pith. sign in

Lizhou Cai

Identifiers

  • name variant Lizhou Cai 0.60 · backfill

Papers (2)

  1. TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning cs.LG · 2026 · author #5
  2. Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex cs.LG · 2026 · author #8

Mentions

  • 2606.11119 #5 · arxiv_oai · confidence 0.70 Lizhou Cai
  • 2605.06139 #8 · arxiv_oai · confidence 0.70 Lizhou Cai

Frequent Coauthors