MALLES: A Multi-agent LLMs-based Economic Sandbox with Consumer Preference Alignment

2026-03-18

AI Summary

This work addresses the challenges of decision modeling in high-dimensional, multimodal economic environments, where agent heterogeneity and sparse combinatorial data hinder accurate simulation. To overcome these issues, the authors propose a unified simulation paradigm that integrates preference learning, mean-field theory, and a multi-agent structured dialogue framework. By aligning and post-training large language models on cross-category transaction data, and incorporating mean-field stabilization mechanisms alongside a collaborative multi-agent discussion architecture, they construct a high-fidelity, scalable economic sandbox. The proposed approach substantially alleviates data sparsity in individual product categories and outperforms existing economic and financial LLM baselines in terms of product selection accuracy, purchase quantity prediction, and simulation stability, thereby enhancing the generalization and scalability of consumer decision modeling.

Technology Category

• Game Theory and Economic Paradigms: Mechanism Design
• Multiagent Systems: Mechanism Design
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

In the real economy, modern decision-making is fundamentally challenged by high-dimensional, multimodal environments, which are further complicated by agent heterogeneity and combinatorial data sparsity. This paper introduces a Multi-Agent Large Language Model-based Economic Sandbox (MALLES), leveraging the inherent generalization capabilities of large-sacle models to establish a unified simulation framework applicable to cross-domain and cross-category scenarios. Central to our approach is a preference learning paradigm in which LLMs are economically aligned via post-training on extensive, heterogeneous transaction records across diverse product categories. This methodology enables the models to internalize and transfer latent consumer preference patterns, thereby mitigating the data sparsity issues prevalent in individual categories. To enhance simulation stability, we implement a mean-field mechanism designed to model the dynamic interactions between the product environment and customer populations, effectively stabilizing sampling processes within high-dimensional decision spaces. Furthermore, we propose a multi-agent discussion framework wherein specialized agents collaboratively process extensive product information. This architecture distributes cognitive load to alleviate single-agent attention bottlenecks and captures critical decision factors through structured dialogue. Experiments demonstrate that our framework achieves significant improvements in product selection accuracy, purchase quantity prediction, and simulation stability compared to existing economic and financial LLM simulation baselines. Our results substantiate the potential of large language models as a foundational pillar for high-fidelity, scalable decision simulation and latter analysis in the real economy based on foundational database.

Problem

• high-dimensional environments
• agent heterogeneity
• data sparsity
• consumer preference
• economic simulation

Innovation

• Multi-agent LLMs
• Preference Alignment
• Mean-field Mechanism
• Economic Simulation
• Consumer Preference Learning