← back to paper

Review history

arxiv: 2508.12387 · 2 revisions

ReaLM: Reflection-Enhanced Autonomous Reasoning with Small Language Models

1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
   143634 ms 21919 in 15410 out 2026-08-15T17:22:35.405882+00:00
2. 2026-08-05 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 4.0
   201221 ms 21900 in 17745 out 2026-08-05T19:30:30.804701+00:00