主题图谱 / multi-agent systems

multi-agent systems

GeneTech 知识引擎共收录 2765 篇相关科研实体，横跨 30 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）

• LLM-Based Multi-Agent Orchestration: A Survey of Frameworks, Communication Protocols, and Emerging Patterns
  2026 · AI Agent 生态 · The proliferation of large language model (LLM) agents has enabled increasingly complex 2 multi-step automation; however, composing multiple agents into coherent systems intro3 duces significant orchestration challenges …
• MIN-Trust: A Minimum Necessary Information Trust Orchestration Framework for Multi-Agent Collaboration
  2026 · AI Agent 生态 · Large language model (LLM)-based multi-agent systems have demonstrated remarkable capabilities in collaborative task solving. Although the mechanisms that facilitate seamless cooperation, such as shared contexts, role as…
• Evaluating routing stability and coordination in swarm-based multi-agent task-oriented dialogue systems.
  2026 · AI Agent 生态 · Conversational systems are becoming a primary interface for services and enterprise automation, and rapid market growth is pushing deployments into safety- and cost-sensitive settings. Reliability remains a bottleneck wh…
• HABIT: A Self-Evolving AI-Agent Harness for GUI-Based CAE Software---Application to Aerospace
  2026 · AI Agent 生态 · Abstract GUI-based CAE software sits at the center of aerospace analysis workflows, yet interacting with it remains a labor-intensive bottleneck. Embedding foundation-model agents inside such software demands two capabil…
• Agent Name Service (ANS): A Universal Directory for Secure AI Agent Discovery and Interoperability
  2026 · AI Agent 生态 · The proliferation of AI agents requires robust mechanisms for secure discovery. This paper introduces the Agent Name Service (ANS), a novel architecture based on DNS addressing the lack of a public agent discovery framew…
• ClinOrch: A Privacy-preserving, Doctor-configurable Multi-Agent Clinical Intelligence Architecture for Pre-consultation, Physician Support, and Longitudinal Care Orchestration
  2026 · AI Agent 生态 · Clinical encounters are increasingly constrained by fragmented records, incomplete patient histories, administrative burden, <br> guideline complexity, and limited physician time. This paper proposes ClinOrch, a pr…
• Transforming Public Administration Workflows with Multi-Agent AI: A Human-in-the-Loop Knowledge Orchestration Framework
  2026 · AI Agent 生态 · Public administrations face increasing pressure to manage large volumes of institutional knowledge while ensuring transparency, accountability, and timely responses to citizen and council inquiries. This paper presents C…
• Beyond Agent Design: A Systematic Framework for MCP Server Runtime Orchestration
  2026 · AI Agent 生态 · The Model Context Protocol (MCP) has rapidly emerged as a standard interface for connecting AI agents to external tools, databases, and services. While considerable research has addressed agent design, prompt engineering…
• Financial Info AI Agent: Building a High-Accuracy Agentic Workflow for Investor Relations Analytics
  2026 · AI Agent 生态 · Building enterprise-grade chat agents capable of answering questions across both structured and unstructured financial data remains a fundamental challenge. The Financial Info AI Agent addresses this by implementing a du…
• Before You Build a Multi-Agent System: An Escalation Framework for LLM Adaptation
  2026 · AI Agent 生态 · Multi-agent systems (MAS) have become a popular framework for deploying large language models (LLMs), yet their operational complexity—increased latency, compounding errors, and difficult-to-optimize orchestration—is oft…
• Synthetic Managerial Agents: A Multi-LLM Ensemble Framework for Computational Agent-Based Theory Exploration
  2026 · AI Agent 生态 · We introduce Synthetic Managerial Agents (SMA), a novel computational methodology that advances agentbased modeling (ABM) by replacing rigid behavioral rules with Large Language Model (LLM)-powered agents capable of flex…
• COLLAB-LLM: A Communication-Centric Role-Based Framework for Scalable Multi-Agent LLM Collaboration
  2026 · AI Agent 生态 · Large Language Models (LLMs) are increasingly deployed in multi-agent systems; however, existing frameworks continue to suffer from communication ambiguity, coordination failures, and poor scalability as task complexity …
• Skill Orchestration Agent: A Knowledge-Driven Orchestration Framework for Adaptive Manufacturing Control
  2025 · AI Agent 生态 · The Skill Orchestration Agent (SkillOA) introduces a modular, distributed approach to manufacturing control, enhancing flexibility beyond traditional programmable logic controllers (PLCs). It is capable of determining an…
• 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…
• An Agent-based Modeling Approach for Effective Innovation Ecosystem Orchestration
  2023 · AI Agent 生态 · Innovation ecosystems are classified as one of the complex economic systems where many parties with different interests are involved. The holistic objective of such alignment of entities is to cooperate in the creation o…
• Accountability Chains: A Formal Specification for AI Agent Delegation
  2026 · AI Agent 生态 · Recent formal work on human-agent collectives identifies an Accountability Horizon: a computable autonomy threshold above which single-locus accountability cannot satisfy a set of minimal axioms simultaneously (Tibebu, 2…
• OpenAI single-agent LLM architecture reduces computational overhead relative to multi-agent orchestration in a simulated mars rover decision-support benchmark.
  2026 · AI Agent 生态 · Mars rover missions require decision-support systems that can interpret terrain, telemetry, environmental conditions, and mission objectives under delayed communication with Earth. This study evaluates whether multi-agen…
• From Organizational Knowledge to AI Agent Memory: Empirical Validation of the SECI Model on the LongMemEval Benchmark
  2026 · AI Agent 生态 · Abstract AI agent memory systems face a fundamental design question: should conversational history be stored verbatim or transformed into structured knowledge before retrieval? We propose that the SECI model of knowledge…
• When Bots Browse: Measuring Advertising Visibility in an AI-Agent Internet
  2026 · AI Agent 生态 · Abstract AI assistants increasingly read webpages on a user's behalf. When that happens, the assistant becomes an intermediary between the publisher and the user, and it is the assistant, not the page layout, that decide…
• AgentVerify: Compositional Formal Verification of AI Agent Safety Properties via LTL Model Checking
  2026 · AI Agent 生态 · Autonomous AI agents operating in high-stakes domains—financial trading, medical diagnostics, autonomous code execution—lack formal safety guarantees for their core operational loops, including memory management, tool in…
• Semantic Tracing in LLM-Based Multi-Agent Systems Using LangChain, LangGraph, and LangSmith for AI Governance
  2026 · AI Agent 生态 · Abstract Autonomous multi-agent systems built on large language models exchange goals, constraints, evidence commitments, and tool-mediated actions through natural-language handoffs. Across hops, semantic meaning may dri…
• Code Broker A Multi Agent System for Automated Code Quality Assessment
  2026 · AI Agent 生态 · Abstract We present Code Broker, a multi-agent system built with Google’s Agent Development Kit (ADK) that analyses Python code from files, local directories, or GitHub repositories and generates actionable quality asses…
• An Integrated Observability Intelligence Framework: Bridging Semantic Data Modeling, Caching, and LLM-Powered Multi-Agent Root Cause Analysis
  2026 · AI Agent 生态 · Abstract Modern cloud-native systems generate heterogeneous observability data at unprecedented scale, yet two critical gaps persist in operational intelligence. First, distributed analytical consumers independently reco…
• Multi-Agent System for Dynamic Business KPI Selection, Evaluation and Quantification Based on Oracle EBS
  2026 · AI Agent 生态 · The growing complexity of enterprise resource planning (ERP) systems necessitates intel-ligent approaches for dynamically identifying and evaluating key performance indicators (KPIs) that accurately reflect organizationa…
• Governing Autonomous Enterprises: A Transaction Cost Perspective on Multi-Agent AI Systems in Supply Chain Operations
  2026 · AI Agent 生态 · Abstract Problem definition : The rapid proliferation of autonomous multi-agent AI systems (MAS) in enterprise environments creates novel governance challenges that existing business frameworks have not addressed. Releva…
• Agora: A Drive-Based Framework for Agent Difffferentiation in Multi-Agent LLM Systems
  2026 · AI Agent 生态 · Abstract Current multi-agent LLM systems difffferentiate agents through hand-crafted roles or layer-stacking architectures. We propose Agora, a framework that difffferentiates agents through six continuous drives (boredo…
• <em>Agent Action Classifier</em>: Classifying AI Agent Actions to Ensure Safety and Reliability
  2025 · AI Agent 生态 · Autonomous AI agents are increasingly being deployed to perform complex tasks with limited human oversight. Ensuring that the actions proposed or executed by such agents are safe, lawful, and aligned with human values is…
• Hinton Hypothesis and Competition in Artificial Intelligence: A Qualitative Uncertainty Principle of Invisible Hand in a Possible AI-Agent Society
  2025 · AI Agent 生态 · The present paper reframes what we call the Hinton Hypothesis, which states that everything of human nature can be duplicated in artificial intelligence. We consider competition to be a significant aspect of human nature…
• LLM-based multi-agent system for neuro-ophthalmic diagnosis and personalized treatment planning.
  2025 · AI Agent 生态 · Introduction Ophthalmic findings can non-invasively reflect nervous-system status. We present an LLM-based multi-agent framework that preserves diagnostic uncertainty to support neuro-ophthalmic screening and referral. M…
• Multi-Agent Orchestration: Coordination, Trust, and Cascading Failures
  2026 · AI Agent 生态 · Background. Agentic artificial intelligence systems, defined by their capacity to reason, plan, and act autonomously through external tools and environments, represent a categorical shift in the operational profile of de…
• Tool Orchestration in Production Agent Systems: Code vs Protocols
  2026 · AI Agent 生态 · Model Context Protocol (MCP) has emerged as a promising way to standardize how AI agents discover and invoke tools. That promise is real: MCP improves interoperability by giving tools a consistent interface that multiple…
• Centralized Agent Orchestration in Multi-Agent Systems
  2026 · AI Agent 生态 · The article describes the problem of agent orchestration in multi-agent systems based on large neural networks, which arises when creating intelligent assistants. The paper examines various architectural patterns used in…
• Contract-Gated Execution: A Deterministic Governance Layer for Autonomous AI Agent Orchestration
  2026 · AI Agent 生态 · This submission responds to the OECD's call for implementation tools that enable trustworthy AI deployment in consequential domains. Contract-gated execution was developed as commercial infrastructure and is presented he…
• Geospatial AI (GeoAI) agent stack : router-based orchestration and design rationale
  2026 · AI Agent 生态 · This report summarizes the current state of a router-based, multiagent Geospatial AI (GeoAI) system designed to reliably execute geospatial workflows while retaining the flexibility of large language model (LLM) reasonin…
• Contamination Percolation in Multi-Agent LLM Systems: A Measurement Framework and Benchmark
  2026 · AI Agent 生态 · Multi-agent large language model (LLM) systems are being deployed in healthcare, finance, and legal settings, yet we lack reliable methods for measuring how misinformation spreads through these networks. We introduce Con…
• Agentic Workflow Drift and Agentic Workflow Subversion: A New Risk Taxonomy for the Governance of Agentic AI in Financial Services
  2026 · AI Agent 生态 · <p>Banks are beginning to deploy AI systems that do not just automate decisions — they determine whether decisions should be made at all. As agentic AI moves into workflow orchestration, a new failure mode is emerging wo…
• Trustworthy Transaction Arena (TTA): A Governance Architecture for Multi-Actor Agentic AI Systems with Probabilistic Workflow Verification
  2026 · AI Agent 生态 · Existing multi-agent frameworks evaluate correctness only at the team outcome level: if the agent team achieves its goal, the transaction is deemed successful. This is insufficient for business and social activities, whi…
• Evaluating Agentic AI Workflows in Finance: A Harness for Grounding, Stability, Permissioning, Prompt Injection, and Workflow Ablation
  2026 · AI Agent 生态 · We present an evaluation harness for agentic AI workflows in finance. Its defining choice is the unit of evaluation: the workflow's artifact — a memo, a signal proposal, a screening recommendation — rather than a single …
• {{Complete}}™ {[List]} of Coinbase® CUSTOMER© SERVICE℗ Contact Numbers — 24/7 Live Agent Support GUide 2026
  2026 · AI Agent 生态 · {{Complete}}™ {[List]} of Coinbase® CUSTOMER© SERVICE℗ Contact Numbers -24/7 Live Agent Support GUide 2026 Reaching a live representative 1-844-530-29.22** or 1-844-530-29.22** (OTA) at Coinbase® can make all the differe…
• Why Your AI Agent Can't Make Money: The Real Reason AI Cost-Cutting Fails
  2026 · AI Agent 生态 · &lt;p&gt;AI adoption has reached 78% across major organizations, yet over 80% report no measurable performance improvement (McKinsey, 2025). This paper argues that the failure is not a product quality problem. It is a st…
• Relational Integrity in Multi-Agent AI Systems: A Polarity Model Framework for Human-AI Safety
  2026 · AI Agent 生态 · &lt;p&gt;This paper presents a novel AI safety architecture derived from the Polarity Model — a cross-scale structural framework for understanding agent, relational, and systemic dynamics (Vimberg, 2026; SSRN 6681058). C…
• From Agent Identity to Agent Economy: Measuring the Operational Readiness of ERC-8004 AI Agents
  2026 · AI Agent 生态 · This paper examines whether blockchain-registered AI agents demonstrate operational readiness beyond identity registration. Using a dataset of ERC-8004 agents on Ethereum, we construct an agent-level feature table coveri…
• AEGIS: Agent Execution Governance and Integrity Standard — A Survey and Reference Architecture for AI Agent Action Accountability
  2026 · AI Agent 生态 · As organizations deploy AI agents to execute tasks in business processes, to our knowledge, no systematic academic framework exists for recording, verifying, and ensuring accountability for their actions. This study surv…
• MurphyGuard: A Failure-First Framework for AI Agent Guardrails
  2026 · AI Agent 生态 · As autonomous AI agents transition from research prototypes to production-grade systems — executing code, calling APIs, managing infrastructure, and interacting with users at scale — the question of safety is no longer t…
• Safety-aware AI for oncology trial pre-screening: a comparative study of rule-based, single-agent, and multi-agent approaches
  2026 · AI Agent 生态 · Background. Oncology trial pre-screening is a high-risk clinical decision support task in which complex eligibility criteria must be matched against heterogeneous patient information. Unsafe false inclusion—incorrectly l…
• Agentic Data Pipeline Orchestration with Multi-Agent AI
  2026 · AI Agent 生态 · Enterprise data platforms run thousands of workflows, but day-two issues schema drift, flaky upstreams, warehouse contention, broken credentials, and endless backfills still cause major operational pain and require cross…
• Agentic AI in Private Equity: Multi-Agent Orchestration for End-to-End Deal Workflows
  2026 · AI Agent 生态 · The term "agentic AI" has become the most overused phrase in enterprise software marketing. Every vendor now claims autonomous agents, yet most offerings amount to linear prompt chains wrapped in a loop. This paper separ…
• Autonomous CI/CD Quality Assurance Using LangGraph Multi-Agent Orchestration and Risk-Proportionate HITL Control
  2026 · AI Agent 生态 · Modern software delivery requires quality assurance that scales with development velocity. Manual test coordination, sequential test execution, and static risk assessment create bottlenecks that constrain release frequen…
• Hierarchical Multi-agent Orchestration in Oracle Fusion Cloud ERP: Designing Supervisory Agent Architectures for End-to-End Order-to-Cash and Procure-to-Pay Automation
  2026 · AI Agent 生态 · Enterprise Resource Planning systems occupy a foundational role in how organisations coordinate their most critical business processes, yet the architecture governing these systems has long remained sequential, transacti…
• Agent-Driven Orchestration for RESTful Enterprise APIs
  2026 · AI Agent 生态 · Orchestration mechanisms in distributed enterprise systems must be adaptable to runtime variability and governed by compliance; however, static rule-based REST orchestration cannot handle transient failures, nondetermini…
• Hierarchical Multi-Agent Orchestration for Automated Dispute Resolution
  2026 · AI Agent 生态 · The subject of automated dispute resolution has become the essential field of research in artificial intelligence, legal informatics, and digital governance. As commercial transactions in the industry quickly become digi…
• Multi-Agent Orchestration for Intent-Based Network Operations: Automated Diagnosis and Remediation at Scale
  2026 · AI Agent 生态 · Modern network infrastructures have grown beyond the capacity of traditional ticket-based management systems, creating operational bottlenecks and extended resolution times. Multi-agent orchestration introduces a paradig…
• Design of Multi Agent Autonomous Workflow Systems using Agentic AI Frameworks
  2026 · AI Agent 生态 · The objective of this paper is to examine the construction and design of multi-agent autonomous workflow systems (MAWS) that utilize agentic AI systems, as well as their impact on the evolution of business systems and th…
• &lt;span&gt;Mandate&lt;/span&gt;: Underwriting, Monitoring and Governing AI Agents that Transact and Borrow A Credit-Risk and Accountability Workflow for Agentic Commerce
  2026 · AI Agent 生态 · Autonomous and semi-autonomous AI agents have begun to transact and, in short order, will borrow on behalf of consumers and businesses. The payment industry has moved quickly to build the rails for this: identity, author…
• Agentic AI-Driven Workflow Orchestration in Loan Trading Platforms: A Microservices and Hybrid Cloud Architecture Perspective
  2026 · AI Agent 生态 · Loan trading platforms operate as long-running, failure-prone distributed systems where workflow orchestration directly impacts correctness, tail latency, and operational cost. Conventional orchestrators implement static…
• Who Sent This Agent? Cryptographic Organizational Identity for the Autonomous Agent Economy
  2026 · AI Agent 生态 · &lt;div&gt; The emerging autonomous agent economy requires a payment capability that no existing rail provides: microtransactions with accountability. Fiat payment rails provide accountability but cannot support &lt;span…
• An LLM-Based Multi-Agent Framework for Autonomous Business Lead Intelligence Using Public Web Data
  2026 · AI Agent 生态 · Business lead intelligence-the task of discovering commercial entities, resolving their identity, enriching them with contact and firmographic attributes, and prioritising them for outreach-is today served either by prop…
• Persistent Identity in LLM Multi-Agent Systems: A Semantic Consensus Framework for Heterogeneous AI Swarms
  2026 · AI Agent 生态 · Large Language Models (LLMs) are increasingly deployed as autonomous agents capable of persistent memory, role specialization, and collaborative reasoning. While recent work has explored multi-agent LLM systems, most arc…
• GraphShield: A Graph-Structured Defense Framework for Prompt Injection in RAG and Multi-Agent LLM Systems
  2026 · AI Agent 生态 · GraphShield is a graph-structured defense framework for LLMs that represents system prompts, retrieved knowledge, agents, and parsed instructions as directed Trust-Knowledge Graph (TKG). Security is formalized as reachab…
• Red-Agent: A Practical Multi-Provider Framework for LLM Red Teaming with Operational Reachability and Artifact-Complete Reporting
  2026 · AI Agent 生态 · We present Red-Agent, a practical multi-provider framework for LLM red teaming focused on reliable cross-model execution, artifact completeness, and reproducible reporting. The empirical results in this paper come from a…

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 https://data.swarmlabs.tools/api/topics.json

# 主题共现知识图谱
curl https://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。