ToLeaP: Rethinking Development of Tool Learning with Large Language Models
Submitted to ACL 2026. First author. Unified evaluation platform for tool-learning agents.
Submitted to ACL 2026. First author. Unified evaluation platform for tool-learning agents.
Submitted to ACL 2026. Reflective reinforcement learning for tool learning.
🏆 **项目负责人** · 端侧(8B)智能体大模型,精通 MCP 工具 [](https://github.com/OpenBMB/MiniCPM) · `5,500+ 下载量`
ArXiv 2025. Team contribution (led MCP agent capabilities). 8,300+ GitHub Stars.