Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection
- 类型：arxiv
- 标识：2608.20169
- 链接：https://arxiv.org/abs/2608.20169
- 主分类：evaluation
- 形态：method
- TLDR：We present a novel approach to efficient LLM harness optimization through adaptive validation task selection. Harness optimization iteratively rewrites the harness code based on validation performance, enabling substantial performance gains without updating the underlying model weights. Existing approaches, however, evaluate a fixed validation set in full at every iteration, incurring substantial evaluation costs even on tasks that become less discriminative as the harness evolves. We propose Task-CoEvolve, which co-evolves the validation tasks with the harness by addressing two challenges: se
- 待LLM分类：否
- 标题中文：Task-CoEvolve：通过自适应验证任务选择实现 Harness 高效优化
- TLDR中文：我们提出一种通过自适应验证任务选择来实现 LLM harness 高效优化的新方法。Harness 优化基于验证性能迭代改写 harness 代码，无需更新底层模型权重即可获得显著性能提升。然而现有方法在每次迭代中对固定的验证集进行完整评估，即便某些任务随 harness 演进区分度下降，仍产生高昂的评测成本。我们提出 Task-CoEvolve，通过应对两项挑战使验证任务与 harness 协同演进：se
- 来源文件：
- /inbox/tom/_candidates/2026-08-25-agent-rag-longcontext-candidates.json