Stable Menus of Public Goods: AI-Enabled Progress

2026-06-15

AI Summary

This study explores effective workflows for integrating artificial intelligence into computational economics research, focusing on the open problem of stable menus of public goods. The authors propose a conversational AI research protocol that combines human intuition–informed prompting with multi-round ambitious reasoning steps. Through controlled experiments, they systematically compare the research output quality of large language models (LLMs) and first-year PhD students on theoretical economics problems. Results indicate that prompts enriched with human intuition significantly enhance LLMs’ “research taste,” while iterative interaction more effectively elicits ambitious reasoning. Nevertheless, current LLMs still underperform novice human researchers in overall research efficacy. This work presents the first structured comparison between LLMs and human researchers in theoretical economics and offers a reproducible workflow paradigm for AI-assisted scientific inquiry.

Abstract

Using an open problem from the EC 2025 paper "Stable Menus of Public Goods" as a testbed, we conduct experiments to understand the effectiveness of different AI-for-EconCS research workflows. Specifically, we study three questions: Does providing human intuition in the prompt help? Does automated multi-turn interaction help? And, does an LLM outperform a first-year PhD student? Regarding the first two questions, we provide evidence for the following workflow suggestions: (1) prompting with human intuition can encourage the LLM to have better "taste", (2) multi-turn workflows help when the pipeline encourages "ambitious" steps. Regarding the third question, using an unpublished manuscript written by the paper's senior authors prior to collaborating with the first-year PhD student, we compare the effectiveness of the LLM with that of the first-year PhD student, and find that the LLM is slightly less effective.

Problem

• Stable Menus
• Public Goods
• AI-for-EconCS
• LLM
• Research Workflow

Innovation

• AI-for-EconCS
• large language models
• public goods
• research workflows
• human-AI collaboration