pith. sign in

Zelin Tan

Identifiers

No identifiers captured yet.

Papers (4)

  1. Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents cs.CL · 2026 · author #2
  2. PAPO: Stabilizing Rubric Integration Training via Decoupled Advantage Normalization cs.AI · 2026 · author #1
  3. Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning cs.LG · 2025 · author #1
  4. The Landscape of Agentic Reinforcement Learning for LLMs: A Survey cs.AI · 2025 · author #6

Mentions

No mention provenance yet.

Frequent Coauthors