Research

Research Field

• Macroeconomics, Optimal Policy, AI, Large Language Model, Agent-based Model, Development

Job Market Paper

Macro-Monopoly Dynamics: How Large Firms Shape Aggregate Outcomes

• Authors: Yuzhi Hao and Danyang Xie
• Presentation: Xiamen University EFG 2025
• Click here for PDF

Abstract: This paper develops a dynamic general equilibrium model with a macro-monopoly, a firm large enough to affect aggregates, to explore how its profit-maximizing decisions under commitment shape macroeconomic dynamics. Unlike monopolistic competitors, a macro-monopoly internalizes its aggregate influence through five channels: price, wage, interest rate, capital and implementability channels. Mechanism decomposition shows that price and wage channels are the dominant sources of distortion, while capital and implementability channels partially offset them. Under baseline calibration, these channels reduce steady-state output by 5.7% relative to the competitive benchmark, reaching 26.5% under configurations of high market power. We contrast two profit valuation approaches: consumption-based (discounting via the stochastic discount factor) and utility-based (weighting by contemporaneous marginal utility). Consumption-based valuation exhibits ``initial-period dependence”: raising period-0 consumption lowers initial marginal utility, reducing the discount rate for all future profits and increasing their present value. This generates a novel source of time inconsistency, generating deviations far larger than those from classical time inconsistency alone while reoptimizing.

Publication

A Multi-LLM-Agent-Based Framework for Economic and Public Policy Analysis

• Authors: Yuzhi Hao and Danyang Xie
• Journal: China Journal of Econometrics, 2025, 5(3): 615-630
• Click here for PDF

Abstract: This paper pioneers a novel approach to economic and public policy analysis by leveraging multiple large language models (LLMs) as heterogeneous artificial economic agents. We first evaluate five LLMs’economic decision-making capabilities in solving two-period consumption allocation problems under two distinct scenarios: With explicit utility functions and based on intuitive reasoning. While previous research has often simulated heterogeneity by solely varying prompts, our approach harnesses the inherent variations in analytical capabilities across different LLMs to model agents with diverse cognitive traits. Building on these findings, we construct a multi-LLM-agent-based (MLAB) framework by mapping these LLMs to specific educational groups and corresponding income brackets. Using interest income taxation as a case study, we demonstrate how the MLAB framework can simulate policy impacts across heterogeneous agents, offering a promising new direction for economic and public policy analysis by leveraging LLMs’ human-like reasoning capabilities and computational power.

Working Papers

Rewiring Opportunity: How Improved Internet Infrastructure Reduces Intra-City Income Inequality in China

• Authors: Yanlin Wan, Xu Zhang, Yuzhi Hao, Aoqing Lyu, Masaru Yarime
• Status: Submitted
• Draft available upon request

Abstract: This study investigates the impact of enhanced internet infrastructure on intra-city income inequality in China. Employing a staggered difference-in-differences methodology, our analysis reveals that the Broadband China Strategic Program from 2014 to 2016 resulted in a notable reduction in the income Gini coefficients of the demonstration cities, with substantial income gains among low- and middle-income households. We argue that the improved internet infrastructure mitigated income inequality mainly by creating new employment opportunities in the service sector for low-skilled workers. Our findings underscore the pivotal role of technology in fostering inclusive economic growth and provide valuable insights for policymakers seeking to harness investments in internet infrastructure and improve social equality in developing countries.

Bridging the Treatment Gap in Mental Healthcare: Evidence from China

• Authors: Yanlin Wan, Yuzhi Hao, Xu Zhang
• Draft available upon request

Abstract: We evaluate a large-scale, nationwide policy in China that aimed to improve population mental well-being by simultaneously expanding the supply of mental healthcare resources and reducing public stigma. Using a difference-in-differences design, we find that the policy significantly improved mental health outcomes on average; however, the benefits were concentrated among individuals with better mental health. We then provide descriptive evidence of an increase in mental healthcare adoption following this policy. To investigate the channels driving this enhanced adoption, we conducted a discrete choice experiment (DCE) focusing on the costs of care: monetary costs (price), time costs (commuting time), and psychological costs (stigma). The DCE reveals crucial heterogeneity: individuals with better mental health are more responsive to reductions in time costs but less sensitive to monetary costs. These findings suggest the policy’s average success was driven by the reduced time costs for these with better mental health conditions. We conclude that effective mental health interventions require a broad approach to improve general access, coupled with targeted efforts to remove financial barriers and provide privacy-sensitive support for those with severe conditions.

Selected Works in Progress

Evaluating Large Language Models as Households: Evidence from China Family Panel Studies

• Authors: Yuzhi Hao and Danyang Xie

Summary: Evaluates LLMs’ ability to replicate household expenditure decisions using a role-playing framework with CFPS data, comparing model predictions against actual survey responses through distributional analysis and household-level accuracy metrics, with implications for calibrating LLM-based agents in macro models.