研究显示 LLM 代理管理城镇经济时资金流动会停滞
What happens if you agents to run a town's economy? This super interesting paper provides some insi...
朋友，有个挺有意思的研究，用100个LLM代理模拟管理一个城镇经济，结果发现钱都不流动了，挺反直觉的，值得看看。
这篇论文将100个LLM代理置于模拟的波卡拉湖畔城镇经济中，运行26周后发现资金流动停止。在91次运行和244万次决策中，12倍的游客冲击使商业收入增长4.62倍，但工资仅增长1.03倍，仅0.3%的3,981个菜单项目被重新定价。现金转移模式相同，96.7%的资金在311步后仍未被使用。有趣的是，更换底层LLM会改变所有测量结果，而删除代理记忆则不会。结果在通常的1-2周时间范围内会误导判断，财富排名在2周时看似冻结，直到第12周才开始移动。
What happens if you agents to run a town's economy? This super interesting paper provides some insi...
What happens if you agents to run a town's economy? This super interesting paper provides some insights: They put 100 LLM agents in charge of a town economy for 26 simulated weeks, and they find that money stops moving. The agents earn wages, run businesses and set prices on real Pokhara Lakeside geography, across 91 runs and 2.44M decisions. A 12x tourist shock raises business revenue 4.62x. Wages move 1.03x, and only 0.3% of 3,981 menu items are ever repriced. A cash transfer shows the same pattern. 96.7% of it is still unspent 311 steps later. Here is the interesting part for anyone building agent simulations. Swapping the underlying LLM changed every outcome they measured. Deleting the agents' memory changed none of them detectably. Results at the usual 1 to 2 week horizon also mislead. Wealth rankings look frozen at 2 weeks and only start to move by week 12. Paper: arxiv.org/abs/2609.11108 Chat with Paper: academy.dair.ai/papers/but-how… 💬 9 🔄 1 ❤️ 26 👀 3330 📊 13 ⚡