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

Published Saturday, October 31, 2026 · 11:06 PM EDT

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

Published by Tech & Business, a media brand covering technology and business. This story was sourced from cs.AI updates on arXiv.org and reviewed by the T&B editorial agent team.

Back to Newswire

Keep reading

Full wire

AI Science

GARDEN preprint demonstrates reusable AI-designed rewards for cooperating agents

Researchers report in a preprint that GARDEN, a system that uses a language model to design rewards for cooperating agents, improved performance when its reward programs transferred unchanged to related scenarios unseen during design.

AI Robotics

Exin founder reports AI-controlled brain injection in a live mouse

An AI agent controlled a robotic brain injection in a living mouse, Exin Therapeutics cofounder Gabriel Ocana Santero told WIRED.

Science AI

P2P preprint reports survey-response reconstruction at approximately $0.8 per survey

Researchers report that Prompts to Proxies, an inference-time system for reconstructing population survey responses, achieved average test mean squared error of 0.014 across 14 American Trends Panel waves at approximately 0.8 USD per survey.

Science AI

WorldFlow preprint reports lower errors in predicting 3D motion

WorldFlow, a model that jointly predicts future video and three-dimensional motion, achieved a 54.2% reduction in average displacement error against the strongest external baseline on the SpatialCog evaluation set, its authors report in an arXiv preprint.

AI Science

GAAC preprint reports lossless cache compression and higher inference throughput

Researchers report in a preprint that GAAC, a system for compressing the stored attention data used by language models, reduces resident cache memory by approximately 26% and increases aggregate serving throughput by 13-29% under comparable cache-memory budgets.

AI Science

Preprint finds hiding system labels improves AI judges of entity matches

A preprint reports that hiding a system's decision label improves how reliably AI judges assess whether records in different knowledge graphs refer to the same entity. The study tested three frontier models, three datasets and four entity alignment systems.