PPL
Xintong Li
Papers (4)
F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and RankingOLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct AgentsMASS-DPO: Multi-negative Active Sample Selection for Direct Policy OptimizationSkill-R1: Agent Skill Evolution via Reinforcement Learning