PPL
Junda Wu
Papers (5)
SkillBrew: Multi-Objective Curation of Skill Banks for LLM AgentsF-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 AgentsFERA: Uncertainty-Aware Federated Reasoning for Large Language ModelsSkill-CMIB: Multimodal Agent Skill for Consistent Action via Conditional Multimodal Information Bottleneck