让智能体用进化出的精简语言对话，大幅降低社会模拟的计算开销。
EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulation
- 通过自然选择筛选同义词并优化句法规则，生成高效通信语言
- 实验显示令牌消耗降低超20%，模拟精度未下降
- 适合大规模社会模拟场景，尤其关注效率与可扩展性的研究者
大型语言模型（LLMs）展现出出色的角色扮演能力，能够复现复杂社会行为。尽管大规模社会模拟日益受到关注，但仍面临高昂的时间与计算成本问题。现有方案如分布式机制或混合代理模型集成，或无法解决推理开销，或牺牲准确性和泛化能力。为此，我们提出EcoLANG：一种面向社会模拟的高效且有效的智能体通信语言诱导方法。EcoLANG分为两个阶段：(1) 语言演化阶段，通过自然选择过滤同义词并优化句子级规则；(2) 语言应用阶段，社会模拟中的智能体使用演化后的语言进行交流。实验结果表明，EcoLANG将令牌消耗降低超过20%，在不损失模拟精度的前提下显著提升效率。
原文摘要 · Abstract (English)
Large language models (LLMs) have demonstrated an impressive ability to role-play humans and replicate complex social dynamics. While large-scale social simulations are gaining increasing attention, they still face significant challenges, particularly regarding high time and computation costs. Existing solutions, such as distributed mechanisms or hybrid agent-based model (ABM) integrations, either fail to address inference costs or compromise accuracy and generalizability. To this end, we propose EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulation. EcoLANG operates in two stages: (1) language evolution, where we filter synonymous words and optimize sentence-level rules through natural selection, and (2) language utilization, where agents in social simulations communicate using the evolved language. Experimental results demonstrate that EcoLANG reduces token consumption by over 20%, enhancing efficiency without sacrificing simulation accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。