发表机构
Karela Technologies Inc.（卡雷拉科技有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过多智能体模拟发现，LLM智能体经济中货币流动在工资和定价环节停滞，财富分配随时间缓慢变化，且模型选择和内存对结果影响不同。
AI 中文摘要
我们将100个配备内存的大型语言模型（LLM）智能体置于一个基于真实博卡拉湖畔地理位置的封闭、货币守恒的空间经济中（负责赚取工资、经营企业、设定价格），并运行该多智能体模拟长达26个模拟周，远超智能体社会研究中典型的1-2周。在91次验证运行中（244万次智能体决策，215亿个令牌），货币以一种特定且可测量的方式停止流动。12倍的旅游需求冲击使企业收入增加4.62倍（$p<0.001$），我们将其精确分解为1.50倍的广延边际（更多企业进行交易）和3.07倍的集约边际（每个企业收入增加）。货币传导在此停止。工资变动1.03倍（$p=0.42$）；3,981个菜单项中仅有0.3%曾被重新定价（$p=0.47$）。一次随机现金转移（向100个智能体中的20个发放5,000尼泊尔卢比）从相反方向显示了相同模式：311个脉冲后仍有96.7%被持有，边际消费倾向通过两种独立测量均为3-4%，与零无显著差异。因此，在该文献使用的时间范围内，财富分配几乎冻结（2个模拟周内$\ ho=0.964$），但并非完全冻结。$\ ho$在12周时降至0.832，在26周时降至0.752，这种对时间范围的依赖性在短期研究中无法观察到。匹配的消融实验显示了哪个旋钮真正重要。更换底层LLM会改变我们测量的每个结果（$p=0.0039$）；删除智能体的内存则不会对任何结果产生可检测的影响。一个纯社交工具在两种模型家族中失败率为94-97%，而经济工具的成功率约为96%，且没有可测量的行为偏移。每个关键数字都经过两次验证：一次由实时验证器进行，另一次由离线重新计算进行，该计算将每个智能体的财富与其自身的签名交易历史进行核对，我们发布完整的运行语料库以供重新分析。
英文摘要
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 trading) and a 3.07x intensive margin (more revenue each). Monetary transmission stops there. Wages move 1.03x ($p=0.42$); 0.3% of 3,981 menu items are ever repriced ($p=0.47$). A randomized cash transfer (NPR 5,000 to 20 of 100 agents) shows the same pattern from the opposite direction: 96.7% is still held 311 pulses later, marginal propensity to consume 3-4% by two independent measures, indistinguishable from zero. The wealth distribution is consequently near-frozen at the horizon this literature uses ($ρ=0.964$ over 2 simulated weeks), but not frozen. $ρ$ falls to 0.832 at 12 weeks and 0.752 at 26, a horizon-dependence no short study can see. Matched ablations show which knob actually matters. Swapping the backing LLM moves every outcome we measure ($p=0.0039$); deleting agents' memory moves none of them detectably. A purely social tool fails 94-97% of the time across two model families, compared with ~96% success on economic tools, with no measurable shift away from it. Every headline number is verified twice, by a live validator and by an offline recomputation that reconciles each agent's wealth against its own signed transaction history, and we release the full run corpus for reanalysis.
Comments8 pages, 7 figures, 6 tables. Dataset and analysis code: https://huggingface.co/datasets/sajalregmi4/agent-town-economy
