MemPO - a NewBeeKing Collection

NewBeeKing 's Collections

MemPO

updated 6 days ago

MemPO

NewBeeKing/MemPO_Qwen2.5-SFT-RL

Text Generation • 7B • Updated about 14 hours ago • 717
NewBeeKing/MemPO_Qwen2.5-SFT

Text Generation • 8B • Updated Mar 11 • 18
NewBeeKing/MemPO_RL-train-dataset

Viewer • Updated about 1 month ago • 10.5k • 25
NewBeeKing/MemPO_eval-dataset

Preview • Updated Mar 11 • 39
MemPO: Self-Memory Policy Optimization for Long-Horizon Agents

Paper • 2603.00680 • Published 8 days ago • 1