为何更优模型会创造更具风险的系统：来自金融市场中大型语言模型（LLM）智能体的证据
Why Better Models Can Create Riskier Systems: Evidence from LLM Agents in Financial Markets
- Massachusetts Institute of Technology（麻省理工学院）
- Harvard Kennedy School（哈佛肯尼迪学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究以金融市场LLM智能体为对象，发现提升单个LLM能力可能增强其行为关联性，在特定情况下会增加系统风险，揭示了能力悖论，为相关系统设计提供了新视角。
AI中文摘要：
大型语言模型（LLM）正被大规模部署于金融市场、内容审核、招聘等关键现实系统中。本文表明，提升单个模型的能力可能会降低而非改善系统层面的结果。我们假设，共享训练与架构会使更强大的LLMs表现出更相似的行为，产生无法通过多样化消除的关联行动。我们开发了一个通用框架，展示这种关联如何形成不可多样化的风险底线，并使用具有不同通用能力的LLM交易者的基于智能体的模拟，在金融市场中验证其预测。我们发现：（1）前沿LLMs表现出显著的关联行为，且该行为随能力提升而增强；（2）当它们的共享推理准确时，增加智能体参与度会降低市场层面的风险；（3）当智能体处于共同的错误信息环境中时，相同的关联行为会成为负担。这些结果共同揭示了一个能力悖论：提升单个模型的能力不一定会产生更好的系统层面结果。这种动态是否会在其他领域出现是一个开放的实证问题。
英文摘要：
Large language models (LLMs) are being deployed at scale in consequential real-world systems, from financial markets to content moderation to hiring. We show that improving individual model capability can degrade rather than improve system-level outcomes. We hypothesize that shared training and architectures can lead more capable LLMs to behave more similarly, creating correlated actions that do not diversify away. We develop a general framework showing how this correlation creates a non-diversifiable risk floor and test its predictions in financial markets using an agent-based simulation with LLM traders of varying general-purpose capability. We find that: (1) frontier LLMs exhibit significantly correlated behavior that increases with capability; (2) when their shared reasoning is accurate, increasing agent participation reduces market-level risk; and (3) when agents share a common misinformation environment, the same correlated behavior becomes a liability. Together, these results identify a capability paradox: improving individual models does not necessarily produce better system-level outcomes. Whether the same dynamics arise in other domains is an open empirical question.
