AI Agent 生态 · 全部实体（第 94 / 100 页）

本页收录第 9301–9400 条，共 10000 条 · 返回 AI Agent 生态 首页

• AdaptOrch: Task-Adaptive Multi-Agent Orchestration in the Era of LLM Performance Convergence
  As large language models from diverse providers converge toward comparable benchmark performance, the traditional paradigm of selecting a single best model per task yields diminishing returns. We argue that orchestration topology -- the structural composition …
  arxiv Geunbin Yu 2026-02-18T21:00:05Z 置信度 0.78 cs.MAcs.AI
• VAmoS Bench: Voice Agent Simulation Bench
  Production voice agents span cascaded, speech-to-speech, and hybrid architectures. Voice-agent benchmarks typically measure component quality and conversational properties such as word error rate, latency, naturalness, and turn-taking. Fewer measure whether th…
  arxiv Joshua Meyer, Sahar Shayegan, Ritiz Tambi, Ali Khan 等 2026-07-29T20:42:38Z 置信度 0.78 cs.AI
• The Orchestration of Multi-Agent Systems: Architectures, Protocols, and Enterprise Adoption
  Orchestrated multi-agent systems represent the next stage in the evolution of artificial intelligence, where autonomous agents collaborate through structured coordination and communication to achieve complex, shared objectives. This paper consolidates and form…
  arxiv Apoorva Adimulam, Rajesh Gupta, Sumit Kumar 2026-01-20T07:13:53Z 置信度 0.78 cs.MAcs.AI
• Small Model as Master Orchestrator: Learning Unified Agent-Tool Orchestration with Parallel Subtask Decomposition
  Multi-agent systems (MAS) demonstrate clear advantages in tackling complex problems by coordinating diverse agents and external tools. However, most existing orchestration methods rely on static workflows or serial agent scheduling, and are further constrained…
  arxiv Wenzhen Yuan, Wutao Xiong, Fanchen Yu, Shengji Tang 等 2026-04-18T14:41:27Z 置信度 0.78 cs.AI
• FIPA-based Interoperable Agent Mobility Proposal
  This paper presents a proposal for a flexible agent mobility architecture based on IEEE-FIPA standards and intended to be one of them. This proposal is a first step towards interoperable mobility mechanisms, which are needed for future agent migration between …
  arxiv Jordi Cucurull, Ramon Marti, Sergi Robles, Joan Borrell 等 2007-06-13T14:37:58Z 置信度 0.78 cs.MAcs.NI
• Position: agentic AI orchestration should be Bayes-consistent
  LLMs excel at predictive tasks and complex reasoning tasks, but many high-value deployments rely on decisions under uncertainty, for example, which tool to call, which expert to consult, or how many resources to invest. While the usefulness and feasibility of …
  arxiv Theodore Papamarkou, Pierre Alquier, Matthias Bauer, Wray Buntine 等 2026-05-01T15:43:43Z 置信度 0.78 cs.AIcs.LGstat.ML
• Learning Reward Machines in Cooperative Multi-Agent Tasks
  This paper presents a novel approach to Multi-Agent Reinforcement Learning (MARL) that combines cooperative task decomposition with the learning of reward machines (RMs) encoding the structure of the sub-tasks. The proposed method helps deal with the non-Marko…
  arxiv Leo Ardon, Daniel Furelos-Blanco, Alessandra Russo 2023-03-24T15:12:28Z 置信度 0.78 cs.AIcs.MAcs.SC
• A General Equilibrium Theory of Orchestrated AI Agent Systems
  We establish a general equilibrium theory for systems of large language model (LLM) agents operating under centralized orchestration. The framework is a production economy in the sense of Arrow-Debreu (1954), extended to infinite-dimensional commodity spaces f…
  arxiv Jean-Philippe Garnier 2026-02-23T13:21:32Z 置信度 0.78 cs.GTcs.AImath.OC
• OrchBench: Evaluating Multi-Agent Orchestration Plans in Isolation via Deterministic Simulation
  Complex tasks often decompose into parallelizable yet interdependent subtasks, making orchestration critical to the performance of multi-agent systems (MAS). Existing evaluations typically rely on end-to-end execution, which conflates orchestration-plan qualit…
  arxiv Zhenzhen Ren, Jiyan He, Xinpeng Zhang, Zhenxing Qian 等 2026-07-28T12:43:34Z 置信度 0.78 cs.AI
• Role-Based Agentic AI for Intent-Driven Network and Service Orchestration
  Telecommunication networks are increasingly complex due to heterogeneous technologies, diverse service requirements, and growing demands for resource efficiency and business agility. Intent-Based Networking (IBN) and, more recently, agentic AI have emerged as …
  arxiv Juan Parra-Ullauri, Talha Ahmed Khan, Daniel McHugh, Shipra Kapoor 等 2026-05-06T08:10:01Z 置信度 0.78 cs.NIcs.AI
• Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis
  Unified multimodal models provide a natural and promising architecture for understanding diverse and complex real-world knowledge while generating high-quality images. However, they still rely primarily on frozen parametric knowledge, which makes them struggle…
  arxiv Shuang Chen, Quanxin Shou, Hangting Chen, Yucheng Zhou 等 2026-03-31T11:41:13Z 置信度 0.78 cs.CVcs.MM
• MegaFlow: Large-Scale Distributed Orchestration System for the Agentic Era
  The rapid development of interactive and autonomous AI systems signals our entry into the agentic era. Training and evaluating agents on complex agentic tasks such as software engineering and computer use requires not only efficient model computation but also …
  arxiv Lei Zhang, Mouxiang Chen, Ruisheng Cao, Jiawei Chen 等 2026-01-12T13:25:33Z 置信度 0.78 cs.DCcs.SE
• Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces
  As large language model (LLM) agents evolve from isolated tool users into coordinated teams, reinforcement learning (RL) must optimize not only individual actions but also how work is spawned, delegated, communicated, aggregated, and stopped. This paper studie…
  arxiv Chenchen Zhang 2026-05-04T16:42:18Z 置信度 0.78 cs.CL
• Internet of Agentic Things: Networked AI Agents for Closed-Loop IoT Orchestration
  The paper introduces the Internet of Agentic Things (IoAT), an architectural framework that integrates agentic AI, IoT, cyber-physical systems, Physical AI, edge computing, and digital twins into a unified closed-loop orchestration framework. The proposed arch…
  arxiv Quanyan Zhu 2026-07-14T11:43:30Z 置信度 0.78 cs.AIcs.MAeess.SY
• SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration
  In recent years, a variety of powerful LLM-based agentic systems have been applied to automate complex tasks through task orchestration. However, existing orchestration methods still face key challenges, including strategy collapse under reward maximization, h…
  arxiv Mingda Zhang, Tiesunlong Shen, Haoran Luo, Wenjin Liu 等 2026-05-13T20:14:44Z 置信度 0.78 cs.AI
• ORCHID: Fairness-Aware Orchestration in Mission-Critical Air-Ground Integrated Networks
  Unmanned Aerial Vehicles (UAVs) provide pivotal on-demand wireless coverage for mission-critical 6G Air-Ground Integrated Networks (AGINs). However, traditional Deep Reinforcement Learning (DRL) orchestration struggles with multi-agent non-stationarity and bal…
  arxiv Chuan-Chi Lai, Chi Jai Choy 2026-02-10T17:18:56Z 置信度 0.78 cs.NI
• GraphBit: A Graph-based Agentic Framework for Non-Linear Agent Orchestration
  Agentic LLM frameworks that rely on prompted orchestration, where the model itself determines workflow transitions, often suffer from hallucinated routing, infinite loops, and non-reproducible execution. We introduce GraphBit, an engine-orchestrated framework …
  arxiv Yeahia Sarker, Md Rahmat Ullah, Musa Molla, Shafiq Joty 2026-03-08T18:32:28Z 置信度 0.78 cs.AIcs.CLcs.DC
• Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale
  The rapid proliferation of Claude agent skills has raised the central question of how to effectively leverage, manage, and scale the agent skill ecosystem. In this paper, we propose AgentSkillOS, the first principled framework for skill selection, orchestratio…
  arxiv Hao Li, Chunjiang Mu, Jianhao Chen, Siyue Ren 等 2026-03-02T18:46:47Z 置信度 0.78 cs.CL
• MRMMIA: Membership Inference Attacks on Memory in Chat Agents
  Membership inference attacks (MIAs) test whether a target data record belongs to a system's private data, and have become a standard tool to measure privacy leakage in machine learning systems. Prior work has primarily focused on training corpora or retrieval …
  arxiv Kai Chen, Yan Pang, Tianhao Wang 2026-05-27T01:31:40Z 置信度 0.78 cs.CRcs.LG
• Preventing Rogue Agents Improves Multi-Agent Collaboration
  Multi-agent systems, where specialized agents collaborate to solve a shared task hold great potential, from increased modularity to simulating complex environments. However, they also have a major caveat -- a single agent can cause the entire system to fail. C…
  arxiv Ohav Barbi, Ori Yoran, Mor Geva 2025-02-09T18:35:08Z 置信度 0.78 cs.CLcs.MA
• LEMON: Learning Executable Multi-Agent Orchestration via Counterfactual Reinforcement Learning
  Large language models (LLMs) have become a strong foundation for multi-agent systems, but their effectiveness depends heavily on orchestration design. Across different tasks, role design, capacity assignment, and dependency construction jointly affect both sol…
  arxiv Xudong Chen, Yixin Liu, Hua Wei, Kaize Ding 2026-05-14T07:24:09Z 置信度 0.78 cs.AI
• MAViS: A Multi-Agent Framework for Long-Sequence Video Storytelling
  Despite recent advances, long-sequence video generation frameworks still suffer from significant limitations: poor assistive capability, suboptimal visual quality, and limited expressiveness. To mitigate these limitations, we propose MAViS, a multi-agent colla…
  arxiv Qian Wang, Ziqi Huang, Ruoxi Jia, Paul Debevec 等 2025-08-11T21:42:41Z 置信度 0.78 cs.CVcs.AIcs.MA
• Learning Latency-Aware Orchestration for Multi-Agent Systems
  Multi-agent systems (MAS) coordinate multiple LLM-powered agents through structured workflows, gaining reasoning power but incurring high inference latency from multi-step execution and repeated model invocations. Existing orchestration methods primarily optim…
  arxiv Xi Shi, Mengxin Zheng, Qian Lou 2026-07-15T00:49:50Z 置信度 0.78 cs.MA
• Extending the Control Plane of Container Orchestrators for I/O Virtualization
  Single Root Input/Output Virtualization (SR-IOV) is a standard technology for forking a single PCI express device and providing it to applications while ensuring performance isolation. It enables container orchestrators to share a limited number of physical ne…
  arxiv Garegin Grigoryan, Minseok Kwon, M. Mustafa Rafique 2025-05-09T13:39:42Z 置信度 0.78 cs.NIeess.SY
• Hierarchical Memory Orchestration for Personalized Persistent Agents
  While long-term memory is essential for intelligent agents to maintain consistent historical awareness, the accumulation of extensive interaction data often leads to performance bottlenecks. Naive storage expansion increases retrieval noise and computational l…
  arxiv Junming Liu, Yifei Sun, Weihua Cheng, Haodong Lei 等 2026-04-02T06:16:53Z 置信度 0.78 cs.AI
• Orchestration Framework for Financial Agents: From Algorithmic Trading to Agentic Trading
  The financial market is a mission-critical playground for AI agents due to its temporal dynamics and low signal-to-noise ratio. Building an effective algorithmic trading system may require a professional team to develop and test over the years. In this paper, …
  arxiv Jifeng Li, Arnav Grover, Abraham Alpuerto, Yupeng Cao 等 2025-12-01T21:50:22Z 置信度 0.78 cs.MAcs.AIcs.CEcs.LG
• Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory
  Recent LLM-based mathematical reasoning agents have begun to tackle research-level problems and, in several cases, have contributed to the resolution of open problems. However, scaling and orchestrating such agents effectively remains challenging, due to the d…
  arxiv Jihao Liu, Guoxiong Gao, Zeming Sun, Bin Wu 等 2026-07-07T16:11:30Z 置信度 0.78 cs.AIcs.CLcs.MA
• Quantifying the effects of environment and population diversity in multi-agent reinforcement learning
  Generalization is a major challenge for multi-agent reinforcement learning. How well does an agent perform when placed in novel environments and in interactions with new co-players? In this paper, we investigate and quantify the relationship between generaliza…
  arxiv Kevin R. McKee, Joel Z. Leibo, Charlie Beattie, Richard Everett 2021-02-16T18:54:39Z 置信度 0.78 cs.MAcs.AI
• MobileUse: A GUI Agent with Hierarchical Reflection for Autonomous Mobile Operation
  Recent advances in Multimodal Large Language Models (MLLMs) have enabled the development of mobile agents that can understand visual inputs and follow user instructions, unlocking new possibilities for automating complex tasks on mobile devices. However, apply…
  arxiv Ning Li, Xiangmou Qu, Jiamu Zhou, Jun Wang 等 2025-07-21T09:37:05Z 置信度 0.78 cs.ROcs.MA
• Towards Effective GenAI Multi-Agent Collaboration: Design and Evaluation for Enterprise Applications
  AI agents powered by large language models (LLMs) have shown strong capabilities in problem solving. Through combining many intelligent agents, multi-agent collaboration has emerged as a promising approach to tackle complex, multi-faceted problems that exceed …
  arxiv Raphael Shu, Nilaksh Das, Michelle Yuan, Monica Sunkara 等 2024-12-06T22:14:17Z 置信度 0.78 cs.CLcs.AI
• MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks
  While multi-agent systems (MAS) promise elevated intelligence through coordination of agents, current approaches to automatic MAS design under-deliver. Such shortcomings stem from two key factors: (1) methodological complexity - agent orchestration is performe…
  arxiv Zixuan Ke, Yifei Ming, Austin Xu, Ryan Chin 等 2026-01-21T04:57:02Z 置信度 0.78 cs.AIcs.CLcs.MA
• An Agentic AI Control Plane for 6G Network Slice Orchestration, Monitoring, and Trading
  6G networks are expected to be AI-native, intent-driven, and economically programmable, requiring fundamentally new approaches to network slice orchestration. Existing slicing frameworks, largely designed for 5G, rely on static policies and manual workflows an…
  arxiv Eranga Bandara, Ross Gore, Sachin Shetty, Ravi Mukkamala 等 2026-01-27T09:50:57Z 置信度 0.78 cs.NIcs.AI
• Focus Is All You Need: Adaptive Goal-aware Attention Orchestration for Multi-Agent Graph Systems
  Large language models (LLMs) enable autonomous agents for reasoning, planning, and tool use. Recent systems increasingly organize these agents as graphs of specialized, interconnected nodes. Although graph-based orchestration supports flexible decomposition an…
  arxiv Mingzhou Fan, Siyuan Xu, Mingxuan Yuan 2026-07-26T14:23:33Z 置信度 0.78 cs.AI
• Dynamic Attentional Context Scoping: Agent-Triggered Focus Sessions for Isolated Per-Agent Steering in Multi-Agent LLM Orchestration
  Multi-agent LLM orchestration systems suffer from context pollution: when N concurrent agents compete for the orchestrator's context window, each agent's task state, partial outputs, and pending questions contaminate the steering interactions of every other ag…
  arxiv Nickson Patel 2026-04-09T07:26:42Z 置信度 0.78 cs.MAcs.AIcs.LG
• Multi-Agent Collaboration via Evolving Orchestration
  Large language models (LLMs) have achieved remarkable results across diverse downstream tasks, but their monolithic nature restricts scalability and efficiency in complex problem-solving. While recent research explores multi-agent collaboration among LLMs, mos…
  arxiv Yufan Dang, Chen Qian, Xueheng Luo, Jingru Fan 等 2025-05-26T07:02:17Z 置信度 0.78 cs.CLcs.AIcs.MA
• Your Code Agent Can Grow Alongside You with Structured Memory
  While "Intent-oriented programming" (or "Vibe Coding") redefines software engineering, existing code agents remain tethered to static code snapshots. Consequently, they struggle to model the critical information embedded in the temporal evolution of projects, …
  arxiv Yi-Xuan Deng, Xiaoqin Liu, Yi Zhang, Guo-Wei Yang 等 2026-02-25T06:39:29Z 置信度 0.78 cs.LGcs.AIcs.SE
• Lang-PINN: From Language to Physics-Informed Neural Networks via a Multi-Agent Framework
  Physics-informed neural networks (PINNs) provide a powerful approach for solving partial differential equations (PDEs), but constructing a usable PINN remains labor-intensive and error-prone. Scientists must interpret problems as PDE formulations, design archi…
  arxiv Xin He, Liangliang You, Hongduan Tian, Bo Han 等 2025-10-03T08:20:02Z 置信度 0.78 cs.AIcs.CEcs.LGcs.MA
• DUCTILE: Agentic LLM Orchestration of Engineering Analysis in Product Development Practice
  Engineering analysis automation in product development relies on rigid interfaces between tools, data formats and documented processes. When these interfaces change, as they routinely do as the product evolves in the engineering ecosystem, the automation suppo…
  arxiv Alejandro Pradas-Gomez, Arindam Brahma, Ola Isaksson 2026-03-10T22:00:47Z 置信度 0.78 cs.SEcs.AIcs.HC
• OrchMAS: Orchestrated Reasoning with Multi Collaborative Heterogeneous Scientific Expert Structured Agents
  Multi-agent large language model frameworks are promising for complex multi step reasoning, yet existing systems remain weak for scientific and knowledge intensive domains due to static prompts and agent roles, rigid workflows, and homogeneous model reliance, …
  arxiv Yichao Feng, Haoran Luo, Zhenghong Lin, Yiqun Sun 等 2026-03-03T13:57:43Z 置信度 0.78 cs.AI
• MemFlow: Intent-Driven Memory Orchestration for Small Language Model Agents
  Modern language agents must operate over long-horizon, multi-turn histories, yet deploying such agents with Small Language Models (SLMs) remains fundamentally difficult. Full-context prompting causes context overflow, flat retrieval exposes the model to noisy …
  arxiv Jiayi Chen, Yingcong Li, Guiling Wang 2026-05-05T02:57:44Z 置信度 0.78 cs.MA
• Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections
  Self-evolving LLM agents update their internal state across sessions, often by writing and reusing long-term memory. This design improves performance on long-horizon tasks but creates a security risk: untrusted external content observed during a benign session…
  arxiv Xianglin Yang, Yufei He, Shuo Ji, Bryan Hooi 等 2026-02-17T15:28:24Z 置信度 0.78 cs.CRcs.AI
• DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents
  Recent methods train search agents via reinforcement learning from (question, answer, evidence) tuples without requiring expert trajectories. The tuples serve as the training environment, and whose properties directly shape what search strategies and generaliz…
  arxiv Jiamian Wang, Ruiyi Zhang, Tong Yu, Jing Shi 等 2026-05-27T21:21:42Z 置信度 0.78 cs.CV
• DynAMO:Dynamic Asset Management Orchestration via Topological Multi-Agent Scheduling
  While LLM-powered agents offer end-to-end automation for industrial asset lifecycles, real-world Industry 4.0 deployment is hindered by latency, concurrency instability, and safety risks. We present DynAMO (Dynamic Asset Management Orchestration), a deployment…
  arxiv Kanishk Kushwaha, Vikrant Vinod Bansode, Harsh Vardhan, Dhaval C. Patel 2026-06-14T10:54:24Z 置信度 0.78 cs.SEcs.AI
• Learning the Value Systems of Agents with Preference-based and Inverse Reinforcement Learning
  Agreement Technologies refer to open computer systems in which autonomous software agents interact with one another, typically on behalf of humans, in order to come to mutually acceptable agreements. With the advance of AI systems in recent years, it has becom…
  arxiv Andrés Holgado-Sánchez, Holger Billhardt, Alberto Fernández, Sascha Ossowski 2026-02-04T13:07:15Z 置信度 0.78 cs.CYcs.AIcs.LG
• CPEMH: An Agentic Framework for Prompt-Driven Behavior Evaluation and Assurance in Foundation-Model Systems for Mental Health Screening
  This paper presents CPEMH, an agentic framework designed to evaluate prompt-driven behavior in foundation-model systems operating on transcript-based datasets for mental-health screening. CPEMH serves as an engineering methodology for behavioral assurance in l…
  arxiv Giuliano Lorenzoni, Ivens Portugal, Paulo Alencar, Donald Cowan 2026-05-11T23:52:01Z 置信度 0.78 cs.AI
• Multi-Agent Orchestration for High-Throughput Materials Screening on a Leadership-Class System
  The integration of Artificial Intelligence (AI) with High-Performance Computing (HPC) is transforming scientific workflows from human-directed pipelines into adaptive systems capable of autonomous decision-making. Large language models (LLMs) play a critical r…
  arxiv Thang Duc Pham, Harikrishna Tummalapalli, Fakhrul Hasan Bhuiyan, Álvaro Vázquez Mayagoitia 等 2026-04-09T01:01:11Z 置信度 0.78 cs.AI
• Warmth and competence in human-agent cooperation
  Interaction and cooperation with humans are overarching aspirations of artificial intelligence (AI) research. Recent studies demonstrate that AI agents trained with deep reinforcement learning are capable of collaborating with humans. These studies primarily e…
  arxiv Kevin R. McKee, Xuechunzi Bai, Susan T. Fiske 2022-01-31T18:57:08Z 置信度 0.78 cs.HCcs.CYcs.LG
• AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration
  Language agents have shown strong promise for task automation. Realizing this promise for increasingly complex, long-horizon tasks has driven the rise of a sub-agent-as-tools paradigm for multi-turn task solving. However, existing designs still lack a dynamic …
  arxiv Jianhao Ruan, Zhihao Xu, Yiran Peng, Fashen Ren 等 2026-02-03T17:46:16Z 置信度 0.78 cs.AIcs.CL
• Beyond Context Sharing: A Unified Agent Communication Protocol (ACP) for Secure, Federated, and Autonomous Agent-to-Agent (A2A) Orchestration
  In the artificial intelligence space, as we transition from isolated large language models to autonomous agents capable of complex reasoning and tool use. While foundational architectures and local context management protocols have been established, the challe…
  arxiv Naveen Kumar Krishnan 2026-02-11T17:02:12Z 置信度 0.78 cs.MAcs.AI
• KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph
  In this paper, we aim to improve the reasoning ability of large language models (LLMs) over knowledge graphs (KGs) to answer complex questions. Inspired by existing methods that design the interaction strategy between LLMs and KG, we propose an autonomous LLM-…
  arxiv Jinhao Jiang, Kun Zhou, Wayne Xin Zhao, Yang Song 等 2024-02-17T02:07:49Z 置信度 0.78 cs.CL
• Causal Agent Replay: Counterfactual Attribution for LLM-Agent Failures
  When an LLM agent fails -- issues a refund it should not have, calls the wrong tool, leaks data -- existing tooling answers what happened (observability) or whether it passed (evaluation), but not which step caused the failure. The obvious heuristics are wrong…
  arxiv Jaineet Shah 2026-06-06T17:44:23Z 置信度 0.78 cs.LGcs.AI
• HearthNet: Edge Multi-Agent Orchestration for Smart Homes
  Smart-home users increasingly want to control their homes in natural language rather than assemble rules, dashboards, and API integrations by hand. At the same time, real deployments are brittle: devices fail, integrations break, and recoveries often require m…
  arxiv Zhonghao Zhan, Krinos Li, Yefan Zhang, Hamed Haddadi 2026-03-16T15:29:37Z 置信度 0.78 cs.DCcs.AIcs.CR
• Agentic Data Pipeline Orchestration with Multi-Agent AI
  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-system diagnosis. We propose a policy-b…
  crossref Dharanidhar Vuppu, Mounica Achanta 2026-04-20T20:01:37Z 置信度 0.70
• AROMA: Adaptive Orchestration for Robust and Cost-Efficient Multi-Agent LLM Systems
  Multi-Agent Large Language Model Systems (MAS) confront significant challenges stemming from systemic design flaws, inter-agent misalignments, and prohibitive operational costs. These systems frequently offer only modest performance gains, or even exhibit setb…
  europepmc Tianyu Yin, Jingyi Jia 2026 置信度 0.80
• Skill Orchestration Agent: A Knowledge-Driven Orchestration Framework for Adaptive Manufacturing Control
  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 and executing ad-hoc orchestrations of ski…
  crossref A. Lober, J. Weber, H. Baumgärtel, L. Ollinger 2025-09-23T17:24:07Z 置信度 0.70
• AutoTestX: Dependable Test Generation with Open-Source LLMs via Multi-Agent Orchestration
  crossref YUNGI KIM, Geunseok Yang 2025-11-27T19:38:57Z 置信度 0.70
• Agentic AI in Private Equity: Multi-Agent Orchestration for End-to-End Deal Workflows
  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 separates the engineering reality from the ve…
  crossref Leigh Coney 2026-04-07T17:24:33Z 置信度 0.70
• Multi-Agent Architecture for Enterprise AI Orchestration
  The business AI landscape has experienced a revolutionary shift from reactive aid models to advanced autonomous agentic systems for independent decision-making and goal-directed action.In this article, the architectural underpinnings, orchestration patterns, a…
  crossref 2025-11-18T04:53:08Z 置信度 0.70
• Multi-agent Distributed Decentralized Dynamic Resource Orchestration in 5G Edge-Cloud Networks
  Effective resource orchestration for network slicing is critical for optimizing the performance of diverse applications running on next generation communication networks. This paper presents a novel approach that leverages advancements in multiagent reinforcem…
  crossref Xingqi Wu, Junaid Farooq, Juntao Chen 2024-10-30T12:41:16Z 置信度 0.70
• Agentic AI Orchestration: An Organizational Design Framework A Practitioner Framework for Reliable Multi-Agent Systems
  Agentic AI is moving fast. Organizations are rushing to adopt autonomous workflows before they have a coherent model for how those workflows should actually be governed. The result is a pattern playing out in real time. Agents given broad access and no account…
  crossref Michael Reilly 2026-04-27T11:08:40Z 置信度 0.70
• Autonomous CI/CD Quality Assurance Using LangGraph Multi-Agent Orchestration and Risk-Proportionate HITL Control
  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 frequency and accumulate quality debt. This pap…
  crossref Kavita Jadhav 2026-06-25T06:25:26Z 置信度 0.70
• Real-Time Micro-Fulfillment Orchestration in Omnichannel Retail Using Multi-Agent Reinforcement Learning Framework
  Micro-fulfillment centers (MFCs) have emerged as a response to growing e-commerce demands, yet their integration into omnichannel retail networks creates order routing challenges that traditional optimization struggles to solve efficiently. This paper introduc…
  crossref Sri Harsha Konda 2026-01-13T18:24:02Z 置信度 0.70
• 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
  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, transactional, and reactive in character. The arr…
  crossref Mujtaba Shafique 2026-08-04T12:00:22Z 置信度 0.70
• X-SHIELD: Explainability-by-Design for Self-Healing Orchestration in Multi-Agent Systems
  crossref Davis Joseph, Wiam Belouard, Sara El Kardi, Antoun Yaacoub 2026-05-26T00:27:11Z 置信度 0.70
• RULE-BASED ORCHESTRATION OF AGENT-SOCIETIES
  crossref 2011-06-28T08:18:00Z 置信度 0.70
• An Adaptive Multi-Agent System with Data-Driven Heuristic Orchestration for Solving 1D/2D Bin-Packing Problems
  crossref Sam Guessoum, Chun-Kit Ngan, Rolf Bardeli 2026-05-26T07:21:16Z 置信度 0.70
• Synergetic Adaptive Orchestration and Governance: A Unified Framework for Production-Grade Multi-Agent Systems
  The field of artificial intelligence is transitioning from isolated Large Language Models (LLMs) to agentic collectives, autonomous networked systems essential for missioncritical deployments. This fundamental shift introduces core challenges of orchestration …
  crossref Khushboo Bhatia 2026-04-20T20:01:37Z 置信度 0.70
• Agent composition for 5G management and orchestration
  Virtualized execution environments in 5G network call for a linkage between network management and orchestration. Execution of 3GPP functionalities and management applications in the cloud also presents an opportunity to innovate outside of traditional paradig…
  crossref Vilho Raisanen 2018-01-15T17:46:24Z 置信度 0.70
• Universal Full-Agent Orchestration Architecture  <div> for AI-Native Enterprise Software Transformation </div>
  Traditional enterprise software systems are constrained by rigid modular architectures, with isolated functional units and limited intelligent collaboration capabilities, which have become bottlenecks for AI-driven digital transformation. To address this chall…
  crossref Qiang Fu 2026-03-10T09:59:11Z 置信度 0.70
• Dynamic Multi-Agent Orchestration and Retrieval for Multi-Source Question-Answer Systems using Large Language Models
  crossref Antony Medeiros, Claudio Cavalcante 2025-02-24T12:20:32Z 置信度 0.70
• Agent-in-the-Loop Sales Autonomy: Multi-Agent Orchestration across Flows, Apex, and Data Cloud
  Enterprise sales has always been a coordination problem.Sellers, solution architects, pricing analysts, and legal reviewers negotiate in a narrow time window, each holding partial knowledge about customer intent, product constraints, risk posture, and margin t…
  crossref Pavan Palleti 2025-10-08T11:30:07Z 置信度 0.70
• MARL-IoTP: Heterogeneous Multi-Agent Learning for Perception-Aware Edge Orchestration
  The deployment of perception-intensive applications on IoT devices imposes substantial computational demands at the network edge. A key challenge lies in the interdependence between perception model selection at IoT devices and resource orchestration at edge s…
  crossref Mohammed Hamdan, Mohamed Cheriet, Ahmed Bali, Fares Ghaleb 2026-07-29T13:17:48Z 置信度 0.70
• Agent-Driven Orchestration for RESTful Enterprise APIs
  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, nondeterministic eligibility outcomes, and changing …
  crossref Rajesh Vasa 2026-03-19T09:14:10Z 置信度 0.70
• CLOUD-NATIVE ORCHESTRATION PATTERNS FOR MULTI-AGENT HEALTHCARE LLMS
  Healthcare organizations increasingly deploy multi-agent large language models (LLMs) for clinical triage, diagnostic support, and documentation. However, deployment at scale requires coordination across distributed cloud infrastructure while satisfying HIPAA,…
  crossref Vallikranth Ayyagari 2025-12-09T10:35:04Z 置信度 0.70
• Network Function Orchestration with LLM based Multi-Agent System
  Large Language Models (LLMs) have significantly advanced the field of Natural Language Processing (NLP), enabling breakthroughs in contextual understanding, language generation, and reasoning. LLMs possess an intrinsic ability to act as orchestrators in dynami…
  crossref Johny Gemayel, Ali Mokh 2025-09-22T17:42:25Z 置信度 0.70
• Agent Orchestration for Resource Allocation in Self-Healing Networks
  crossref Priyanka V. Galagali 2026-02-12T05:36:19Z 置信度 0.70
• Autonomous Medallion Orchestration: A Multi-Agent Reinforcement Learning Framework for Financial Ecosystems
  The rapid migration of financial institutions toward hybrid-cloud lakehouse architectures has introduced unprecedented complexity in balancing data consistency, regulatory compliance, and operational expenditure. Traditional database management relies on react…
  crossref Uttama Sanepalli 2026-02-18T09:24:06Z 置信度 0.70
• EWOK: A Flexible Agent-Based Disaster Recovery Orchestration System for Stateful Cloud Services
  crossref Sahil Sabharwal, Akshay Pratinav, Chaitanya Bhatt 2026-07-31T18:14:50Z 置信度 0.70
• Agent-based Architecture for Task Scheduling and Dynamic Orchestration Support
  crossref Sarah Ben Othman, Inès Ajmi, Alain Quilliot 2016-09-24T16:41:25Z 置信度 0.70
• Intelligent Multi-Agent Orchestration Framework for Enterprise Financial Systems
  crossref Swamy Biru 2026-07-10T19:37:04Z 置信度 0.70
• Agent Orchestration Frameworks
  In Chapter 4 , we introduced the agents and the benefits of using agents over straight-up LLMs. Then in the previous chapter, we extended the capabilities of agents to carry out tasks and focusing on the Model Context Protocol (MCP).
  crossref Julian Soh, John Tidwell, Priyanshi Singh 2026-07-30T06:43:24Z 置信度 0.70
• Hierarchical Multi-Agent Orchestration for Automated Dispute Resolution
  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 digitalized, online marketplaces, financial …
  crossref Anvesh Katipelly 2026-03-28T06:37:31Z 置信度 0.70
• ASO Author Reflections: Artificial Intelligence Based Multi-Agent Oncology Care Orchestration.
  europepmc Ko Un Park 2026 置信度 0.80
• Large Scale Agent Mediated Autonomic Service Orchestration in Grid Environment
  The service oriented architecture (SOA) as an IT architecture is gaining acceptance in the manufacturing industry. Services orchestration across enterprises is increasingly becoming a competitive factor for many industrial application domains. The need for aut…
  crossref Peter Leong, Miao Chunyan, Bu-sung Lee 2007-01-10T11:09:47Z 置信度 0.70
• AI Strategy Agent for Airline Logistics: A Multi-Layered, KPI-Governed Architecture for Real-Time Optimization and Ethical Orchestration
  This study presents the design and empirical validation of the AI Strategy Agent for Airline Logistics (AISAL) a multi-role, four-layer architecture (Perception, Cognition, Strategy, Action) that autonomously orchestrates 110 airline logistics Key Performance …
  crossref SeyyedAbdolHojjat MoghadasNian, Hamed Kashian 2026-01-12T08:47:38Z 置信度 0.70
• Multi-Agent Orchestration Protocol for Generative AI Systems
  The growing use of large language models (LLMs) in industry demands new solutions for governance, compliance, and secure coordination across distributed AI agents. Existing agent frameworks lack built-in policy controls and assume a uniform environment, leadin…
  crossref Varsha Shukla, Geoffrey Parker 2026-02-20T21:13:55Z 置信度 0.70
• LLM-Based Multi-Agent Orchestration: A Survey of Frameworks, Communication Protocols, and Emerging Patterns
  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 that remain poorly documented. This surv…
  europepmc Yiwen Zhu, Lihe Liu, Jiaqian Yu, Di Zhang 2026 置信度 0.80
• Multi-Agent Systems for Autonomous Orchestration in AI-Driven Computing Networks
  AI-driven computing networks spanning edge, fog, and cloud demand real-time coordination under volatile workloads, heterogeneous resources, and strict service-level objectives. This paper proposes a multi-agent systems (MAS) architecture for autonomous orchest…
  crossref Chloe Bennett, Adichie Okafor 2025-12-13T06:41:31Z 置信度 0.70
• Bottom-Up Resource Orchestration in Edge Computing: An Agent-Based Modeling Approach
  Edge computing addresses delay-sensitive microservices near applications, supplementing cloud computing. The dynamic nature of resources and workloads in edge clusters challenges traditional machine learning tools for resource prediction and allocation for eac…
  crossref Abdorasoul Ghasemi, Melanie Schranz 2024-10-09T17:45:15Z 置信度 0.70
• A Hierarchical Multi-Agent System for Dynamic Orchestration of Clinical Workflows
  crossref Iris Panaro, Paolo Maresca 2026-06-19T19:38:35Z 置信度 0.70
• Replacing Web Interfaces with Intelligent Multi-Agent REST API Orchestration
  The future of automation lies not only in human interaction with APIs but in AI agents seamlessly orchestrating complex tasks. This paper introduces a novel framework designed to bridge the gap between large language models and existing REST APIs, enabling int…
  crossref Viren Bhosale, Ramanshu Gawande 2025-11-17T18:38:41Z 置信度 0.70
• Multi-Agent Orchestration for Intent-Based Network Operations: Automated Diagnosis and Remediation at Scale
  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 paradigm where specialized artificial intellige…
  crossref Satya Sagar Reddi 2026-03-28T10:50:21Z 置信度 0.70
• Deep Reinforcement Learning for Operational Coastal Emergency Response With AI Agent Orchestration and Human Oversight
  Despite urgent needs for adaptive coastal risk management, operational systems still rely heavily on static triggers and fragmented information that overlook interactions between evolving hazards and response actions. Building on a completed game-like deep rei…
  crossref Marcello Sano, Davide Ferrario, Samuele Casagrande, Sebastiano Vascon 等 2026-03-14T03:19:41Z 置信度 0.70
• Dynamic Agent Orchestration: Empowering Enterprise Automation with LLMs
  In today’s digital era, enterprises face mounting pressure to adopt automation solutions that are both agile and intelligent. Dynamic agent orchestration offers a transformative strategy by leveraging advanced Large Language Models (LLMs) to coordinate network…
  crossref Lakshman Kumar Jamili, Soham Sunil Kulkarni, Er Om Goel 2025-10-05T10:35:27Z 置信度 0.70
• Multi-Agent DQN with Sample-Efficient Updates for Large Inter-Slice Orchestration Problems
  Data-driven network slicing has been recently explored as a major driver for beyond 5G networks. Nevertheless, we are still a long way before such solutions are practically applicable in real problems. Reinforcement learning based solutions, addressing the pro…
  crossref Pavlos Doanis, Thrasyvoulos Spyropoulos 2024-06-21T17:20:54Z 置信度 0.70
• TrustOrch: A Dynamic Trust-Aware Orchestration Framework for Adversarially Robust Multi-Agent Collaboration
  Multi-agent systems (MAS) have emerged as a critical paradigm for distributed problem-solving in complex environments. However, their deployment in mission-critical applications faces significant challenges regarding trust, security, and adversarial robustness…
  europepmc Yi Hu, Jinming Li, Kangning Gao, Zizhao Zhang 等 2025 置信度 0.80
• Agent Orchestration: A New Paradigm for Autonomous and Scalable MarTech Ecosystems
  The paradigm presented in the paper extends the ability to orchestrate an agent in the context of MarTech ecosystem to achieve autonomous, scalable coordination of heterogeneous tools and compositions, including CRM systems, content engines, analytics platform…
  crossref Ashwaray Chaba 2025-07-26T16:37:33Z 置信度 0.70
• MIN-Trust: A Minimum Necessary Information Trust Orchestration Framework for Multi-Agent Collaboration
  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 assignments, and iterative message passing…
  europepmc Jinyu Chen, Feiyang Wang, Tian Guan, Yumeng Ma 等 2026 置信度 0.80
• ClinOrch: A Privacy-preserving, Doctor-configurable Multi-Agent Clinical Intelligence Architecture for Pre-consultation, Physician Support, and Longitudinal Care Orchestration
  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 privacy-preserving and doctor-configurable…
  crossref Sagar Patnaik, Mohammad Akbar Khan, Srikanth Akkineni 2026-08-04T10:26:27Z 置信度 0.70
• GNN-Based Multi-Agent DRL for Energy-Efficient Multi-Domain 6G Resource Orchestration
  The rapid evolution towards 6G networks introduces new challenges in orchestrating services across distributed domains while ensuring sustainability goals, such as energy efficiency. Traditional scaling strategies focus on the number of network function instan…
  crossref Abdelmounaim Bouroudi, Abdelkader Outtagarts, Yassine Hadjadj-Aoul 2026-03-19T20:04:01Z 置信度 0.70