← back to paper

Review history

arxiv: 2602.01869 · 2 revisions

Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents

1. 2026-08-03 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 5.0
   88999 ms 22170 in 9169 out 2026-08-03T05:30:59.680985+00:00
2. 2026-05-16 UNVERDICTED LOW v0.9.0 novelty 7.0
   38209 ms 5504 in 1729 out 2026-05-16T08:31:09.441739+00:00