AEPO - a dongguanting Collection

dongguanting 's Collections

AEPO

ARPO

AEPO

updated Oct 21

The official datasets and model checkpoints of AEPO

Agentic Entropy-Balanced Policy Optimization

Paper • 2510.14545 • Published Oct 16 • 103
dongguanting/Qwen3-8B-AEPO-DeepSearch

Text Generation • 8B • Updated Oct 27 • 7 • 1
dongguanting/Qwen3-14B-AEPO-DeepSearch

Robotics • 15B • Updated Oct 21 • 9 • 1
dongguanting/Qwen2.5-7B-AEPO

Text Generation • 8B • Updated Oct 27 • 16 • 1