思考的代价：测试时推理在LLM交易中是否值得？

中文摘要 AI 辅助

虽然大型语言模型（LLMs）中的推理时计算承诺带来更好的决策，但其更高的计算成本可能不会带来更好的经济结果。然而，推理控制很少被作为经济干预措施来评估，即模型输出的变化必须在考虑交易成本后转化为更优的投资组合。我们对来自DeepSeek、GPT和Gemini系列的代表性LLM进行了受控研究。我们在每个形成日期保持可用信息、提示、输出格式和投资组合构建不变，同时改变推理努力程度。我们的评估涵盖了美国股票一整年的数据，在三种输入条件下进行：数值型、可识别新闻和掩码新闻。评估包括超过80万次资产预测和重复的模型生成。在所有三个模型系列中，额外的推理并未带来净投资组合收益的可靠改善。对于DeepSeek，我们考察了从无推理到最大推理的完整进展，其性能是非单调的。重复生成也产生不稳定的处理效应和投资组合选择，即使总体得分保持相似。这些发现表明，额外的推理可以改变金融决策，但并不能可靠地提高其经济价值，这促使在部署前对每项任务进行验证。

英文摘要

While inference-time reasoning in large language models (LLMs) promises better decision making, its higher computational cost may not yield better economic outcomes. Yet reasoning controls are rarely evaluated as economic interventions, where changes in model outputs must translate into better portfolios after trading costs. We conduct a controlled study of representative LLMs from the DeepSeek, GPT, and Gemini families. We vary reasoning effort while holding information available at each formation date, prompts, output formats, and portfolio construction fixed. Our evaluation covers a full year of U.S. equities under three input conditions: numerical, identifiable news, and masked news. It includes more than 800,000 asset predictions and repeated model generations. Across all three model families, additional reasoning does not produce a reliable improvement in net portfolio returns. For DeepSeek, where we examine the full progression from no reasoning to maximum reasoning, performance is nonmonotonic. Repeated generations also produce unstable treatment effects and portfolio selections, even when overall scores remain similar. These findings show that additional reasoning can change financial decisions without reliably improving their economic value, motivating validation for each task before deployment.

发表机构

• New Jersey Institute of Technology（新泽西理工学院）

机构由 AI 辅助整理，请以论文原文为准。