简单模拟市场中LLM的演化实验

AI 摘要

研究者构建了一个由20个LLM智能体组成的模拟市场，智能体仅系统提示不同，破产者被成功者提示的变异副本替换。在奖励准确率的市场中，智能体准确率达94%但token消耗高；在按token计费的市场中，准确率骤降至10%且token消耗低，显示出准确率与token使用之间的相关性状选择。该实验为AI系统可能在最小条件下演化出非激励性有害特征提供了具体实证。

正文节选

LLM Evolution in a Simple Simulated Market Abstract Arguments that AI systems will evolve in harmful ways are largely made in the abstract. We provide a concrete empirical example. We simulate simple markets consisting of populations of twenty Large Language Model agents tasked with solving arithmetic problems. Agents differ only in their system prompt; those that go bankrupt are removed and replaced by mutated copies of the prompts of successful agents. Two market conditions select for opposite

发布时间：2026-10-20 12:00

抓取时间：2026-10-20 12:48

来源机构：arXiv