Performance comparison of Procedural Graph against 7 baselines (Vanilla ReAct, MemoryBank, RAP, ExpeL, AutoGuide, AWM, KnowAgent) on τ-bench (customer service retail domain (115 test items, DB state match)) using Gemini 3.1 Pro. Procedural Graph achieves 80.0% compared to the best baseline score of 73.04% (margin of +6.96%).

Performance comparison of Procedural Graph against 7 baselines (Vanilla ReAct, MemoryBank, RAP, ExpeL, AutoGuide, AWM, KnowAgent) on τ-bench (customer service retail domain (115 test items, DB state match)) using Gemini 3.1 Pro. Procedural Graph achieves 80.0% compared to the best baseline score of 73.04% (margin of +6.96%). · CiteArk

测量结果

已评估 0/8 项

获得支持 0有争议或冲突 0尚未评估 8

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
model: Gemini 3.1 Pro · method: Vanilla ReAct (Yao et al., 2023b) · benchmark: τ-bench	72.17%	—	尚未评估
model: Gemini 3.1 Pro · method: MemoryBank (Zhong et al., 2024) · benchmark: τ-bench	67.83%	—	尚未评估
model: Gemini 3.1 Pro · method: RAP (Kagaya et al., 2024) · benchmark: τ-bench	73.04%	—	尚未评估
model: Gemini 3.1 Pro · method: ExpeL (Zhao et al., 2024) · benchmark: τ-bench	64.35%	—	尚未评估
model: Gemini 3.1 Pro · method: AutoGuide (Fu et al., 2024) · benchmark: τ-bench	65.22%	—	尚未评估
model: Gemini 3.1 Pro · method: AWM (Wang et al., 2025b) · benchmark: τ-bench	67.83%	—	尚未评估
model: Gemini 3.1 Pro · method: KnowAgent (Zhu et al., 2025) · benchmark: τ-bench	64.35%	—	尚未评估
model: Gemini 3.1 Pro · method: Procedural Graph (Ours) · benchmark: τ-bench	80%	—	尚未评估

报告指标与观测值

Assessment（0）

关联运行（0）

测量结果