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)→
More from Research
- WEDGE paper generates training environments conditioned on navigation agent failures — _akhaliq · 2026-10-16
- RExBench: best coding agent completes only 33% of autonomous research extensions — najoungkim · 2026-10-16
- Google's CLASHarness benchmarks multi-agent conflicts in computer use, finds frontier VLMs struggle — google · 2026-10-16
- Tsinghua team proves vanilla flow-matching sampling can't exceed constant-depth expressive power — SQZ · 2026-10-16
- APEX-Harm benchmark: script-based injection attacks easily compromise agents in shared workspaces — KAUST · 2026-10-16
- Residual-stream forecasts predict agent violations before they happen, USC study shows — USC · 2026-10-16