PRO-LONG scores 97.4% on ARC-AGI-3 with a log-file harness and 30-line prompt

srchvrs · x · 2026-07-27

PRO-LONG reaches 97.4% on public ARC-AGI-3 by using a log-file harness

The cited preprint argues that compositional generalization can improve when environment interaction is moved into a separate log file and a coding agent manipulates it programmatically.

The broader claim is that simple harnesses can make tasks more in-distribution, and in this case the harness plus minimal memory appears to do most of the work.

Original post →

More from coding & agent

coding & agent channel →