# ForeCritic preprint reports 4.4-7.5 times shorter ML agent task times

_Published Saturday, October 31, 2026 at 11:06 PM EDT · Science, AI · Latest · Tier 2 — Notable_

Researchers report in a preprint that ForeCritic cuts mean task time by 4.4-7.5 times inside AIDE, ML-Master and ForeAgent while keeping mean scores within 0.01 or raising them. The system selects promising candidate programs without executing every candidate.

ForeCritic adapts a 9B decision model using 5k executed program pairs. On 12,438 held-out pairs from 26 machine-learning tasks, it selected the better program 79.4% of the time, compared with 53-62% for general-purpose language-model judges. It learns directly which candidate is better rather than predicting intermediate execution outcomes.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2610.38439)

---
Canonical: https://techandbusiness.org/newswire/YOGGkRZg3_7HcXtIudzaeN
Published: 2026-11-01T03:06:31.501Z
Story chronology: 2026-10-31T04:00:00.000Z
Retrieved: 2026-11-01T05:23:06.956Z
Publisher: Tech & Business (techandbusiness.org)