pith. sign in

Lu Pan

Identifiers

  • name variant Lu Pan 0.60 · backfill

Papers (6)

  1. Rethinking Continual Experience Internalization for Self-Evolving LLM Agents cs.CL · 2026 · author #8
  2. SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training cs.AI · 2026 · author #10
  3. Skill or Skip? Learning Selective Skill Invocation in Agentic Tasks via Dual-Granularity Preference Learning cs.CL · 2026 · author #8
  4. From $\log \pi$ to $\pi$: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight cs.LG · 2026 · author #8
  5. How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization cs.LG · 2026 · author #7
  6. MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning cs.LG · 2026 · author #8

Mentions

  • 2606.04703 #8 · arxiv_oai · confidence 0.70 Lu Pan
  • 2606.02355 #10 · arxiv_oai · confidence 0.70 Lu Pan
  • 2606.00510 #8 · arxiv_oai · confidence 0.70 Lu Pan

Frequent Coauthors