← back to paper

Review history

arxiv: 2607.26457 · 2 revisions

DHRCL:Training Code LLMs with Dense Hierarchical Rewards and Curriculum Learning

1. 2026-08-05 CONDITIONAL HIGH v1.3.0-alltime-deepseek novelty 6.0
   181686 ms 17323 in 17513 out 2026-08-05T04:21:42.693278+00:00
2. 2026-08-01 CONDITIONAL MODERATE v1.3.0-daily-deepseek novelty 6.0
   218323 ms 17294 in 12528 out 2026-08-01T15:25:23.814104+00:00