LLM Coding Agent Experiments
收藏官方服务：
资源简介：
Session logs, scoring rubrics, and analysis outputs from pre-registered model comparison experiments (exp3, exp4) evaluating open-weight LLM coding agents as SCOUT delegates in the goose-coder recipe. Data include per-run structured delegate outputs (JSON), blind scorer justifications, group assignment maps, and token/timing metadata.
提供机构：
Zenodo创建时间：
2026-03-16
