Reinforcement Learning

AgentCPM-Explore

🏆 **项目负责人** · 我主导了一个面向长程深度探索的开源 4B 智能体模型 [![Stars](https://img.shields.io/github/stars/OpenBMB/AgentCPM?style=social)](https://github.com/OpenBMB/AgentCPM)

Mar 20, 2026 • 1 min read

Autonomous Agents

AgentCPM-Explore

🏆 **Project Lead** · I led an open-source 4B agent model for long-horizon deep exploration …

Mar 20, 2026 • 1 min read

Autonomous Agents

AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents

ArXiv 2026. First author. Open-source 4B agent model achieving SOTA on GAIA & HLE, surpassing GPT-5 and Claude-4.5-Sonnet.

Haotian Chen

• Feb 1, 2026 • 1 min read

Autonomous Agents

AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents

ArXiv 2026. First author. Open-source 4B agent model achieving SOTA on GAIA & HLE, surpassing GPT-5 and Claude-4.5-Sonnet.

Haotian Chen

• Feb 1, 2026 • 1 min read

Tool Learning

Reflective Reinforcement Tool Learning

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

Haotian Chen

• Jan 1, 2026 • 1 min read

Tool Learning

Reflective Reinforcement Tool Learning

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

Haotian Chen

• Jan 1, 2026 • 1 min read

Reinforcement Learning

AgentRL

🏆 **项目负责人** · 面向 AgentCPM 模型族的全异步智能体强化学习训练基础设施 `100+ 工具` · `20+ 基准` · `全流程可视化`

Jan 1, 2026 • 1 min read

Reinforcement Learning

AgentRL

🏆 **Project Lead** · Fully asynchronous agent RL training infrastructure for the AgentCPM model family `100+ Tools` · `20+ Benchmarks` · `Full-cycle Visualization`

Jan 1, 2026 • 1 min read