Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chen, Ziyang, Chen, Renbing, Li, Daowei, Liao, Jinzhi, Sun, Jiashen, Zeng, Ke, Zhao, Xiang
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2604.15190
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915940677976064
author Chen, Ziyang
Chen, Renbing
Li, Daowei
Liao, Jinzhi
Sun, Jiashen
Zeng, Ke
Zhao, Xiang
author_facet Chen, Ziyang
Chen, Renbing
Li, Daowei
Liao, Jinzhi
Sun, Jiashen
Zeng, Ke
Zhao, Xiang
contents Simulating group-level user behavior enables scalable counterfactual evaluation of merchant strategies without costly online experiments. However, building a trustworthy simulator faces two structural challenges. First, information incompleteness causes reasoning-based simulators to over-rationalize when unobserved factors such as offline context and implicit habits are missing. Second, mechanism duality requires capturing both interpretable preferences and implicit statistical regularities, which no single paradigm achieves alone. We propose Policy-Guided Hybrid Simulation (PGHS), a dual-process framework that mines transferable decision policies from behavioral trajectories and uses them as a shared alignment layer. This layer anchors an LLM-based reasoning branch that prevents over-rationalization and an ML-based fitting branch that absorbs implicit regularities. Group-level predictions from both branches are fused for complementary correction. We deploy PGHS on Meituan with 101 merchants and over 26,000 trajectories. PGHS achieves a group simulation error of 8.80%, improving over the best reasoning-based and fitting-based baselines by 45.8% and 40.9% respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2604_15190
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Meituan Merchant Business Diagnosis via Policy-Guided Dual-Process User Simulation
Chen, Ziyang
Chen, Renbing
Li, Daowei
Liao, Jinzhi
Sun, Jiashen
Zeng, Ke
Zhao, Xiang
Artificial Intelligence
Computation and Language
H.3.3
Simulating group-level user behavior enables scalable counterfactual evaluation of merchant strategies without costly online experiments. However, building a trustworthy simulator faces two structural challenges. First, information incompleteness causes reasoning-based simulators to over-rationalize when unobserved factors such as offline context and implicit habits are missing. Second, mechanism duality requires capturing both interpretable preferences and implicit statistical regularities, which no single paradigm achieves alone. We propose Policy-Guided Hybrid Simulation (PGHS), a dual-process framework that mines transferable decision policies from behavioral trajectories and uses them as a shared alignment layer. This layer anchors an LLM-based reasoning branch that prevents over-rationalization and an ML-based fitting branch that absorbs implicit regularities. Group-level predictions from both branches are fused for complementary correction. We deploy PGHS on Meituan with 101 merchants and over 26,000 trajectories. PGHS achieves a group simulation error of 8.80%, improving over the best reasoning-based and fitting-based baselines by 45.8% and 40.9% respectively.
title Meituan Merchant Business Diagnosis via Policy-Guided Dual-Process User Simulation
topic Artificial Intelligence
Computation and Language
H.3.3
url https://arxiv.org/abs/2604.15190