But How Would AI Agents Run a Town's Economy?
- 类型：arxiv
- 标识：2609.11108
- 链接：http://arxiv.org/abs/2609.11108v1
- 主分类：agent
- 形态：method
- TLDR：We placed 100 memory-equipped large language model (LLM) agents in charge of a closed, money-conserving spatial economy on real Pokhara Lakeside geography (earning wages, running businesses, setting prices) and ran this multi-agent simulation for up to 26 simulated weeks, well past the 1-2 weeks typical of agent-society studies. Across 91 validated runs (2.44M agent decisions, 21.5B tokens), the money stops moving, in a specific and measurable way. A 12x tourist demand shock raises business revenue 4.62x ($p<0.001$), which we decompose exactly into a 1.50x extensive margin (more businesses tra
- 待LLM分类：否
- 标题中文：AI Agent 究竟要如何运行一座城镇的经济？
- TLDR中文：我们将 100 个具备记忆能力的大语言模型（LLM）agent 部署在一个封闭、守恒的空间经济中，基于真实的博卡拉湖滨地理环境（赚取工资、经营企业、设定价格），并将此多 agent 模拟运行最长 26 个模拟周，远超一般 agent 社会研究中典型的 1–2 周。在 91 次经过验证的运行中（244 万次 agent 决策、215 亿 token），货币以特定且可度量的方式停止流动。施加 12 倍的旅游需求冲击可使企业营收提升 4.62 倍（p<0.001），我们将其精确分解为 1.50 倍的扩展边际（更多企业交易）和……
- 来源文件：
- /inbox/tom/_candidates/2026-09-11-agent-rag-longcontext-candidates.json