Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents
- 类型：arxiv
- 标识：2609.39982
- 链接：https://arxiv.org/abs/2609.39982
- 主分类：evaluation
- 形态：method
- TLDR：Terminal agents act through stochastic model generations, yet the ability to generate a useful action does not ensure its reliable execution. A poor command (e.g., wrong package install) can change the environment in ways that hinder subsequent progress, even when the model could generate a better alternative. We investigate whether allocating test-time compute at the model-harness boundary can improve action reliability and trajectory success, and what makes this allocation effective. To study these questions, we introduce Mid-Harness, which samples and verifies candidate actions before forwa
- 副分类：agent
- 待LLM分类：否
- 来源文件：
- /inbox/tom/_candidates/2026-10-01-agent-rag-longcontext-candidates.json