← back to paper

Review history

arxiv: 2506.13358 · 2 revisions

Socratic RL: A Novel Framework for Efficient Knowledge Acquisition through Iterative Reflection and Viewpoint Distillation

1. 2026-08-15 UNVERDICTED HIGH v1.4.0-alltime-deepseek-medium novelty 6.0
   127290 ms 7615 in 14220 out 2026-08-15T20:03:46.850457+00:00
2. 2026-08-07 CONDITIONAL HIGH v1.4.0-alltime-deepseek-medium novelty 5.0
   103115 ms 7641 in 10868 out 2026-08-07T00:34:10.228196+00:00