中文
相关论文

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

200 篇论文

The emergence of multi-agent systems powered by large language models (LLMs) has unlocked new frontiers in complex task-solving, enabling diverse agents to integrate unique expertise, collaborate flexibly, and address challenges…

人工智能 · 计算机科学 2025-11-05 Jingbo Wang , Sendong Zhao , Haochun Wang , Yuzheng Fan , Lizhe Zhang , Yan Liu , Ting Liu

Large language model (LLM) applications such as agents and domain-specific reasoning increasingly rely on context adaptation: modifying inputs with instructions, strategies, or evidence, rather than weight updates. Prior approaches improve…

General-purpose agents perform tasks in unfamiliar environments without domain-specific manual customization. Yet no study has systematically measured how agent architecture shapes performance across heterogeneous protocols and diverse…

Deep reinforcement learning has been applied successfully to solve various real-world problems and the number of its applications in the multi-agent settings has been increasing. Multi-agent learning distinctly poses significant challenges…

机器学习 · 计算机科学 2021-02-24 Ngoc Duy Nguyen , Thanh Thi Nguyen , Doug Creighton , Saeid Nahavandi

Computer-use agents that combine GUI interaction with structured API calls via the Model Context Protocol (MCP) show promise for automating software tasks. However, existing approaches lack a principled understanding of how agents should…

人工智能 · 计算机科学 2026-04-14 Tiantian He , Yihang Chen , Keyue Jiang , Ka Yiu Lee , Kaiwen Zhou , Kun Shao , Shuai Wang

The Model Context Protocol (MCP) is rapidly emerging as a pivotal open standard, designed to enhance agent-tool integration and interoperability, and is positioned to unlock a new era of powerful, interconnected, and genuinely utilitarian…

计算与语言 · 计算机科学 2025-09-15 Zikang Guo , Benfeng Xu , Chiwei Zhu , Wentao Hong , Xiaorui Wang , Zhendong Mao

Graph-based Multi-Agent Systems (MAS) enable complex cyclic workflows but suffer from inefficient static model allocation, where deploying strong models uniformly wastes computation on trivial sub-tasks. We propose CASTER (Context-Aware…

人工智能 · 计算机科学 2026-01-28 Shanyv Liu , Xuyang Yuan , Tao Chen , Zijun Zhan , Zhu Han , Danyang Zheng , Weishan Zhang , Shaohua Cao

Since the introduction of the Model Context Protocol (MCP), the number of available tools for Large Language Models (LLMs) has increased significantly. These task-specific tool sets offer an alternative to general-purpose tools such as web…

计算与语言 · 计算机科学 2025-12-12 Reza Esfandiarpoor , Vishwas Suryanarayanan , Stephen H. Bach , Vishal Chowdhary , Anthony Aue

Predicting the future behavior of agents is a fundamental task in autonomous vehicle domains. Accurate prediction relies on comprehending the surrounding map, which significantly regularizes agent behaviors. However, existing methods have…

计算机视觉与模式识别 · 计算机科学 2024-01-19 Chen Feng , Hangning Zhou , Huadong Lin , Zhigang Zhang , Ziyao Xu , Chi Zhang , Boyu Zhou , Shaojie Shen

Large language model (LLM)-powered agents are increasingly used to plan and execute scientific workflows, yet most research cyberinfrastructure (CI) exposes heterogeneous APIs and implements security models that present barriers for use by…

Communication is a critical factor for the big multi-agent world to stay organized and productive. Typically, most previous multi-agent "learning-to-communicate" studies try to predefine the communication protocols or use technologies such…

人工智能 · 计算机科学 2017-10-31 Hangyu Mao , Zhibo Gong , Yan Ni , Zhen Xiao

With the development of large models and autonomous decision-making AI, agents are rapidly becoming the new entities of the internet, following mobile apps. However, existing internet infrastructure is primarily designed for human…

网络与互联网体系结构 · 计算机科学 2025-08-04 Gaowei Chang , Eidan Lin , Chengxuan Yuan , Rizhao Cai , Binbin Chen , Xuan Xie , Yin Zhang

AI agents have become increasingly adept at complex tasks such as coding, reasoning, and multimodal understanding. However, building generalist systems requires moving beyond individual agents to collective inference -- a paradigm where…

The vision of autonomous systems is becoming increasingly important in many application areas, where the aim is to replace humans with agents. These include autonomous vehicles and other agents' applications in business processes and…

网络与互联网体系结构 · 计算机科学 2025-03-20 Joseph Sifakis , Dongming Li , Hairong Huang , Yong Zhang , Wenshuan Dang , River Huang , Yijun Yu

Since their inception, Multi Agent Systems (MASs) have been championed as a solution for the increasing problem of software complexity. Communities of distributed autonomous computing entities that are capable of collaborating, negotiating…

多智能体系统 · 计算机科学 2017-11-08 David J. Lillis

Trajectory prediction in urban mixed-traffic zones (a.k.a. shared spaces) is critical for many intelligent transportation systems, such as intent detection for autonomous driving. However, there are many challenges to predict the…

计算机视觉与模式识别 · 计算机科学 2020-06-24 Hao Cheng , Wentong Liao , Michael Ying Yang , Monika Sester , Bodo Rosenhahn

Digital agents capable of automating complex computer tasks have attracted considerable attention due to their immense potential to enhance human-computer interaction. However, existing agent methods exhibit deficiencies in their…

人工智能 · 计算机科学 2024-10-25 Chengyou Jia , Minnan Luo , Zhuohang Dang , Qiushi Sun , Fangzhi Xu , Junlin Hu , Tianbao Xie , Zhiyong Wu

This paper provides an in-depth technical analysis and implementation methodology of the open-source Agent-to-Agent (A2A) protocol developed by Google and the Model Context Protocol (MCP) introduced by Anthropic. While the evolution of…

人工智能 · 计算机科学 2025-10-03 Cheonsu Jeong

The rapid advancement of large language models (LLMs) has enabled the development of multi-agent systems where multiple LLM-based agents collaborate on complex tasks. However, existing systems often rely on centralized coordination, leading…

多智能体系统 · 计算机科学 2025-06-02 Yingxuan Yang , Huacan Chai , Shuai Shao , Yuanyi Song , Siyuan Qi , Renting Rui , Weinan Zhang

This work presents a novel communication framework for decentralized multi-agent systems operating in dynamic network environments. Integrated into a multi-agent reinforcement learning system, the framework is designed to enhance…

多智能体系统 · 计算机科学 2025-01-03 Ben McClusky