MemT-1.0: Towards Memory-Native Evolution
ArXiv 2026. Team contribution (led the RL stage). 100K+ downloads within one week of release.
memtensor-team
•
•
1 min read
MemT-1.0: Towards Memory-Native Evolution
ArXiv 2026. Team contribution (led the RL stage). 100K+ downloads within one week of release.
memtensor-team
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.
Reflective Reinforcement Tool Learning
Reflective reinforcement learning for tool learning.
Reflective Reinforcement Tool Learning
Reflective reinforcement learning for tool learning.
MiniCPM4: Ultra-Efficient LLMs on End Devices
ArXiv 2025. Team contribution (led MCP agent capabilities). 10,700+ GitHub Stars.
minicpm-team
MiniCPM4: Ultra-Efficient LLMs on End Devices
ArXiv 2025. Team contribution (led MCP agent capabilities). 10,700+ GitHub Stars.
minicpm-team
ToLeaP: Rethinking Development of Tool Learning with Large Language Models
ArXiv 2025. First author. Unified evaluation platform for tool-learning agents.
ToLeaP: Rethinking Development of Tool Learning with Large Language Models
ArXiv 2025. First author. Unified evaluation platform for tool-learning agents.