MetaBench-Harness: Unlocking End-to-End Optimization of Benchmark Harnesses
This work proposes to optimize the benchmark generation workflow itself end to end with MetaBench-Harness, a dual-loop search framework that enables multi-dimensional evolution, steadily improving evolution reasonableness, benchmark competency, and evaluator robustness across successive rounds.
Xuan-Jun Chen, Hua-Hsuan Chen, Wei-Chung Lu et al.
· 0 citations