Stable Menus of Public Goods: AI-Enabled Progress
2026-06-15 • Computer Science and Game Theory
Computer Science and Game TheoryArtificial IntelligenceComputers and Society
AI summaryⓘ
The authors tested different ways to use AI language models (LLMs) to help with an economics problem about public goods. They found that giving the AI some human ideas in the prompt made its suggestions better, and letting the AI interact in multiple steps helped when it took bold actions. When comparing the AI to a first-year PhD student, they discovered that the AI was a bit less effective. Overall, the authors suggest ways to improve collaboration between humans and AI in economic research.
AI language modelseconomic computer sciencepublic goodsprompt engineeringmulti-turn interactionhuman intuitionPhD student comparisonworkflow evaluationstable menuscollaborative research
Authors
Sara Fish
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 Regarding the third question, using an unpublished manuscript written by the paper's senior authors prior to collaborating with the first-year PhD student, we compare the effectiveness of the LLM with that of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.