Task-CoEvolve Cuts Evaluation Cost by 80% via Adaptive Sampling

burny_tech · x · 2026-08-24

This paper introduces 'Task-CoEvolve,' an optimization method that uses adaptive validation task selection to reduce computational waste. Instead of re-evaluating every candidate on every task, it samples tasks where candidate harnesses disagree most and corrects for this sampling bias to estimate full-set performance. On Terminal-Bench 2.1, it achieves nearly identical final performance with only 20% of the evaluations, reducing search costs by 67-80%.

Related event: Task-CoEvolve Algorithm Cuts Evaluation Costs by 80%(2 posts)→

Original post →

More from Research

Research channel →