On the Limits of Test-Time Compute for Self-Evaluation
arXiv:2611.00350v1 Announce Type: new Abstract: Self-verification and aggregation have emerged as popular approaches for bridging the gap between pass@1 and pass@N. However, increasing the number of candidates does not consistently narrow the gap between final-answer accuracy and pass@N. To underst…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-11-03 05:00 · arXiv cs.LG
On the Limits of Test-Time Compute for Self-Evaluation