AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents
Submitted to KDD 2026. Corresponding author. Diagnosing step-level process quality in tool-using agents.
shengda-fan
•
•
1 分钟阅读时长
ToLeaP: Rethinking Development of Tool Learning with Large Language Models
Submitted to ACL 2026. First author. Unified evaluation platform for tool-learning agents.
Reflective Reinforcement Tool Learning
Submitted to ACL 2026. Reflective reinforcement learning for tool learning.
MiniCPM4-MCP
🏆 **Project Lead** · Edge-scale (8B) agent LLM mastering MCP tools [](https://github.com/OpenBMB/MiniCPM) …
•
1 分钟阅读时长
MiniCPM4: Ultra-Efficient LLMs on End Devices
ArXiv 2025. Team contribution (led MCP agent capabilities). 8,300+ GitHub Stars.
minicpm-team
ToolLLM
🔧 **Project Refactoring Lead** · Tool learning framework connecting to 16,000+ real-world APIs …
•
1 分钟阅读时长