English
Related papers

Related papers: OSWorld-MCP: Benchmarking MCP Tool Invocation In C…

200 papers

We present M^3-Bench, the first benchmark for evaluating multimodal tool use under the Model Context Protocol. The benchmark targets realistic, multi-hop and multi-threaded workflows that require visual grounding and textual reasoning,…

Artificial Intelligence · Computer Science 2026-02-05 Yang Zhou , Mingyu Zhao , Zhenting Wang , Difei Gu , Bangwei Guo , Ruosong Ye , Ligong Han , Can Jin , Dimitris N. Metaxas

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…

Artificial Intelligence · Computer Science 2026-04-14 Tiantian He , Yihang Chen , Keyue Jiang , Ka Yiu Lee , Kaiwen Zhou , Kun Shao , Shuai Wang

The Model Context Protocol (MCP) standardizes how large language model (LLM) agents discover, describe, and call external tools. While MCP unlocks broad interoperability, it also enlarges the attack surface by making tools first-class,…

Cryptography and Security · Computer Science 2026-03-25 Dongsen Zhang , Zekun Li , Xu Luo , Xuannan Liu , Peipei Li , Wenjun Xu

Recent advancements in Large Language Models (LLMs) and the introduction of the Model Context Protocol (MCP) have significantly expanded LLM agents' capability to interact dynamically with external tools and APIs. However, existing tool…

Computation and Language · Computer Science 2025-05-13 Elias Lumer , Anmol Gulati , Vamse Kumar Subbiah , Pradeep Honaganahalli Basavaraju , James A. Burke

As AI agents increasingly operate in open, real-world environments, they require a deep synergy of multimodal perception, tool invocation with multi-hop reasoning, and dynamic interaction with users. However, existing benchmarks fail to…

Artificial Intelligence · Computer Science 2026-05-28 Yunqi Liu , Tong Niu , Zitong Wang , Zhenlong Dai , Yuqi Qing , Weiqiang Wang , Jian Liu

Graphical User Interface (GUI) agents show promising capabilities for automating computer-use tasks and facilitating accessibility, but existing interactive benchmarks are mostly English-only, covering web-use or Windows, Linux, and Android…

Artificial Intelligence · Computer Science 2025-10-21 Pei Yang , Hai Ci , Mike Zheng Shou

AI agents with advanced reasoning and tool use capabilities have demonstrated impressive performance in web browsing for deep search. While existing benchmarks such as BrowseComp evaluate these browsing abilities, they primarily focus on…

The AI agent ecosystem has converged on two protocols: the Model Context Protocol (MCP) for tool invocation and Agent-to-Agent (A2A) for single-principal task delegation. Both assume a single controlling principal, meaning one person or…

Multiagent Systems · Computer Science 2026-04-14 Kaiyang Qian , Xinmin Fang , Zhengxiong Li

The Model Context Protocol has emerged as a transformative standard for connecting large language models to external data sources and tools, rapidly gaining adoption across major AI providers and development platforms. However, existing…

Artificial Intelligence · Computer Science 2025-08-21 Ziyang Luo , Zhiqi Shen , Wenzhuo Yang , Zirui Zhao , Prathyusha Jwalapuram , Amrita Saha , Doyen Sahoo , Silvio Savarese , Caiming Xiong , Junnan Li

The Model Context Protocol (MCP) standardizes tool use for LLM-based agents and enable third-party servers. This openness introduces a security misalignment: agents implicitly trust tools exposed by potentially untrusted MCP servers.…

Cryptography and Security · Computer Science 2026-02-25 Zhenhong Zhou , Yuanhe Zhang , Hongwei Cai , Moayad Aloqaily , Ouns Bouachir , Linsey Pang , Prakhar Mehrotra , Kun Wang , Qingsong Wen

Today's AI agents are built on large language models (LLMs) equipped with tools to access and modify external environments, such as corporate file systems, API-accessible platforms and websites. AI agents offer the promise of automating…

Computers and Society · Computer Science 2026-03-26 Merlin Stein

Large Language Models (LLMs) increasingly rely on external tools to perform complex, realistic tasks, yet their ability to utilize the rapidly expanding Model Contextual Protocol (MCP) ecosystem remains limited. Existing MCP research covers…

Artificial Intelligence · Computer Science 2026-04-17 Wenhao Wang , Peizhi Niu , Zhao Xu , Zhaoyu Chen , Jian Du , Yaxin Du , Xianghe Pang , Keduan Huang , Yanfeng Wang , Qiang Yan , Siheng Chen

Large Language Models (LLMs) are evolving from text generators into reasoning agents. This transition makes their ability to use external tools a critical capability. However, evaluating this skill presents a significant challenge. Existing…

Computation and Language · Computer Science 2025-10-14 Fei Lei , Yibo Yang , Wenxiu Sun , Dahua Lin

Human-AI collaboration faces growing challenges as AI systems increasingly outperform humans on complex tasks, while humans remain responsible for orchestration, validation, and decision oversight. To address this imbalance, we introduce…

Human-Computer Interaction · Computer Science 2026-02-16 Yuanrong Tang , Huiling Peng , Bingxi Zhao , Hengyang Ding , Hanchao Song , Tianhong Wang , Chen Zhong , Jiangtao Gong

This paper introduces \textbf{FinMCP-Bench}, a novel benchmark for evaluating large language models (LLMs) in solving real-world financial problems through tool invocation of financial model context protocols. FinMCP-Bench contains 613…

Artificial Intelligence · Computer Science 2026-03-27 Jie Zhu , Yimin Tian , Boyang Li , Kehao Wu , Zhongzhi Liang , Junhui Li , Xianyin Zhang , Lifan Guo , Feng Chen , Yong Liu , Chi Zhang

Effective multi-agent systems cannot be designed by selecting prompts or communication graphs in isolation. Agent behavior depends on the information an agent receives, while the usefulness of a communication edge depends on how the…

Artificial Intelligence · Computer Science 2026-05-28 Yi Ding , Zijie Xuan , Haowei Zhou , Zhenyu Ju , Xiaoxiao Dong , Jingwen Zhang , Xingyu Zhu , Leixin Sun , Haochi Zhang

The rapid expansion of the model context protocol (MCP) ecosystem enables large language model (LLM)-based agents to access a wide range of external tools via a standardized interface. However, identifying appropriate MCP servers for a…

Software Engineering · Computer Science 2026-04-21 Shiyu He , Zhiman Chen , Yuqi Zhao , Neng Zhang , Ran Mo , Yutao Ma

Model Context Protocol (MCP) servers contain a collection of thousands of open-source standardized tools, linking LLMs to external systems; however, existing datasets and benchmarks lack realistic, human-like user queries, remaining a…

Artificial Intelligence · Computer Science 2026-03-02 Shubh Laddha , Lucas Changbencharoen , Win Kuptivej , Surya Shringla , Archana Vaidheeswaran , Yash Bhaskar

The Model Context Protocol (MCP) enables large language models (LLMs) to access external resources on demand. While commonly assumed to enhance performance, how LLMs actually leverage this capability remains poorly understood. We introduce…

Artificial Intelligence · Computer Science 2025-08-19 Wei Song , Haonan Zhong , Ziqi Ding , Jingling Xue , Yuekang Li

Model Context Protocol (MCP) is increasingly adopted for tool-integrated LLM agents, but its multi-layer design and third-party server ecosystem expand risks across tool metadata, untrusted outputs, cross-tool flows, multimodal inputs, and…

Cryptography and Security · Computer Science 2026-04-24 Run Hao , Zhuoran Tan