GovSim-SelfGovern：LLM 智能体自我治理实验

1. 12:00
   arXiv · Multiagent Systems

   GovSim-SelfGovern：LLM 智能体能否在崩溃中自我治理并自我牺牲？

   研究构建 GovSim-SelfGovern，让 LLM 智能体用可执行 Python 立法、沙箱测试并投票。资源丰富时自治将社区无人饿死的存活率从 52.5% 提升到 75.0%；资源不足时治理无法拯救公共资源，因为智能体常起草驱逐法却投票否决。

Current heat 9·Comparable peak 10（Oct 9）·Comparable change over 24 hours –

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.