Resource use and parsing robustness across PG construction modes on MultiChallenge (56-sample test split) with Gemini 3.5 Flash. Mode 5 (Scratch + Online Evolution) achieves a 45.7% reduction in parsing failures per sample relative to unguided baseline (0.57 vs 1.05), while using 5.05 steps and 92.81s per sample (compared to 8.02 steps and 166.57s for Mode 4). Mode 3 achieves highest overall success (92.86%) at 6.73 steps and 128.50s.

Resource use and parsing robustness across PG construction modes on MultiChallenge (56-sample test split) with Gemini 3.5 Flash. Mode 5 (Scratch + Online Evolution) achieves a 45.7% reduction in parsing failures per sample relative to unguided baseline (0.57 vs 1.05), while using 5.05 steps and 92.81s per sample (compared to 8.02 steps and 166.57s for Mode 4). Mode 3 achieves highest overall success (92.86%) at 6.73 steps and 128.50s. · CiteArk

测量结果

已评估 0/30 项

获得支持 0有争议或冲突 0尚未评估 30

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
constructionMode: Unguided Baseline (w/o PG)	87.5%	—	尚未评估
constructionMode: Unguided Baseline (w/o PG)	7,403.98 tokens	—	尚未评估
constructionMode: Unguided Baseline (w/o PG)	7.05 steps	—	尚未评估
constructionMode: Unguided Baseline (w/o PG)	1.05 failures_per_sample	—	尚未评估
constructionMode: Unguided Baseline (w/o PG)	127.59 seconds	—	尚未评估
constructionMode: Mode 1: Hand-crafted Expert	58.93%	—	尚未评估
constructionMode: Mode 1: Hand-crafted Expert	11,039.82 tokens	—	尚未评估
constructionMode: Mode 1: Hand-crafted Expert	6.6 steps	—	尚未评估
constructionMode: Mode 1: Hand-crafted Expert	0.88 failures_per_sample	—	尚未评估
constructionMode: Mode 1: Hand-crafted Expert	117.7 seconds	—	尚未评估
constructionMode: Mode 2: Expert + Static Update	53.57%	—	尚未评估
constructionMode: Mode 2: Expert + Static Update	5,990.79 tokens	—	尚未评估

报告指标与观测值

Assessment（0）

关联运行（0）

测量结果