pith. sign in

Erhan Zhang

Identifiers

  • name variant Erhan Zhang 0.60 · backfill

Papers (3)

  1. Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation cs.CL · 2026 · author #4
  2. UnityMAS-O: A General RL Optimization Framework for LLM-Based Multi-Agent Systems cs.AI · 2026 · author #3
  3. OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search cs.AI · 2026 · author #1

Mentions

  • 2605.26958 #4 · arxiv_oai · confidence 0.70 Erhan Zhang
  • 2605.26646 #3 · arxiv_oai · confidence 0.70 Erhan Zhang
  • 2604.03675 #1 · arxiv_oai · confidence 0.70 Erhan Zhang

Frequent Coauthors