静态沙盒环境存在不足：模拟社会复杂性需要在基于大语言模型的多智能体仿真中实现开放式协同进化

摘要

倘若人工智能体不仅能交流，还能进化、适应，并以我们无法完全预见的方式重塑其世界，那将会怎样？随着大语言模型（LLM）如今驱动着多智能体系统和社会模拟，我们正目睹着为开放、不断变化的环境建模的新可能。然而，当前大多数模拟仍局限于静态的沙盒之中，其特征是预设任务、有限的动态变化和僵化的评估标准。这些限制使得它们难以捕捉现实社会中的复杂性。本文主张，静态的、任务特定的基准从根本上讲是不足的，必须重新思考。我们批判性地审视了将LLM与多智能体动态相结合的新兴架构，强调了诸如平衡稳定性与多样性、评估意外行为以及扩展至更高复杂性等关键挑战，并为此快速发展的领域引入了一套全新的分类体系。最后，我们提出了一项以开放性、持续协同进化以及发展具有韧性、社会对齐的AI生态系统为核心的研究路线图。我们呼吁社区超越静态范式，共同塑造下一代适应性强、具备社会意识的多智能体模拟系统。

English

What if artificial agents could not just communicate, but also evolve, adapt, and reshape their worlds in ways we cannot fully predict? With llm now powering multi-agent systems and social simulations, we are witnessing new possibilities for modeling open-ended, ever-changing environments. Yet, most current simulations remain constrained within static sandboxes, characterized by predefined tasks, limited dynamics, and rigid evaluation criteria. These limitations prevent them from capturing the complexity of real-world societies. In this paper, we argue that static, task-specific benchmarks are fundamentally inadequate and must be rethought. We critically review emerging architectures that blend llm with multi-agent dynamics, highlight key hurdles such as balancing stability and diversity, evaluating unexpected behaviors, and scaling to greater complexity, and introduce a fresh taxonomy for this rapidly evolving field. Finally, we present a research roadmap centered on open-endedness, continuous co-evolution, and the development of resilient, socially aligned AI ecosystems. We call on the community to move beyond static paradigms and help shape the next generation of adaptive, socially-aware multi-agent simulations.

静态沙盒环境存在不足：模拟社会复杂性需要在基于大语言模型的多智能体仿真中实现开放式协同进化

Static Sandboxes Are Inadequate: Modeling Societal Complexity Requires Open-Ended Co-Evolution in LLM-Based Multi-Agent Simulations

摘要

Support