pith. sign in

Heyuan Deng

Identifiers

  • name variant Heyuan Deng 0.60 · backfill

Papers (3)

  1. EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL cs.CL · 2026 · author #11
  2. Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning cs.LG · 2025 · author #9
  3. KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning cs.LG · 2025 · author #3

Mentions

  • 2506.02208 #3 · arxiv_oai · confidence 0.70 Heyuan Deng
  • 2605.18703 #11 · arxiv_oai · confidence 0.70 Heyuan Deng

Frequent Coauthors