Empowering Economic Simulation Through Situation-Aware Llm-Driven Generative System

• URL: http://arxiv.org/abs/2606.20720v1
• Date: Tue, 16 Jun 2026 17:24:32 GMT
• Title: Empowering Economic Simulation Through Situation-Aware Llm-Driven Generative System
• Abstract summary: Agent-Based Modeling (ABM) employs a BOTTOM-UP solution by incorporating micro-level dynamics to generate macroeconomic phenomena.<n>We propose SAMAS, which models individual agents with rich macroeconomic understanding embedded in LLMs and economic trajectories.<n>By jointly modeling both macro-level structural patterns and micro-level dynamic behaviors, SAMAS achieves superior performance in volatility realism and turning point prediction.
• Score: 3.666833138043776
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Traditional economic modeling typically follows a TOP-DOWN paradigm, neglecting individual diversity and the complexity of social interactions. To better capture the complexity of societal structure, Agent-Based Modeling (ABM) employs a BOTTOM-UP solution by incorporating micro-level dynamics to generate macroeconomic phenomena. Reinforcement Learning further improves its decision-making ability through tailored reward signals. However, existing ABM systems struggle to generalize beyond predefined scenarios. Recognizing the potential of LLM-driven role-playing in perception and human-like decision-making, we propose SAMAS, which models individual agents with rich macroeconomic understanding embedded in LLMs and economic trajectories experienced in the passing simulation steps. By jointly modeling both macro-level structural patterns and micro-level dynamic behaviors, SAMAS achieves superior performance in volatility realism and turning point prediction.

Related papers

• From Economic Agents to Agentic Economies: A Systems Blueprint for Economic World Models [79.95211458571744]
  Economic World Models (EWMs) are generative economic models that simulate how economies evolve from within.<n>This paper develops an implementation roadmap for building economic world models as generative engines.
  arXiv  Detail & Related papers  (2026-08-06T13:26:46Z)
• MobEvolve: An Agentic Self-Evolving Heuristic System for Interpretable Human Mobility Generation [51.824145170051516]
  MobEvolve is a self-evolving framework for human mobility generation.<n>It employs an agent to iteratively evolve its internal logic.<n>It significantly outperforms state-of-the-art deep generative and LLM-based methods.
  arXiv  Detail & Related papers  (2026-06-01T03:46:25Z)
• MALLES: A Multi-agent LLMs-based Economic Sandbox with Consumer Preference Alignment [18.220563522041733]
  This paper introduces a Multi-Agent Large Language Model-based Economic Sandbox (MALLES)<n>Central to our approach is a preference learning paradigm in which LLMs are economically aligned via post-training on extensive, heterogeneous transaction records.<n>Experiments demonstrate that our framework achieves significant improvements in product selection accuracy, purchase quantity prediction, and simulation stability.
  arXiv  Detail & Related papers  (2026-03-18T13:11:09Z)
• Reinforcement World Model Learning for LLM-based Agents [60.65003139516272]
  Reinforcement World Model Learning (RWML) is a self-conditioned method that learns action-supervised world models for LLM-based agents.<n>Our method aligns simulated next states produced by the model with realized next states observed from the environment.<n>We evaluate our method on ALFWorld and $2$ Bench and observe significant gains over the base model, despite being entirely self-supervised.
  arXiv  Detail & Related papers  (2026-02-05T16:30:08Z)
• Social World Model-Augmented Mechanism Design Policy Learning [58.739456918502704]
  We introduce SWM-AP (Social World Model-Augmented Mechanism Design Policy Learning), which learns a social world model hierarchically to enhance mechanism design.<n>We show that SWM-AP outperforms established model-based and model-free RL baselines in cumulative rewards and sample efficiency.
  arXiv  Detail & Related papers  (2025-10-22T06:01:21Z)
• Modeling Earth-Scale Human-Like Societies with One Billion Agents [54.465233996410156]
  Light Society is an agent-based simulation framework.<n>It formalizes social processes as structured transitions of agent and environment states.<n>It supports efficient simulation of societies with over one billion agents.
  arXiv  Detail & Related papers  (2025-06-07T09:14:12Z)
• Empowering Economic Simulation for Massively Multiplayer Online Games through Generative Agent-Based Modeling [53.26311872828166]
  We take a preliminary step in introducing a novel approach using Large Language Models (LLMs) in MMO economy simulation.<n>We design LLM-driven agents with human-like decision-making and adaptability.<n>These agents are equipped with the abilities of role-playing, perception, memory, and reasoning, addressing the aforementioned challenges effectively.
  arXiv  Detail & Related papers  (2025-06-05T07:21:13Z)
• TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets [41.858410843530244]
  Large language model (LLM) agents have gained traction as simulation tools for modeling human behavior.<n>We introduce TwinMarket, a novel multi-agent framework that leverages LLMs to simulate socio-economic systems.<n>Our approach provides valuable insights into the complex interplay between individual decision-making and collective socio-economic patterns.
  arXiv  Detail & Related papers  (2025-02-03T16:39:48Z)
• On the limits of agency in agent-based models [13.130587222524305]
  Agent-based modeling offers powerful insights into complex systems, but its practical utility has been limited by computational constraints. Recent advancements in large language models (LLMs) could enhance ABMs with adaptive agents, but their integration into large-scale simulations remains challenging. We present LLM archetypes, a technique that balances behavioral complexity with computational efficiency, allowing for nuanced agent behavior in large-scale simulations.
  arXiv  Detail & Related papers  (2024-09-14T04:17:24Z)
• EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities [43.70290385026672]
  We introduce EconAgent, a large language model-empowered agent with human-like characteristics for macroeconomic simulation. We first construct a simulation environment that incorporates various market dynamics driven by agents' decisions. Through the perception module, we create heterogeneous agents with distinct decision-making mechanisms.
  arXiv  Detail & Related papers  (2023-10-16T14:19:40Z)
• Simulation of emergence in artificial societies: a practical model-based approach with the EB-DEVS formalism [0.11470070927586014]
  We apply EB-DEVS, a novel formalism tailored for the modelling, simulation and live identification of emergent properties. This work provides case study-driven evidence for the neatness and compactness of the approach to modelling communication structures.
  arXiv  Detail & Related papers  (2021-10-15T15:55:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.