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. 830+ GitHub Stars.
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. 830+ GitHub Stars.
MiniCPM4-MCP
Project Lead — edge-scale (8B) agent LLM mastering MCP tools; surpasses GPT-4o and Qwen3-8B; 5,500+ downloads
•
1 min read
Collaborative Evolving Strategy for Automatic Data-Centric Development
ArXiv 2024. Co-first author. Collaborative evolving strategy for data-centric development. 15,100+ GitHub Stars.
xu-yang
Collaborative Evolving Strategy for Automatic Data-Centric Development
ArXiv 2024. Co-first author. Collaborative evolving strategy for data-centric development. 15,100+ GitHub Stars.
xu-yang
RD2Bench: Toward Data-Centric Automatic R&D
ICLR 2024 Workshop. First author. RD2Bench / RD-Agent for data-centric automatic R&D. Featured in the Microsoft Build 2025 keynote; 15,100+ GitHub Stars.
RD2Bench: Toward Data-Centric Automatic R&D
ICLR 2024 Workshop. First author. RD2Bench / RD-Agent for data-centric automatic R&D. Featured in the Microsoft Build 2025 keynote; 15,100+ GitHub Stars.