Alfredo Garcia

Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize Approach

ADARL: Adaptive Low-Rank Structures for Robust Policy Learning under Uncertainty

Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Reward Design

ST-PPO: Stabilized Off-Policy Proximal Policy Optimization for Multi-Turn Agents

Joint Reward and Policy Learning with Demonstrations and Human Feedback Improves Alignment