Wentao Hong — accepted AI-conference papers

2026

MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools

Zikang Guo, Benfeng Xu, Chiwei Zhu, Wentao Hong, Xiaorui Wang, Zhendong Mao

AAAI 2026technical

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 agentic AI. However, despite MCP

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

AgentRefine: Enhancing Agent Generalization through Refinement Tuning

Dayuan Fu, Keqing He, Yejie Wang, Wentao Hong, Zhuoma GongQue, Weihao Zeng +4

ICLR 2025poster

Large Language Model (LLM) based agents have proved their ability to perform complex tasks like humans. However, there is still a large gap between open-sourced LLMs and commercial models like the GPT series. In this paper, we focus on improving the agent generalization capabilities of LLMs via inst…

Cited by 5 Source ↗PDF ↗Scholar ↗