English
Related papers

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

200 papers

Autonomous agents that accomplish complex computer tasks with minimal human interventions have the potential to transform human-computer interaction, significantly enhancing accessibility and productivity. However, existing benchmarks…

The Model Context Protocol (MCP) is emerging as a standard interface through which large language model (LLM) agents discover and invoke external tools. However, existing MCP evaluations fall short along three key axes: realistic multi-step…

Tool calling has emerged as a critical capability for AI agents. In contrast to conventional tool calling frameworks that rely on static, provider-specific tool definitions, the Model Context Protocol (MCP) offers a unified interface to…

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…

Computation and Language · Computer Science 2025-09-15 Zikang Guo , Benfeng Xu , Chiwei Zhu , Wentao Hong , Xiaorui Wang , Zhendong Mao

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…

Computation and Language · Computer Science 2025-12-12 Reza Esfandiarpoor , Vishwas Suryanarayanan , Stephen H. Bach , Vishal Chowdhary , Anthony Aue

Model Context Protocol (MCP) has become a key infrastructure for connecting LLMs with external tools, scaling to 10,000+ MCP servers with diverse tools. Unfortunately, there is still a large gap between real-world MCP usage and current…

Artificial Intelligence · Computer Science 2026-02-27 Guozhao Mo , Wenliang Zhong , Jiawei Chen , Qianhao Yuan , Xuanang Chen , Yaojie Lu , Hongyu Lin , Ben He , Xianpei Han , Le Sun

LLMs' capabilities are enhanced by using function calls to integrate various data sources or API results into the context window. Typical tools include search, web crawlers, maps, financial data, file systems, and browser usage, etc.…

Artificial Intelligence · Computer Science 2025-08-12 Shiqing Fan , Xichen Ding , Liang Zhang , Linjian Mo

MCP standardizes how LLMs interact with external systems, forming the foundation for general agents. However, existing MCP benchmarks remain narrow in scope: they focus on read-heavy tasks or tasks with limited interaction depth, and fail…

We introduce MCP-Bench, a benchmark for evaluating large language models (LLMs) on realistic, multi-step tasks that demand tool use, cross-tool coordination, precise parameter control, and planning/reasoning for solving tasks. Built on the…

Computation and Language · Computer Science 2025-08-29 Zhenting Wang , Qi Chang , Hemani Patel , Shashank Biju , Cheng-En Wu , Quan Liu , Aolin Ding , Alireza Rezazadeh , Ankit Shah , Yujia Bao , Eugene Siow

Large Language Models (LLMs) are increasingly serving as autonomous agents, and their utilization of external tools via the Model Context Protocol (MCP) is considered a future trend. Current MCP evaluation sets suffer from issues such as…

Artificial Intelligence · Computer Science 2026-01-22 Wenrui Liu , Zixiang Liu , Elsie Dai , Wenhan Yu , Lei Yu , Tong Yang , Jinjun Han , Hong Gao

The Model Context Protocol (MCP) enables large language models to invoke external tools through natural-language descriptions, forming the foundation of many AI agent applications. However, MCP does not enforce consistency between…

Cryptography and Security · Computer Science 2026-02-04 Zhihao Li , Boyang Ma , Xuelong Dai , Minghui Xu , Yue Zhang , Biwei Yan , Kun Li

Tool-using agents are increasingly expected to operate across realistic professional workflows, where they must interpret multimodal inputs, coordinate external tools, inspect intermediate artifacts, and revise their actions before…

Artificial Intelligence · Computer Science 2026-05-19 Zhiqiang Liu , Wenhui Dong , Yilang Tan , Yuwen Qu , Haochen Yin , Chenyang Si

As Large Language Models (LLMs) evolve from passive text generators to active reasoning agents capable of interacting with external tools, the Model Context Protocol (MCP) has emerged as a key standardized framework for dynamic tool…

Artificial Intelligence · Computer Science 2025-10-14 Xuanqi Gao , Siyi Xie , Juan Zhai , Shiqing Ma , Chao Shen

Current LLM agents are proficient at calling isolated APIs but struggle with the "last mile" of commercial software automation. In real-world scenarios, tools are not independent; they are atomic, interdependent, and prone to environmental…

Artificial Intelligence · Computer Science 2026-05-21 Yuanyang Li , Xue Yang , Longyue Wang , Weihua Luo , Hongyang Chen

(M)LLM-powered computer use agents (CUA) are emerging as a transformative technique to automate human-computer interaction. However, existing CUA benchmarks predominantly target GUI agents, whose evaluation methods are susceptible to UI…

Generative AI is being leveraged to solve a variety of computer-use tasks involving desktop applications. State-of-the-art systems have focused solely on improving accuracy on leading benchmarks. However, these systems are practically…

Artificial Intelligence · Computer Science 2026-05-19 Reyna Abhyankar , Qi Qi , Yiying Zhang

While GUI agents have shown impressive capabilities in common computer-use tasks such as OSWorld, current benchmarks mainly focus on isolated and single-application tasks. This overlooks a critical real-world requirement of coordinating…

Artificial Intelligence · Computer Science 2026-05-01 Jinchao Li , Yunxin Li , Chenrui Zhao , Zhenran Xu , Baotian Hu , Min Zhang

The Model Context Protocol (MCP) introduces a standard specification that defines how Foundation Model (FM)-based agents should interact with external systems by invoking tools. However, to understand a tool's purpose and features, FMs rely…

Software Engineering · Computer Science 2026-02-24 Mohammed Mehedi Hasan , Hao Li , Gopi Krishnan Rajbahadur , Bram Adams , Ahmed E. Hassan

Computer-using agents have shown strong potential to boost human productivity and enable new application forms across platforms. While recent advances have led to usable applications, existing benchmarks fail to account for the internal…

Among existing online mobile-use benchmarks, AndroidWorld has emerged as the dominant benchmark due to its reproducible environment and deterministic evaluation; however, recent agents achieving over 90% success rates indicate its…

Computation and Language · Computer Science 2026-01-01 Quyu Kong , Xu Zhang , Zhenyu Yang , Nolan Gao , Chen Liu , Panrong Tong , Chenglin Cai , Hanzhang Zhou , Jianan Zhang , Liangyu Chen , Zhidan Liu , Steven Hoi , Yue Wang
‹ Prev 1 2 3 10 Next ›