mlsanityData to 14 Oct 2026

Meituan Merchant Business Diagnosis via Policy-Guided Dual-Process User Simulation

arXiv 2604.15190 ↗First posted 16 Apr 2026cs.AI cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 27 references that are in the map. First posted on arXiv 16 Apr 2026.

Builds on

13 of 27 references.

References · 13

  1. 2018Self-Attentive Sequential Recommendationcited by 1,184
  2. 2016Wide & Deep Learning for Recommender Systemscited by 747
  3. 2017Deep Interest Network for Click-Through Rate Predictioncited by 544
  4. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectivescited by 257
  5. 2021Deconfounded Recommendation for Alleviating Bias Amplificationcited by 51
  6. 2024Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agentscited by 40
  7. 2024LLM-Powered User Simulator for Recommender Systemcited by 39
  8. 2024ControlAgent: Automating Control System Design via Novel Integration of LLM Agents and Domain Expertisecited by 21
  9. 2025User Simulation in the Era of Generative AI: User Modeling, Synthetic Data Generation, and System Evaluationcited by 17
  10. 2020Causal Network Motifs: Identifying Heterogeneous Spillover Effects in A/B Testscited by 14
  11. 2024CXSimulator: A User Behavior Simulation using LLM Embeddings for Web-Marketing Campaign Assessmentcited by 8
  12. 2017Limitations of design-based causal inference and A/B testing under arbitrary and network interferencecited by 6
1 more
  1. 2019The Identification and Estimation of Direct and Indirect Effects in A/B Tests through Causal Mediation Analysiscited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies
  2. 2026Dynamics of Cognitive Heterogeneity: Investigating Behavioral Biases in Multi-Stage Supply Chains with LLM-Based Simulation
  3. 2026What Makes a Sale? Simulating End-to-End Seller--Buyer Retail Dynamics with LLM Agents
  4. 2026MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations
  5. 2026RetailBench: Benchmarking long horizon reasoning and coherent decision making of LLM agents in realistic retail environments
  6. 2026Learning to Simulate Individuals from Macro Social Signals
  7. 2026RetailBench: Evaluating Long-Horizon Autonomous Decision-Making and Strategy Stability of LLM Agents in Realistic Retail Environments
  8. 2026When Guardrails Look Effective: Construct Validity Failures in LLM Agent Commerce Evaluation