中文
相关论文

相关论文: ACE-Router: Generalizing History-Aware Routing fro…

200 篇论文

Large language models (LLMs) are rapidly evolving from passive engines of text generation into agentic entities that can plan, remember, invoke external tools, and co-operate with one another. This perspective paper investigates how such…

信息检索 · 计算机科学 2025-07-11 Reza Yousefi Maragheh , Yashar Deldjoo

Multi-Agent Policy Gradient (MAPG) has made significant progress in recent years. However, centralized critics in state-of-the-art MAPG methods still face the centralized-decentralized mismatch (CDM) issue, which means sub-optimal actions…

多智能体系统 · 计算机科学 2024-01-17 Xingzhou Lou , Junge Zhang , Timothy J. Norman , Kaiqi Huang , Yali Du

This paper proposes a new architecture for multi-agent systems to cover an unknowingly distributed fast, safely, and decentralizedly. The inter-agent communication is organized by a directed graph with fixed topology, and we model agent…

系统与控制 · 电气工程与系统科学 2023-07-11 Hossein Rastgoftar

Future wireless networks are moving toward autonomous service operation, where network control and resource management need to respond to time-varying radio conditions and evolving service objectives. To address this shift, this article…

信号处理 · 电气工程与系统科学 2026-05-18 Yuanwei Liu , Xu Gan , Zhaolin Wang , Shan Shan , Zongyao Zhao , Zhiguo Ding

Active traffic management with autonomous vehicles offers the potential for reduced congestion and improved traffic flow. However, developing effective algorithms for real-world scenarios requires overcoming challenges related to…

机器学习 · 计算机科学 2024-09-04 Shengchao Yan , Lukas König , Wolfram Burgard

Autonomous agents represent an inevitable evolution of the internet. Current agent frameworks do not embed a standard protocol for agent-to-agent interaction, leaving existing agents isolated from their peers. As intellectual property is…

人工智能 · 计算机科学 2025-01-14 Andrea Muttoni , Jason Zhao

The paradigm of agentic AI is shifting from engineered complex workflows to post-training native models. However, existing agents are typically confined to static, predefined action spaces--such as exclusively using APIs, GUI events, or…

机器学习 · 计算机科学 2025-12-11 Kaichen He , Zihao Wang , Muyao Li , Anji Liu , Yitao Liang

Contemporary large language model (LLM)-based multi-agent systems exhibit systematic advantages in deep research tasks, which emphasize iterative, vertically structured information seeking. However, when confronted with wide search tasks…

多智能体系统 · 计算机科学 2026-02-03 Mingju Chen , Guibin Zhang , Heng Chang , Yuchen Guo , Shiji Zhou

The Agent Conversation Reasoning Engine (ACRE) is intended to aid agent developers to improve the management and reliability of agent communication. To evaluate its effectiveness, a problem scenario was created that could be used to compare…

多智能体系统 · 计算机科学 2014-10-13 David Lillis , Rem W. Collier , Howell R. Jordan

In this work, we propose a novel memory-based multi-agent meta-learning architecture and learning procedure that allows for learning of a shared communication policy that enables the emergence of rapid adaptation to new and unseen…

Packet routing is a fundamental problem in communication networks that decides how the packets are directed from their source nodes to their destination nodes through some intermediate nodes. With the increasing complexity of network…

人工智能 · 计算机科学 2021-07-29 Xuan Mai , Quanzhi Fu , Yi Chen

In artificial multi-agent systems, the ability to learn collaborative policies is predicated upon the agents' communication skills: they must be able to encode the information received from the environment and learn how to share it with…

机器学习 · 计算机科学 2023-01-23 Emanuele Pesce , Giovanni Montana

Recent advances in Large Language Model Multi-Agent Systems enable scalable orchestration and retrieval of specialized, parallelized subagents, each equipped with hundreds or thousands of Model Context Protocol (MCP) servers and tools.…

计算与语言 · 计算机科学 2025-11-25 Faheem Nizar , Elias Lumer , Anmol Gulati , Pradeep Honaganahalli Basavaraju , Vamse Kumar Subbiah

AI agents -- powered by reasoning-capable large language models (LLMs) and integrated with tools, data, and web search -- are poised to transform the internet into a \emph{Web of Agents}: a machine-native ecosystem where autonomous agents…

人工智能 · 计算机科学 2025-09-08 Rajesh Tembarai Krishnamachari , Srividya Rajesh

Cloud computing is a model for enabling on-demand network access to a shared pool of computing resources, that can be dynamically allocated and released with minimal effort. However, this task can be complex in highly dynamic environments…

分布式、并行与集群计算 · 计算机科学 2018-10-18 Merzoug Soltane , Yudith Cardinale , Rafael Angarita , Philippe Rosse , Marta Rukoz , Derdour Makhlouf , Kazar Okba

The upcoming generation of mobile telecommunication systems is expected to support new use cases, where the mobile network serves one or more IP subnetworks located behind the User Equipment (UEs). This would create new challenges for the…

网络与互联网体系结构 · 计算机科学 2025-03-12 Hamed Hellaoui , Matti Laitila , Markus Isomäki , Hua Chao

Congestion Control (CC), as the core networking task to efficiently utilize network capacity, received great attention and widely used in various Internet communication applications such as 5G, Internet-of-Things, UAN, and more. Various CC…

网络与互联网体系结构 · 计算机科学 2022-06-07 Jianing Bai , Tianhao Zhang , Guangming Xie

This work proposes a neural network architecture that learns policies for multiple agent classes in a heterogeneous multi-agent reinforcement setting. The proposed network uses directed labeled graph representations for states, encodes…

人工智能 · 计算机科学 2020-10-22 Douglas De Rizzo Meneghetti , Reinaldo Augusto da Costa Bianchi

Autonomous agent frameworks still struggle to reconcile long-term experiential learning with real-time, context-sensitive decision-making. In practice, this gap appears as static cognition, rigid workflow dependence, and inefficient context…

人工智能 · 计算机科学 2026-03-11 Xiaoxing Wang , Ning Liao , Shikun Wei , Chen Tang , Feiyu Xiong

Mixture-of-Agents (MoA) inference can suffer from dense inter-agent communication and low hardware utilization, which jointly inflate serving latency. We present a serving design that targets these bottlenecks through an algorithm-system…

人工智能 · 计算机科学 2025-12-23 Zijun Wang , Yijiahao Qi , Hanqiu Chen , Zishen Wan , Gongjin Sun , Dongyang Li , Shuyi Pei , Cong Hao