Performance comparison of Procedural Graph against 7 baselines (Vanilla ReAct, MemoryBank, RAP, ExpeL, AutoGuide, AWM, KnowAgent) on MultiChallenge (multi-turn dialogue instruction retention (166 test items, LLM judged overall success)) using Gemini 3.1 Pro. Procedural Graph achieves 95.78% compared to the best baseline score of 95.18% (margin of +0.6%).

model: Gemini 3.1 Pro · method: Vanilla ReAct (Yao et al., 2023b) · benchmark: MultiChallenge

model: Gemini 3.1 Pro · method: MemoryBank (Zhong et al., 2024) · benchmark: MultiChallenge

model: Gemini 3.1 Pro · method: RAP (Kagaya et al., 2024) · benchmark: MultiChallenge

model: Gemini 3.1 Pro · method: ExpeL (Zhao et al., 2024) · benchmark: MultiChallenge

model: Gemini 3.1 Pro · method: AutoGuide (Fu et al., 2024) · benchmark: MultiChallenge

model: Gemini 3.1 Pro · method: AWM (Wang et al., 2025b) · benchmark: MultiChallenge

model: Gemini 3.1 Pro · method: KnowAgent (Zhu et al., 2025) · benchmark: MultiChallenge

model: Gemini 3.1 Pro · method: Procedural Graph (Ours) · benchmark: MultiChallenge