Tool Learning

ToLeaP: Rethinking Development of Tool Learning with Large Language Models

Submitted to ACL 2026. First author. Unified evaluation platform for tool-learning agents.

avatar
Haotian Chen

ToLeaP: Rethinking Development of Tool Learning with Large Language Models

Submitted to ACL 2026. First author. Unified evaluation platform for tool-learning agents.

avatar
Haotian Chen
ToLeaP featured image

ToLeaP

📏 **项目负责人** · 工具学习智能体一键评测平台 [![Stars](https://img.shields.io/github/stars/thunlp/ToLeaP?style=social)](https://github.com/thunlp/ToLeaP) · `50+ 基准` · `33 数据集`

ToLeaP featured image

ToLeaP

📏 **Project Lead** · One-click evaluation platform for tool-learning agents …

Reflective Reinforcement Tool Learning

Submitted to ACL 2026. Reflective reinforcement learning for tool learning.

avatar
Haotian Chen

Reflective Reinforcement Tool Learning

Submitted to ACL 2026. Reflective reinforcement learning for tool learning.

avatar
Haotian Chen
MiniCPM4-MCP featured image

MiniCPM4-MCP

🏆 **项目负责人** · 端侧(8B)智能体大模型,精通 MCP 工具 [![Stars](https://img.shields.io/github/stars/OpenBMB/MiniCPM?style=social)](https://github.com/OpenBMB/MiniCPM) · `5,500+ 下载量`

MiniCPM4-MCP featured image

MiniCPM4-MCP

🏆 **Project Lead** · Edge-scale (8B) agent LLM mastering MCP tools [![Stars](https://img.shields.io/github/stars/OpenBMB/MiniCPM?style=social)](https://github.com/OpenBMB/MiniCPM) …

MiniCPM4: Ultra-Efficient LLMs on End Devices featured image

MiniCPM4: Ultra-Efficient LLMs on End Devices

ArXiv 2025. Team contribution (led MCP agent capabilities). 8,300+ GitHub Stars.

minicpm-team
MiniCPM4: Ultra-Efficient LLMs on End Devices featured image

MiniCPM4: Ultra-Efficient LLMs on End Devices

ArXiv 2025. Team contribution (led MCP agent capabilities). 8,300+ GitHub Stars.

minicpm-team