Across five trials, DoCtOR improves initial task success rates by 22% on HotPotQA, 26% on ChartQAPro, and 27% on Mind2Web, and outperforms the reported reflection baselines.

Across five trials, DoCtOR improves initial task success rates by 22% on HotPotQA, 26% on ChartQAPro, and 27% on Mind2Web, and outperforms the reported reflection baselines. · CiteArk

测量结果

已评估 0/3 项

获得支持 0有争议或冲突 0尚未评估 3

保留同一结论下的完整结果组。已有评估排在前面；单项判断不替代整组结论。展开行查看条件、来源与历次证据。

每行是一项测量，分别显示论文报告、最近可用实测和累计证据状态。
指标与条件	论文报告	最近可用实测	证据判断
trials: 5 · dataset: HotPotQA · metric_scope: task success rate · test_tasks_per_trial: 100	22 percentage_points	—	尚未评估
trials: 5 · dataset: ChartQAPro · metric_scope: task success rate · test_tasks_per_trial: 100	26 percentage_points	—	尚未评估
trials: 5 · dataset: Mind2Web · metric_scope: task success rate · test_tasks_per_trial: 100	27 percentage_points	—	尚未评估

Across five trials, DoCtOR improves initial task success rates by 22% on HotPotQA, 26% on ChartQAPro, and 27% on Mind2Web, and outperforms the reported reflection baselines.

报告指标与观测值

Assessment（0）

关联运行（0）

测量结果