理论家工具箱:基于智能体的LLM辅助经济理论研究工具
Theorist Toolbox: Tools for Agent Based LLM-assisted economic theory Research
AI总结:
提出一种验证优先的经济理论LLM辅助协议,通过三种可重用方法(单次检查、对抗性证明-验证对、多智能体项目)在等级膨胀的Gans-Kominers特征模型上设计Groves/Pigouvian激励机制的实例验证。
摘要:
实证经济学家继承了一个工具箱:共享软件包、复制档案和流传的指南等。理论家则大多从空白页开始。到2026年,大型语言模型可以生成并检查非平凡的数学,因此机器辅助理论的约束不再是生产而是信任:一个流畅的模型会同样轻易地证明假定理和真定理。我提出一种用于与语言模型进行经济理论的验证优先协议,并将其实例化为三种可重用方法,这些方法在单一轴上有所不同,即工作如何被检查:一次纪律严明的通过、一个对抗性的证明者-验证者对(Claude Opus~4.8提出,OpenAI Codex反驳,作者分类),以及一个带有审阅者门控的结构化多智能体项目。我在一个开放的工作示例上评估该协议:为Gans-Kominers等级膨胀的特征模型设计一个Groves/Pigouvian激励机制;三次运行均未产生严格的直接显示VCG/Clarke机制,这一点由对抗性通过本身确立。证据是一个单一的工作示例,由一位操作者运行一个模型配对,因此接下来是演示而非测量效果。三个现象重复出现。第一,收敛发现:两次运行在相反边际上推导出相同的有效电阻外部性核。第二,对抗性验证是承重的:该对捕捉了其自身的三个虚假声明,并且门控拒绝了一个子目标。第三,润色不等于严谨:看起来最完成的输出是验证最少的。方法论上的收获是,外部验证,而非模型能力,才是设计变量。
英文摘要:
Empirical economists often start their projects with a toolbox. Shared packages, replication archives, and circulated guides shorten the time between and idea and a rough initial draft. Theorists, on the other-hand, largely start from a blank page. By 2026, large language models can a produce and check nontrivial mathematics. The can also hallucinate and write wrong claims very convincingly. The current bottleneck on machine-assisted theory is no longer production but trust: a model will claim to prove a false theorem as readily as a true one. Building on recent attempts in mathematics, I present 3 methods for doing economic theory with a language model. These methods differ on how the work is verified: a single disciplined pass, an adversarial prover-verifier pair (Claude Opus~4.8 proposing, OpenAI Codex refuting), and a structured multi-agent project with a reviewer gate (inspired by the Google co-mathematician architecture). I demonstrate these protocols on one open worked example: designing a Groves/Pigouvian incentive mechanism for the Gans--Kominers eigengrade model of grade inflation. None of the three runs produced a strict direct-revelation VCG/Clarke mechanism (as requested, perhaps due to the non-existence of such mechanism). Three phenomena recur. First, convergent discovery: two runs derive the same effective-resistance externality kernel on opposite margins. Second, adversarial verification is load-bearing: the pair caught three of its own false claims and the gate rejected a sub-goal. Third, polish is not rigor: the most finished-looking output was the least verified. The methodological takeaway is that external verification, not model capability, is the design variable.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。