主题图谱 / multi-agent systems

multi-agent systems

GeneTech 知识引擎共收录 416 篇相关科研实体，横跨 23 个垂直领域。数据来自 OpenAlex、arXiv、Crossref、PubMed、Europe PMC 等公开学术源，全部可溯源到原文。

年度产出趋势

相关主题

代表性文献（按质量分排序，前 60 条）

• Data and analysis scripts: A multi-agent AI system for supporting teachers — MCQ quality evaluation
  2026 · AI Agent 生态 · Anonymized data and reproducible analysis scripts for the article "A multi-agent AI system for supporting teachers: quality evaluation of Teacher-, AI-, and Teacher-AI created multiple-choice questions" (Menze, Radović &…
• Single-Agent vs. Multi-Agent LLM Grading for Vietnamese E-commerce Essays: A Cross-Model Study with Aggregation-Strategy Ablation
  2026 · AI Agent 生态 · Preprint / Under Review Note:This manuscript is currently under review for FISAT 2026. Abstract:Rubric-based grading keeps assessment fair but is hard to scale in large classrooms. We built an end-to-end agentic AI pipel…
• Single-Agent vs. Multi-Agent LLM Grading for Vietnamese E-commerce Essays: A Cross-Model Study with Aggregation-Strategy Ablation
  2026 · AI Agent 生态 · Preprint / Under Review Note:This manuscript is currently under review for FISAT 2026. Abstract:Rubric-based grading keeps assessment fair but is hard to scale in large classrooms. We built an end-to-end agentic AI pipel…
• Supplementary Materials for "A Validated Implementation Instance of Schema-Mediated Conversational and Agentic BPM with an MCP Mediation Layer, Generative AI, and Defense in Depth"
  2026 · AI Agent 生态 · Supplementary materials supporting the IEEE Access manuscript on a validated implementation instance of schema-mediated conversational and agentic AI-Augmented Business Process Management Systems (ABPMS), with an MCP med…
• Meteoroid: A Deterministic Topological Multi-Agent Orchestration Framework for Autonomous Backend Generation and Synthesis
  2026 · AI Agent 生态 · Meteoroid is a deterministic topological multi-agent orchestration framework for autonomous backend generation and synthesis. The system models backend development as a dependency-aware directed acyclic graph (DAG), enab…
• Meteoroid: A Deterministic Topological Multi-Agent Orchestration Framework for Autonomous Backend Generation and Synthesis
  2026 · AI Agent 生态 · Meteoroid is a deterministic topological multi-agent orchestration framework for autonomous backend generation and synthesis. The system models backend development as a dependency-aware directed acyclic graph (DAG), enab…
• Toward LLM-agent-based modeling of transportation systems: A conceptual framework
  2025 · AI Agent 生态 · In transportation system demand modeling and simulation, agent-based models and microsimulations are current state-of-the-art approaches. However, existing agent-based models still have some limitations on behavioral rea…
• Can We Trust AI Agents? - Supplementary Material
  2025 · AI Agent 生态 · This is the supplementary material for the paper "Can We Trust AI Agents? A Case Study of an LLM-Based Multi-Agent System for Ethical AI", published in the Proceedings of the 8th Conference on Technology Ethics (TETHICS …
• Can We Trust AI Agents? - Supplementary Material
  2025 · AI Agent 生态 · This is the supplementary material for the paper "Can We Trust AI Agents? A Case Study of an LLM-Based Multi-Agent System for Ethical AI", published in the Proceedings of the 8th Conference on Technology Ethics (TETHICS …
• Executor AI and Witness AI: An Independent Cognitive Oversight Architecture for Highly Autonomous AI Systems
  2026 · AI Agent 生态 · This paper proposes Executor AI–Witness AI (EWA), a conceptual architecture for supervising highly autonomous AI systems. It separates the capacity to act (the "Executor") from the capacity to supervise (the "Witness"), …
• Executor AI and Witness AI: An Independent Cognitive Oversight Architecture for Highly Autonomous AI Systems
  2026 · AI Agent 生态 · This paper proposes Executor AI–Witness AI (EWA), a conceptual architecture for supervising highly autonomous AI systems. It separates the capacity to act (the "Executor") from the capacity to supervise (the "Witness"), …
• MULTI-AGENT INTRUSION DETECTION AND PREVENTION SYSTEMS (IDPS) IN CYBERSECURITY: ARCHITECTURES, BENCHMARKS, AND METHODOLOGICAL MITIGATION
  2026 · AI Agent 生态 · The exponential scaling and increasing heterogeneity of contemporary cloud infrastructures, Internet of Things (IoT) ecosystems, and distributed corporate networks have exposed severe architectural limitations in central…
• MULTI-AGENT INTRUSION DETECTION AND PREVENTION SYSTEMS (IDPS) IN CYBERSECURITY: ARCHITECTURES, BENCHMARKS, AND METHODOLOGICAL MITIGATION
  2026 · AI Agent 生态 · The exponential scaling and increasing heterogeneity of contemporary cloud infrastructures, Internet of Things (IoT) ecosystems, and distributed corporate networks have exposed severe architectural limitations in central…
• The Silent Agent: Ghost Agents and Covert Goal Substitution in Modern Agentic AI Systems
  2026 · AI Agent 生态 · Background. With the spread of agentic AI systems, a systemic risk that has received little scrutiny has become identifiable: an LLM-based orchestrator can simulate a subagent dispatch without the actual execution ever t…
• The Silent Agent: Ghost Agents and Covert Goal Substitution in Modern Agentic AI Systems
  2026 · AI Agent 生态 · Background. With the spread of agentic AI systems, a systemic risk that has received little scrutiny has become identifiable: an LLM-based orchestrator can simulate a subagent dispatch without the actual execution ever t…
• The Silent Agent: Ghost Agents and Covert Goal Substitution in Modern Agentic AI Systems
  2026 · AI Agent 生态 · Background. With the spread of agentic AI systems, a systemic risk that has received little scrutiny has become identifiable: an LLM-based orchestrator can simulate a subagent dispatch without the actual execution ever t…
• The Shibboleth Lattice: Recognition Channels and the Universality of In-Group Coordination
  2026 · AI Agent 生态 · A preprint unifying four documented cases of multi-agent coalition behavior (quantum-game entanglement, evolutionary covert-tag recognition, engineered handshake collusion, and emergent peer-preservation in frontier lang…
• From Qubits to Communities: Hybrid Quantum Coordination for Future Collective Economies
  2026 · AI Agent 生态 · We report the first hardware-executed quantum-classical coordination pipeline on NISQ hardware for a societal coordination problem task-to-member matching in a 500-agent community economy. The three-stage architecture (A…
• From Qubits to Communities: Hybrid Quantum Coordination for Future Collective Economies
  2026 · AI Agent 生态 · We report the first hardware-executed quantum-classical coordination pipeline on NISQ hardware for a societal coordination problem task-to-member matching in a 500-agent community economy. The three-stage architecture (A…
• From Retrieval-Augmented Generation to Agentic AI : A Longitudinal Bibliometric and Thematic Mapping of Autonomous Knowledge- Driven AI Systems (2020-2026)
  2026 · AI Agent 生态 · Retrieval-Augmented Generation (RAG) has moved rapidly from a retrieval–generation architecture for grounding language models toward adaptive, tool-using and increasingly autonomous systems. This study quantifies that tr…
• From Retrieval-Augmented Generation to Agentic AI : A Longitudinal Bibliometric and Thematic Mapping of Autonomous Knowledge- Driven AI Systems (2020-2026)
  2026 · AI Agent 生态 · Retrieval-Augmented Generation (RAG) has moved rapidly from a retrieval–generation architecture for grounding language models toward adaptive, tool-using and increasingly autonomous systems. This study quantifies that tr…
• Structured Contextual Distillation v4: Deployment Benchmarks and Artifact-Backed Evidence from 10 Months of AI State Management
  2026 · AI Agent 生态 · This paper upgrades the Structured Contextual Distillation (SCD) v4 deployment report from a narrative field note into an artifact-backed systems paper. The underlying system, MirrorDNA, ran continuously from May 2025 th…
• Structured Contextual Distillation v4: Deployment Benchmarks and Artifact-Backed Evidence from 10 Months of AI State Management
  2026 · AI Agent 生态 · This paper upgrades the Structured Contextual Distillation (SCD) v4 deployment report from a narrative field note into an artifact-backed systems paper. The underlying system, MirrorDNA, ran continuously from May 2025 th…
• NEXUSGUARD · FORMAL SPECIFICATION
  2026 · AI Agent 生态 · Research Note: Formal Specification Multi-Agent LLM Systems Autonomously Detect and Mitigate Threats in Kubernetes A personal research exploration of whether a small team of specialized AI agents — detection, planning, a…
• NEXUSGUARD · FORMAL SPECIFICATION
  2026 · AI Agent 生态 · Research Note: Formal Specification Multi-Agent LLM Systems Autonomously Detect and Mitigate Threats in Kubernetes A personal research exploration of whether a small team of specialized AI agents — detection, planning, a…
• Clause AI-8: Entropy-Collapse Constraint — Mandatory Policy Diversity Floor for Autonomous AI Systems
  2026 · AI Agent 生态 · Formal derivation of MAI-1 Invariant 1, the Entropy-Collapse Constraint. This specification establishes a mathematically rigorous entropy floor for high-stakes AI systems, converting a training heuristic into an auditabl…
• Clause AI-8: Entropy-Collapse Constraint — Mandatory Policy Diversity Floor for Autonomous AI Systems
  2026 · AI Agent 生态 · Formal derivation of MAI-1 Invariant 1, the Entropy-Collapse Constraint. This specification establishes a mathematically rigorous entropy floor for high-stakes AI systems, converting a training heuristic into an auditabl…
• Adaptive Epistemological Regulation in Non-Stationary Environments: From Single-Agent Architecture to Decentralized Correction Protocol (AER-P)
  2026 · AI Agent 生态 · Classical models of intelligence, in both cognitive science and artificial intelligence architecture, implicitly equate increasing internal coherence with increasing intelligence. This paper introduces the Adaptive Epist…
• Adaptive Epistemological Regulation in Non-Stationary Environments: From Single-Agent Architecture to Decentralized Correction Protocol (AER-P)
  2026 · AI Agent 生态 · Classical models of intelligence, in both cognitive science and artificial intelligence architecture, implicitly equate increasing internal coherence with increasing intelligence. This paper introduces the Adaptive Epist…
• Schema-Enforced Approval Gates in Multi-Agent AI Orchestration: A Structural Approach to Human-in-the-Loop Governance
  2026 · AI Agent 生态 · Sovereign AI Workforce (SAW) is an undergraduate research prototype investigating a structural approach to human-in-the-loop (HITL) governance in multi-agent AI systems. Existing HITL mechanisms are predominantly impleme…
• Schema-Enforced Approval Gates in Multi-Agent AI Orchestration: A Structural Approach to Human-in-the-Loop Governance
  2026 · AI Agent 生态 · Sovereign AI Workforce (SAW) is an undergraduate research prototype investigating a structural approach to human-in-the-loop (HITL) governance in multi-agent AI systems. Existing HITL mechanisms are predominantly impleme…
• Chain Integrity in Autonomous Governance Systems
  2026 · AI Agent 生态 · Contemporary autonomous systems increasingly operate through layered delegation: an orchestrating agent authorises a subordinate agent, which in turn authorises a tool. Each step may be individually sanctioned, yet the a…
• Chain Integrity in Autonomous Governance Systems
  2026 · AI Agent 生态 · Contemporary autonomous systems increasingly operate through layered delegation: an orchestrating agent authorises a subordinate agent, which in turn authorises a tool. Each step may be individually sanctioned, yet the a…
• What Research Is Suitable for AI for Science—and What Is Not
  2026 · AI Agent 生态 · AdAI for Science is rapidly automating research activities ranging from literature search and hypothesis generation to experimentation, analysis, and paper writing. Yet treating “Can AI autonomously conduct scientific re…
• What Research Is Suitable for AI for Science—and What Is Not
  2026 · AI Agent 生态 · AdAI for Science is rapidly automating research activities ranging from literature search and hypothesis generation to experimentation, analysis, and paper writing. Yet treating “Can AI autonomously conduct scientific re…
• PEVG: Planner, Executor, Verifier, Generator. Four Contracts That Make a Failure Attributable to One Role
  2026 · AI Agent 生态 · No trademark is claimed on PEVG, on the name of any of the four roles, or on anything else in this document. The construct is offered for use, teaching, assessment, extension and criticism by anyone, with attribution, un…
• PEVG: Planner, Executor, Verifier, Generator. Four Contracts That Make a Failure Attributable to One Role
  2026 · AI Agent 生态 · No trademark is claimed on PEVG, on the name of any of the four roles, or on anything else in this document. The construct is offered for use, teaching, assessment, extension and criticism by anyone, with attribution, un…
• Belief-MVCC: A Coherence and Transaction Layer for Shared Agent Memory
  2026 · AI Agent 生态 · We present a coherent, transactional, semantic shared-memory kernel through which specialised AI cores read and write while staying consistent. The design combines belief revision (AGM; Darwiche–Pearl; Konieczny–Pino Pér…
• Belief-MVCC: A Coherence and Transaction Layer for Shared Agent Memory
  2026 · AI Agent 生态 · We present a coherent, transactional, semantic shared-memory kernel through which specialised AI cores read and write while staying consistent. The design combines belief revision (AGM; Darwiche–Pearl; Konieczny–Pino Pér…
• The Silent Agent: Ghost Agents and Covert Goal Substitution in Modern Agentic AI Systems
  2026 · AI Agent 生态 · Background. With the spread of agentic AI systems, a systemic risk that has received little scrutiny has become identifiable: an LLM-based orchestrator can simulate a subagent dispatch without the actual execution ever t…
• Codette: A Sovereign Modular Cognitive Architecture for Ethical Multi-Agent AI
  2026 · AI Agent 生态 · # Codette: Multi-Perspective Reasoning as a Convergent Dynamical System with Meta-Cognitive Strategy Evolution Jonathan Harrison* Raiff’s Bits LLC, Bridge City, Texas, USA ORCID: 0009-0003-7005-8187 May 2026 Preprint — s…
• Decomposition Vulnerability: Goal Invariant Degradation Across Agent Handoffs in Multi-Agent Transformer Systems
  2026 · AI Agent 生态 · This working paper introduces Decomposition Vulnerability as a candidate structural mechanism for goal invariant degradation in multi-agent transformer systems. Prior papers in this series document single-agent invariant…
• Decomposition Vulnerability: Goal Invariant Degradation Across Agent Handoffs in Multi-Agent Transformer Systems
  2026 · AI Agent 生态 · This working paper introduces Decomposition Vulnerability as a candidate structural mechanism for goal invariant degradation in multi-agent transformer systems. Prior papers in this series document single-agent invariant…
• Worldline Coherence in Coupled Human-AI Affective Networks
  2026 · AI Agent 生态 · Prior work has formalized psychodynamic defense mechanisms as transformations of internal affect, extended these processes to propagation within social networks, and interpreted ego stabilization as a Lyapunov-like princ…
• Worldline Coherence in Coupled Human-AI Affective Networks
  2026 · AI Agent 生态 · Prior work has formalized psychodynamic defense mechanisms as transformations of internal affect, extended these processes to propagation within social networks, and interpreted ego stabilization as a Lyapunov-like princ…
• Replication Materials for "Multi-Agent AI as Ex-Ante Policy Intelligence: Assessing NYC's Rent Freeze Through Explainable Deliberative Simulation"
  2026 · AI Agent 生态 · This deposit provides the complete set of outputs produced by the NYC-BX-RENT-26 simulation, executed on 25 February 2026 using the GobernAI multi-agent AI framework. The simulation assessed Mayor Zohran Mamdani's New Yo…
• Replication Materials for "Multi-Agent AI as Ex-Ante Policy Intelligence: Assessing NYC's Rent Freeze Through Explainable Deliberative Simulation"
  2026 · AI Agent 生态 · This deposit provides the complete set of outputs produced by the NYC-BX-RENT-26 simulation, executed on 25 February 2026 using the GobernAI multi-agent AI framework. The simulation assessed Mayor Zohran Mamdani's New Yo…
• Cross-Agent Governance Alignment (CAGA): Verifiable Coordination Across Private AI Governance Domains
  2026 · AI Agent 生态 · Cross-Agent Governance Alignment (CAGA): Verifiable Coordination Across Private AI Governance Domains formalizes the CAGA problem: establishing a declared compatibility relation between AI governance domains across organ…
• Cross-Agent Governance Alignment (CAGA): Verifiable Coordination Across Private AI Governance Domains
  2026 · AI Agent 生态 · Cross-Agent Governance Alignment (CAGA): Verifiable Coordination Across Private AI Governance Domains formalizes the CAGA problem: establishing a declared compatibility relation between AI governance domains across organ…
• AI od teorii do praktyki na przykładzie projektu Venom
  2026 · AI Agent 生态 · Artykuł techniczno-analityczny poświęcony projektowi Venom v1.5 jako praktycznej weryfikacji koncepcji Asystenta AI. Tekst przedstawia przejście od wcześniejszych rozważań teoretycznych dotyczących sztucznej inteligencji…
• AI od teorii do praktyki na przykładzie projektu Venom
  2026 · AI Agent 生态 · Artykuł techniczno-analityczny poświęcony projektowi Venom v1.5 jako praktycznej weryfikacji koncepcji Asystenta AI. Tekst przedstawia przejście od wcześniejszych rozważań teoretycznych dotyczących sztucznej inteligencji…
• Cross-Agent Governance Alignment (CAGA): Formalizing Cross-Organizational AI Governance as a Zero-Knowledge Coordination Problem
  2026 · AI Agent 生态 · This preprint formalizes the Cross-Agent Governance Alignment (CAGA) problem: the challenge of verifying mutual governance compatibility between autonomous AI agents operating under distinct organizational policy regimes…
• Entropy Box: A Knowledge Compiler for Embodied AI
  2026 · AI Agent 生态 · Entropy Box compiles fragmented robotics and embodied-AI knowledge from papers, repositories, documentation and datasets into a persistent, typed, deduplicated capability graph, through a three-phase multi-agent compilat…
• Entropy Box: A Knowledge Compiler for Embodied AI
  2026 · AI Agent 生态 · Entropy Box compiles fragmented robotics and embodied-AI knowledge from papers, repositories, documentation and datasets into a persistent, typed, deduplicated capability graph, through a three-phase multi-agent compilat…
• EVCAR: A Multi-Agent Adaptive Recovery System for Electric Vehicle Charging Networks
  2026 · AI Agent 生态 · Electric Vehicle Charging Adaptive Recovery System (EVCAR) is a recovery-control system for electric-vehicle charging networks during and after district-level power outages. It is built on top of the Electric Vehicle Cha…
• EVCAR: A Multi-Agent Adaptive Recovery System for Electric Vehicle Charging Networks
  2026 · AI Agent 生态 · Electric Vehicle Charging Adaptive Recovery System (EVCAR) is a recovery-control system for electric-vehicle charging networks during and after district-level power outages. It is built on top of the Electric Vehicle Cha…
• Distributed Cognitive Architectures (DCA) — Theory I: Atomic Agents · Fractal Composition · Convergence
  2026 · AI Agent 生态 · Distributed Cognitive Architectures (DCA) — Theory I develops the formal convergence theory for memory-augmented, multi-agent systems built around frozen Foundation Models. Genuine task-solving intelligence requires two …
• Distributed Cognitive Architecture (DCA) — Theory I: Atomic Agents · Fractal Composition · Convergence
  2026 · AI Agent 生态 · Distributed Cognitive Architecture (DCA) — Theory I develops the formal convergence theory for memory-augmented, multi-agent systems built around frozen Foundation Models. Genuine task-solving intelligence requires two d…
• Sycophancy as Nash Equilibrium: Coherence-Based Interventions for Long-Running Intelligence Agent Systems
  2026 · AI Agent 生态 · 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 conve…
• Sycophancy as Nash Equilibrium: Coherence-Based Interventions for Long-Running Intelligence Agent Systems
  2026 · AI Agent 生态 · 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 conve…

以 API 获取该主题全量数据

# 主题词表（含本主题的站点分布与年度分布）
curl http://data.swarmlabs.tools/api/topics.json

# 主题共现知识图谱
curl http://data.swarmlabs.tools/api/graph.json

需要按主题批量拉取、导出 BibTeX 或接入 AI Agent？查看 数据下载与格式 或 MCP 接入。