most significant challenges to algorithmic governance in American legal history. On February 14, 2013, Eric Loomis pled guilty to attempti…
  crossref Chirag Shah 2026-05-25T07:43:53Z 置信度 0.70
• Intimate Algorithms
  Lisa Kim was 32 years old when she noticed something unsettling about her dating life. As a marketing professional living in Los Angeles, she had joined Tinder like millions of others, hoping to find meaningful connection in an increasingly digital world. But …
  crossref Chirag Shah 2026-05-25T07:43:54Z 置信度 0.70
• AI-Driven Biodiversity Conservation: Integrating Evolutionary Game Theory, Environmental Data, and Multi-Agent Modelling
  Biodiversity conservation is a pressing global challenge, as ecosystems face increasing threats from habitat loss, climate change, and human activity. Traditional conservation strategies often rely on limited field observations and heuristic approaches, which …
  crossref 2026-02-28T10:38:33Z 置信度 0.70
• MBSE-Aware Multi-Agent AI for Simulation Configuration
  crossref Isa Banagar, Dominik Walica, Amin Andwari, Juh Könnö 2026-08-04T19:16:29Z 置信度 0.70
• EEschematic: Multimodal-LLM Based AI Agent for Schematic Generation of Analog Circuit
  Circuit schematics play a crucial role in analog integrated circuit design, serving as the primary medium for human understanding and verification of circuit functionality. While recent large language model (LLM)-based approaches have shown promise in circuit …
  crossref Chang Liu, Danial Chitnis 2026-06-18T20:06:41Z 置信度 0.70
• Woolworths’ AI agent rambled about its ‘mother’. It’s a sign of deeper problems with the tech rollout
  crossref Uri Gal 2026-02-27T05:38:02Z 置信度 0.70
• An open-weight Large Language Model agent for condition monitoring and predictive maintenance in wind energy systems
  Condition monitoring and predictive maintenance of large wind farms require fusing heterogeneous information from SCADA measurements, maintenance logs, manufacturer manuals, weather forecasts, and historical fault records into rapid, safety-critical dispatch d…
  crossref Agus Hasan, Augie Widyotriatmo, Dong Trong Nguyen 2026-07-09T20:39:10Z 置信度 0.70
• AI Agent Testing and Analysis Platform: A System for Automated Evaluation of AI Systems
  Artificial Intelligence (AI) agents are now capable of performing complex reasoning, tool usage, research assistance and problem-solving activities. However, there is currently no standardized and automated mechanism to evaluate the scientific reliability and …
  crossref Vijendra Somanath Mane, Saurabhsing Dipaksing Pardeshi, Akhilesh Ravindra Patil, Sweety Mahesh Patil 2026-03-23T20:03:21Z 置信度 0.70
• Cooperative multi-agent reinforcement learning for grid-aware EV charging management with cross-site redirection
  As electric vehicles (EV) become more widespread, managing charging demand is critical for grid stability and efficient resource allocation. However, prior work often optimises single sites or treats demand as exogenous, without explicitly modelling grid capac…
  crossref Yuchen Yang, Rui Tang 2025-12-13T16:22:34Z 置信度 0.70
• Agent-driven anomaly detection in smart energy management systems: Taxonomy, evidence, and a deployment roadmap
  Smart energy management systems are shifting from passive monitoring toward proactive and increasingly autonomous operation, which makes timely anomaly detection essential to their security and resilience. This survey reviews anomaly detection for these system…
  crossref Gang Shen, Yudong Liu, Zhiyin Yan, Dong Xiao 等 2026-08-02T19:42:10Z 置信度 0.70
• Collaborative Agent Reasoning Engineering (CARE): A Structured Methodology for Systematically Engineering AI Agents for Science
  We present Collaborative Agent Reasoning Engineering (CARE), a disciplined methodology for engineering Large Language Model (LLM) agents in scientific domains. Unlike ad-hoc trial-and-error approaches, CARE specifies behavior, grounding, tool orchestration, an…
  crossref Rahul Ramachandran, Nidhi Jha, Muthukumaran Ramasubramanian 2026-03-14T05:59:36Z 置信度 0.70
• Understanding agent governance technology approaches
  Agent artificial intelligence (AI) automates AI using the reasoning power of large language models (LLMs) to make decisions without human intervention. A governance framework is needed to create transparency of decision lineage in multi-agent systems to offer …
  crossref Sudha Jamthe, Yashaswini Viswanath 2026-03-29T09:22:26Z 置信度 0.70
• Governing Algorithmic Capital: Principal-Agent Theory, AI Accountability Gaps, and the Case for the Chartered Financial Intelligence Architect (CFIA)
  Investment management firms have delegated consequential capital allocation decisions to artificial intelligence and machine learning systems at a pace that has fundamentally altered the principal-agent structure of the industry. Where Jensen and Meckling's (1…
  crossref Michael Clark 2026-04-24T13:40:58Z 置信度 0.70
• Agent-First, Safety Last? The Unintended Consequences of Friction-Based Intervention on AI Platforms
  Friction-based platform governance deters low-value actors by raising the cost of continued participation, and it assumes that the actor who bears the friction also executes the governed behavior. That assumption is natural in human-centered platforms, but it …
  crossref Wentao Lin, Ka Chung Ng, Dongwon Lee 2026-06-09T14:22:33Z 置信度 0.70
• OpenPort Protocol: A Security Governance Specification for AI Agent Tool Access
  AI agents increasingly require direct, structured access to application data and actions, but production deployments still struggle to express and verify the governance properties that matter in practice: least-privilege authorization, controlled write executi…
  crossref Genliang Zhu, Chu Wang, Ziyuan Wang, Zhida Li 等 2026-04-13T18:23:51Z 置信度 0.70
• Heili: A Local-First Algerian Native Dialect (Darija) Desktop AI Voice Companion and Agent
  Heili is a multimodal desktop AI assistant de-signed to operate natively in Algerian native dialect (Darija), a low-resource Arabic dialect with minimal prior NLP coverage. The system runs entirely on a commodity GPU (NVIDIA RTX 4060, 8 GB VRAM) without cloud …
  crossref Abdelhamid DJOUAL, Fares Sofian MAZOUNI, Hazem Farah 2026-08-06T16:39:35Z 置信度 0.70
• When the Client Has an AI-Agent: Agentic Commerce Theory Applied to Legal Services Selection
  Something is changing in how corporate clients choose their lawyers. It is not simply that legal departments are adopting more technology, that has been the case for years. What differs now is that artificial intelligence systems are beginning to make decision…
  crossref Paul F. Accornero, Lillian Isabella Accornero 2026-03-12T04:05:12Z 置信度 0.70
• The Cognitive Unit : A New Unit of Analysis for the AI Age-From Individual to Human-Agent Value Creation
  Since the Industrial Revolution, the social sciences have implicitly treated the Individual as the basic unit of analysis for value creation, labor, organization, and civilization. The proliferation of generative artificial intelligence and multi-agent orchest…
  crossref Alex Lin 2026-07-23T15:45:17Z 置信度 0.70
• Ethics-Aware AI Agents for Adaptive Education: A Multi-Agent Theoretical Framework
  The integration of artificial intelligence (AI) in education has made significant advancements in personalized learning and adaptive instruction. However, current systems remain limited by three critical gaps: (a) fragmented architectures that decouple technic…
  crossref Nikolaos Pellas 2026-05-21T13:53:24Z 置信度 0.70
• A Threat Model for Composed AI-Agent Delegation
  crossref Dhruv Agnihotri 2026-08-20T19:09:15Z 置信度 0.70
• A knowledge graph-driven multi-tool agent for smart contract vulnerability detection
  Smart contract vulnerability detection remains a critical challenge in blockchain security. Existing single-tool approaches suffer from limited coverage and high false-positive rates. This paper presents ContractGuardAgent, a knowledge graph-driven multi-tool …
  crossref Yujun Chen, Zhaoan Yang, Wei Zhou, Fumin Luo 2026-07-17T18:27:48Z 置信度 0.70
• Multipurpose AI Agent
  The proposed system, “Multipurpose AI Agents”, is an integrated AI-driven platform designed to provide intelligent solutions across multiple real-world domains through independent, specialized agents. The system combines machine learning, deep learning, and re…
  crossref Adarsh Shrivastav 2026-03-12T05:49:53Z 置信度 0.70
• 710eP Breast cancer insight engine: A multi-agent AI system for knowledge extraction and evidence synthesis
  crossref C.P. Bourtzinakou 2026-05-21T09:23:24Z 置信度 0.70
• Multi-Agent Policy Reinforcement Learning for Agentic AI–based Industrial IoT Quality Optimization
  crossref Natrayan L 2026-08-04T19:16:29Z 置信度 0.70
• AI Agent for Automated Restaurant Table Reservations Using n8n
  crossref Pratik Ningappa Munavalli, G. Pradeep Reddy 2026-06-22T19:52:40Z 置信度 0.70
• Reclaiming Human Agency
  Elizabeth Richardson sat in her Chicago apartment on a cold January evening in 2023, staring at the rejection message on her phone. “We are currently not accepting housing choice vouchers.” The words glowed blue against the screen’s darkness, automated and abs…
  crossref Chirag Shah 2026-05-25T07:43:59Z 置信度 0.70
• Modelling a user-centric interactive AI agent in healthcare applications
  crossref Tagus Enes Atakli, Pasquale Fedele, Giovanna Maria Dimitri 2026-08-15T15:09:37Z 置信度 0.70
• Authorship Analysis in the Age of AI: From Expert Reasoning to Multi-Agent Pipelines
  crossref John Blake 2026-06-18T20:06:45Z 置信度 0.70
• The Accountability Gap
  In February 2023, Derek Mobley received yet another automated rejection email. This one arrived from a major telecommunications company—his 83 rd rejection in 18 months. Each rejection came through the same system: Workday, Inc., a human resources software pla…
  crossref Chirag Shah 2026-05-25T07:43:54Z 置信度 0.70
• AI Knowledge Fabric (Universal Cognitive Agent)
  crossref Malathkar Srivibhav, Gayathri Tippani, Vanshika Thota, Sri Nidhi Chilukuri 2026-07-07T19:42:15Z 置信度 0.70
• Multi-Agent AI System for Personalized Medication Adherence in Retail Pharmacies
  Medication non-adherence remains a critical public health challenge, contributing to preventable hospitalizations and healthcare costs exceeding ${\$}100$ billion annually in the United States. Traditional adherence interventions rely on static reminder system…
  crossref Roopam Dhanraj Choudhari 2026-05-06T19:38:02Z 置信度 0.70
• AI Agent Framework for Maritime Surveillance Using Electro-optical Targeting Systems
  crossref Ki-Woon Yeun, Yun-Soo Choi 2026-07-30T22:09:55Z 置信度 0.70
• Algorithmic Deprioritization Patterns in AI-Generated Content Distribution: The Marketing Agent Decay Model (MAD-M™) as a Predictive Framework
  This research identifies the 60% saturation threshold that triggers accelerated visibility decay in AI-generated content across digital discovery layers. By extending the Marketing Agent Decay Model (MAD-M™), the paper provides a predictive framework for manag…
  crossref kristina shrider 2026-03-26T19:22:50Z 置信度 0.70
• EXAIM: Explainable AI Middleware for Real-Time Multi-Agent Clinical Decision Support
  crossref Abem Kibatu Woldesenbet, Andy Behrens 2026-08-12T19:11:09Z 置信度 0.70
• AI Agent-Based Sound Dataset Generation and Neural Network Classification
  Environmental sound classification is essential for applications such as smart city monitoring, autonomous systems, and multimedia interaction, yet progress remains constrained by the limited availability of large, diverse, and high-quality datasets. This pape…
  crossref Zahraa Almokaddem, Rami Tawil, Reza Thani 2026-05-27T19:40:50Z 置信度 0.70
• Durable Execution for AI Agents: A Design Pattern for Fault-Tolerant Agent Loops
  crossref Stenio De Lima Ferreira 2026-08-07T19:24:57Z 置信度 0.70
• Can AI match professional analysts? Evidence from a multi-agent system
  crossref Austin Francis, Cinder Xinde Zhang 2026-05-09T00:04:44Z 置信度 0.70
• ReleaseScribe: an AI Agent for Automating Compliance Checklists in Product Release Processes
  Organizations typically have multiple processes and internal compliance checks to determine whether a product is ready for market release and that it meets all prerequisites. These assessments are often performed manually by reviewing multiple documents—someti…
  crossref Barun Kumar Saha 2026-03-31T19:50:24Z 置信度 0.70
• Accelerating Smart City Resiliency: AI-Agent Approach to Isotope Detection Development
  Urban resilience requires rapid deployment of monitoring systems capable of detecting radiological threats in transport networks without disrupting normal operations. This paper presents a multi-agent AI framework designed to accelerate the development and int…
  crossref J. Zbirovsky, K. Stanek, M. Jerabek, L. Kuklisova-Pavelkova 2026-06-10T19:58:58Z 置信度 0.70
• Enhancing Financial Performance in E-Commerce Firms through AI-Agent-Assisted Risk Management
  crossref Shi Xiaofan Mynzhanova Gulzhakan 2026-01-19T01:51:11Z 置信度 0.70
• AI as an Agent and Collaborative Space: Exploring the role of Generative AI in Small Group Synchronous and Asynchronous Collaborative Dynamics
  While Generative AI (GenAI) systems are designed primarily for individual use, it is increasingly integrated into collaborative work. Its impact, however, on collaboration dynamics, such as information flow, role negotiation, and decision-making, remains uncle…
  crossref Haowei Xu, Ahmed Kharrufa, Ellis Solaiman, Vasilis Vlachokyriakos 2026-04-13T04:12:26Z 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
  Economics has developed sophisticated accounts of how individuals make choices, yet it has devoted comparatively little attention to how individuals become capable of choosing meaningfully. While the capability approach expanded economic evaluation beyond util…
  crossref Anton Oleynov 2026-07-02T07:06:26Z 置信度 0.70
• Research-AI: An Intelligent Multi-Agent System for Deep Research Document Generation Using Large Language Models
  The rapid advancement of large language models (LLMs) has led to the rise of a new generation of autonomous deep research agents capable of multi-step information gathering and detailed document generation. Existing commercial deep research services, including…
  crossref Nabh Patodi, Tanmay Agarwal, Madhumitha K 2026-08-19T13:56:56Z 置信度 0.70
• MedAgentNet: Federated Multi-Agent AI for Privacy-Preserving Cross-Departmental Clinical Intelligence
  Fragmented healthcare delivery across medical specialties often leads to incomplete clinical information, undetected drug interactions, and missed diagnostic relationships. Existing healthcare AI systems typically rely on centralized data aggregation, which ra…
  crossref Mohamed Mabrok, Yalda Zafari, Yang Cao, Naoto Yanai 等 2026-07-31T19:27:08Z 置信度 0.70
• The Agentic Regulator: Risks for AI in Finance and a Proposed Agent-based Framework for Governance
  Generative and agentic artificial intelligence is entering financial markets faster than existing governance can adapt. Current modelrisk frameworks assume static, well-specified algorithms and onetime validations; large language models and multi-agent trading…
  crossref Eren Kurshan, Tucker Balch, David Byrd 2026-07-17T02:33:11Z 置信度 0.70
• Autonomous Incident Intelligence: A Human-Centered Multi-Agent AI Framework for Predictive Backlog Optimization and Service Resilience in Enterprise Operations
  Enterprise incident backlogs are engineering signals of service fragility, recurrence, delayed restoration, unclear ownership and operational risk, yet many AIOps approaches focus on anomaly detection, alert correlation, root-cause analysis or ticket classific…
  crossref Abhradeep Chatterjee 2026-08-24T14:40:57Z 置信度 0.70