← back to paper

Review history

arxiv: 2509.07676 · 2 revisions

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding

1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 4.0
   173446 ms 13218 in 22716 out 2026-08-15T16:12:24.190943+00:00
2. 2026-08-04 REJECT MODERATE v1.3.0-alltime-deepseek novelty 4.0
   147634 ms 13194 in 15469 out 2026-08-04T21:51:10.828236+00:00