发表机构
Mohamed bin Zayed University of Artificial Intelligence; University of Waterloo（穆罕默德·本·扎耶德人工智能大学; 滑铁卢大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对大规模多智能体模拟中异质性下降问题，提出前景状态传播方法，解耦微观状态为前景与语义两部分，实现可扩展的LLM模拟。
AI 中文摘要
当前基于大语言模型的多智能体系统（MAS）会周期性压缩中间状态以减少推理时的令牌消耗，从而尝试纳入更多智能体。然而，朴素的扩展策略面临挑战。例如，在经济模拟中，大规模MAS通常丢弃语义丰富的经济状态，即智能体行为轨迹，而这些正是宏观经济波动的关键驱动因素。本文揭示了模拟过程中智能体异质性逐渐下降的现象，并提出了面向多智能体系统的前景状态传播（PspMAS）。受前景理论启发，PspMAS将每个智能体的微观状态解耦为紧凑的前景状态和富有表达力的语义状态。前者通过轻量级、可并行化的传播器记录心理痕迹，并持续向系统注入异质性；后者则利用大语言模型强大的感知、推理、规划和决策能力。这两个组件互补协作，提供了一种可扩展的基于大语言模型的多智能体模拟解决方案。
英文摘要
Current LLM-based multi-agent systems (MAS) periodically compress intermediate states to reduce inference-time token consumption, thereby attempting to incorporate more agents. However, naive scaling strategies face challenges. For example, in economic simulations, large-scale MAS typically discard semantically rich economic states, i.e., agent behavioral trajectories, which are key drivers of macroeconomic fluctuations. In this paper, we reveal a phenomenon in which agent heterogeneity gradually decreases during simulation, and propose Prospect-State Propagation for Multi-Agent Systems (PspMAS). Inspired by prospect theory, PspMAS decouples each agent's micro state into a compact Prospect State and an expressive Semantic State. The former records psychological traces through a lightweight, parallelizable propagator and continuously injects heterogeneity into the system. The latter leverages the strong perception, reasoning, planning, and decision-making abilities of LLMs. These two components work complementarily, providing a scalable LLM-based multi-agent simulation solution.
CommentsAccepted to Findings of EMNLP 2026
