Zhen-Wen Dai

Follow the Winners: Conservative Policy Improvement with the Cross-Entropy Method for Critic-Free RFT

Critic-free reinforcement fine-tuning (RFT) for agentic large language models is often done through GRPO-style methods, which compute a group baseline over repeated rollouts to reduce target variance. However, this setup is ill-suited to agents acting in stateful environments such as live services or security sandboxes...