PulseAugur
中
实时 12:46:46
English(EN) 100 LLM Agents Running a Town Economy for 26 Weeks: What Breaks When Agents Set Prices and Earn Wages

100个大语言模型代理模拟26周城镇经济，揭示货币停滞

作者 PulseAugur 编辑部 · [1 个来源] ·

最近的一项模拟将100个大语言模型代理置于一个封闭的经济模型中进行了26个模拟周，使用了真实的地理信息和代理记忆。代理的任务是自主赚取工资、经营企业和设定价格。在数百万次决策中，模拟显示货币交易显著放缓，尽管存在巨大的需求冲击，工资和价格在很大程度上保持不变。这种延长的模拟时长暴露了在短期代理实验中不明显的经济协调和状态管理失败。 AI

影响 揭示了多代理大语言模型系统中潜在的长期经济协调失败。

排序理由 详细介绍新颖模拟方法学及其发现的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 dev.to — LLM tag 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

100个大语言模型代理模拟26周城镇经济，揭示货币停滞

本文如何被排名

Signal score
23 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
详细介绍新颖模拟方法学及其发现的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. dev.to — LLM tag TIER_1 English(EN) · mech.app ·

    100个大型语言模型代理运行城镇经济26周：当代理设定价格和赚取工资时，什么会崩溃

    <p>A team placed 100 memory-equipped LLM agents in a closed economy simulation on real Pokhara Lakeside geography and ran it for 26 simulated weeks. The agents earned wages, ran businesses, and set prices autonomously. Across 91 validated runs (2.44M agent decisions, 21.5B tokens…

相关实体

相关话题