English
Related papers

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

200 papers

Large language models (LLMs) show remarkable potential to act as computer agents, enhancing human productivity and software accessibility in multi-modal tasks that require planning and reasoning. However, measuring agent performance in…

Reusable skills have become a core substrate for improving agent capabilities, yet most existing skill packages encode reusable behavior primarily as textual prompts, executable code, or learned routines. For visual agents, however,…

Artificial Intelligence · Computer Science 2026-05-15 Kangning Zhang , Shuai Shao , Qingyao Li , Jianghao Lin , Lingyue Fu , Shijian Wang , Wenxiang Jiao , Yuan Lu , Weiwen Liu , Weinan Zhang , Yong Yu

Autonomous embodied agents live on an Internet of multimedia websites. Can they hop around multimodal websites to complete complex user tasks? Existing benchmarks fail to assess them in a realistic, evolving environment for their embodiment…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Shulin Tian , Ziniu Zhang , Liangyu Chen , Ziwei Liu

To reduce development overhead and enable seamless integration between potential components comprising any given generative AI application, the Model Context Protocol (MCP) (Anthropic, 2024) has recently been released and subsequently…

Cryptography and Security · Computer Science 2025-04-14 Brandon Radosevich , John Halloran

Multimodal large language models (MLLMs) have made significant progress in mobile agent development, yet their capabilities are predominantly confined to a reactive paradigm, where they merely execute explicit user commands. The emerging…

As multimodal large language models (MLLMs) advance, MLLM-based virtual agents have demonstrated remarkable performance. However, existing benchmarks face significant limitations, including uncontrollable task complexity, extensive manual…

Computer Vision and Pattern Recognition · Computer Science 2025-06-11 Wendong Bu , Yang Wu , Qifan Yu , Minghe Gao , Bingchen Miao , Zhenkui Zhang , Kaihang Pan , Yunfei Li , Mengze Li , Wei Ji , Juncheng Li , Siliang Tang , Yueting Zhuang

Graphical User Interface (GUI) automation holds significant promise for assisting users with complex tasks, thereby boosting human productivity. Existing works leveraging Large Language Model (LLM) or LLM-based AI agents have shown…

Computer Vision and Pattern Recognition · Computer Science 2024-01-02 Difei Gao , Lei Ji , Zechen Bai , Mingyu Ouyang , Peiran Li , Dongxing Mao , Qinchen Wu , Weichen Zhang , Peiyi Wang , Xiangwu Guo , Hengxu Wang , Luowei Zhou , Mike Zheng Shou

Medical calculators are fundamental to quantitative, evidence-based clinical practice. However, their real-world use is an adaptive, multi-stage process, requiring proactive EHR data acquisition, scenario-dependent calculator selection, and…

Artificial Intelligence · Computer Science 2026-02-02 Yakun Zhu , Yutong Huang , Shengqian Qin , Zhongzhen Huang , Shaoting Zhang , Xiaofan Zhang

The rapid rise of Large Language Models (LLMs)-based intelligent agents underscores the need for robust, scalable evaluation frameworks. Existing methods rely on static benchmarks and labor-intensive data collection, limiting practical…

Artificial Intelligence · Computer Science 2025-08-05 Zhiwei Liu , Jielin Qiu , Shiyu Wang , Jianguo Zhang , Zuxin Liu , Roshan Ram , Haolin Chen , Weiran Yao , Shelby Heinecke , Silvio Savarese , Huan Wang , Caiming Xiong

Recent agentic-robotics systems, from Code-asPolicies to modern vision-language-action (VLA) foundation models, presuppose that drivers, SDKs, or ROS-style primitives for the target hardware already exist. Writing those primitives is the…

Robotics · Computer Science 2026-05-12 Quilee Simeon , Justin M. Wei , Yile Fan

Agent tools are becoming a core interface through which LLM agents access external data, services, and execution environments. As these tools are distributed through public marketplaces, raw tool counts may substantially overstate ecosystem…

Software Engineering · Computer Science 2026-05-19 Taein Kim , David Jiang , Yuepeng Hu , Yuqi Jia , Neil Gong

We introduce ETOM, a five-level benchmark for evaluating multi-hop, end-to-end tool orchestration by LLM agents within a hierarchical Model-Context Protocol (MCP) ecosystem. Existing benchmarks often assess tools in isolation, overlooking…

Artificial Intelligence · Computer Science 2026-01-21 Jia-Kai Dong , I-Wei Huang , Chun-Tin Wu , Yi-Tien Tsai

Recent progress in Multimodal Large Language Models (MLLMs) has enabled mobile GUI agents capable of visual perception, cross-modal reasoning, and interactive control. However, existing benchmarks are largely English-centric and fail to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Yang Li , Yuchen Liu , Haoyu Lu , Zhiqiang Xia , Hongzhen Wang , Kaiyang Han , Changpeng Yang , Jinyang Wu , Jiaming Xu , Runyu Shi , Ying Huang

Large language models (LLMs) can now access a wide range of external tools, thanks to the Model Context Protocol (MCP). This greatly expands their abilities as various agents. However, LLMs rely entirely on the text descriptions of tools to…

Artificial Intelligence · Computer Science 2025-09-23 Kazem Faghih , Wenxiao Wang , Yize Cheng , Siddhant Bharti , Gaurang Sriramanan , Sriram Balasubramanian , Parsa Hosseini , Soheil Feizi

Computer Use Agents (CUAs) can act through both atomic GUI actions, such as click and type, and high-level tool calls, such as API-based file operations, but this hybrid action space often leaves them uncertain about when to continue with…

Artificial Intelligence · Computer Science 2026-05-13 Xuhao Hu , Xi Zhang , Haiyang Xu , Kyle Qiao , Jingyi Yang , Xuanjing Huang , Jing Shao , Ming Yan , Jieping Ye

Towards an embodied generalist for real-world interaction, Multimodal Large Language Model (MLLM) agents still suffer from challenging latency, sparse feedback, and irreversible mistakes. Video games offer an ideal testbed with rich visual…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Mingyu Ouyang , Siyuan Hu , Kevin Qinghong Lin , Hwee Tou Ng , Mike Zheng Shou

The Model Context Protocol (MCP) is emerging as a common interface connecting large language models (LLMs) with external services. Remote deployments are becoming increasingly important as agents connect to user-linked online services, such…

Cryptography and Security · Computer Science 2026-05-22 Huijun Zhou , Xiaohan Zhang , Haozhe Zhang , Haoyang Zhang , Mi Zhang , Min Yang

General-purpose computer-use agents have shown impressive performance across diverse digital environments. However, our new benchmark, OSExpert-Eval, indicates they remain far less helpful than human experts. Although inference-time scaling…

Artificial Intelligence · Computer Science 2026-03-10 Jiateng Liu , Zhenhailong Wang , Rushi Wang , Bingxuan Li , Jeonghwan Kim , Aditi Tiwari , Pengfei Yu , Denghui Zhang , Heng Ji

Large language model agents that interact with PC applications often face limitations due to their singular mode of interaction with real-world environments, leading to restricted versatility and frequent hallucinations. To address this, we…

Artificial Intelligence · Computer Science 2025-03-25 Zirui Song , Yaohang Li , Meng Fang , Yanda Li , Zhenhao Chen , Zecheng Shi , Yuan Huang , Xiuying Chen , Ling Chen

The Model Context Protocol (MCP) has emerged as a widely adopted mechanism for connecting large language models to external tools and resources. While MCP promises seamless extensibility and rich integrations, it also introduces a…

Cryptography and Security · Computer Science 2025-07-10 Zhihao Li , Kun Li , Boyang Ma , Minghui Xu , Yue Zhang , Xiuzhen Cheng
‹ Prev 1 3 4 5 6 7 10 Next ›