ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning
Paper • 2610.18683 • Published • 16
Qi Zhu
zhuqi
AI & ML interests
Dialog system, Pre-training
Recent Activity
liked a model over 1 year ago
unsloth/Meta-Llama-3.1-8B liked a model about 3 years ago
openai/whisper-large-v2Organizations
upvoted a paper 12 days ago