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.
AgentCPM-Explore
🏆 **Project Lead** · Open-source 4B agent model achieving SOTA on GAIA & HLE benchmarks …
•
1 分钟阅读时长
Reflective Reinforcement Tool Learning
Submitted to ACL 2026. Reflective reinforcement learning for tool learning.
AgentRL
🏆 **Project Lead** · Fully asynchronous agent RL training infrastructure for the AgentCPM model family `100+ Tools` · `20+ Benchmarks` · `Full-cycle Visualization`
•
1 分钟阅读时长
AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning
EMNLP 2025 Demo. GUI agents with reinforcement fine-tuning. 1,200+ GitHub Stars.
zhong-zhang