← back to paper

Review history

arxiv: 2607.19345 · 2 revisions

Copy Less, Ground More: Overcoming Repetitive Copying in Long-Context Reasoning via Evidence-Aware Reinforcement Learning

1. 2026-08-03 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 5.0
   205387 ms 15642 in 20573 out 2026-08-03T01:50:53.176508+00:00
2. 2026-08-01 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 6.0
   183608 ms 15621 in 20439 out 2026-08-01T12:41:36.617241+00:00