AEPO - a dongguanting Collection

dongguanting 's Collections

AEPO

ARPO

AEPO

updated 6 days ago

The official datasets and model checkpoints of AEPO

Agentic Entropy-Balanced Policy Optimization

Paper • 2510.14545 • Published 11 days ago • 96
dongguanting/Qwen3-8B-AEPO-DeepSearch

Text Generation • 8B • Updated about 6 hours ago • 54
dongguanting/Qwen3-14B-AEPO-DeepSearch

Robotics • 15B • Updated 6 days ago • 44 • 1
dongguanting/Qwen2.5-7B-AEPO

Text Generation • 8B • Updated about 6 hours ago • 44