Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| 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 |