Turn-PPO: Turn-Level Advantage Estimation with PPO for Improved Multi-Turn RL in Agentic LLMs Paper • 2512.17008 • Published Dec 18, 2025 • 10
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization Paper • 2601.05242 • Published 10 days ago • 194
