← back to paper

Review history

arxiv: 2507.18305 · 2 revisions

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit

1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
   148649 ms 13209 in 17327 out 2026-08-15T18:15:30.452059+00:00
2. 2026-08-06 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
   125292 ms 13209 in 12688 out 2026-08-06T14:35:45.763485+00:00