← back to paper

Review history

arxiv: 2605.07501 · 2 revisions

ExpThink: Experience-Guided Reinforcement Learning for Adaptive Chain-of-Thought Compression

1. 2026-05-20 UNVERDICTED LOW v0.9.0 novelty 6.0
   31731 ms 5805 in 1106 out 2026-05-20T23:06:17.129120+00:00
2. 2026-05-11 UNVERDICTED LOW v0.9.0 novelty 5.0
   21869 ms 5574 in 1206 out 2026-05-11T01:56:57.476130+00:00