Healthcare Mechanisms from Policy-as-Code Search under Strategic Provider Response

2026-05-28

AI Summary

Existing healthcare AI benchmarks overlook the strategic behavior of care providers, limiting their ability to evaluate mechanisms under equilibrium conditions. This work addresses this gap by formulating hospital mechanism design as a program synthesis problem for language models and introduces Medi-Sim, a multi-agent simulator that integrates strategic channel modeling—encompassing coding, selection, delay, effort, and triage—with incentive scanning and LLM-guided evolutionary search to synthesize interpretable rule-based programs. The resulting hybrid-objective mechanisms effectively eliminate upcoding, reduce patient refusal rates by 50%, and retain most of the revenue achieved by profit-driven baselines. Furthermore, the approach uncovers a “pressure-shifting” phenomenon, offering a novel paradigm for healthcare mechanism design grounded in strategic interaction and automated program synthesis.

Abstract

Healthcare mechanisms are inseparable from the strategic provider response they induce: existing healthcare AI benchmarks hold this response fixed and so cannot evaluate mechanisms by the equilibrium they produce. We recast hospital mechanism design as program synthesis for language models: typed, inspectable rule programs are executed and scored by Medi-Sim, a multi-agent simulator with five strategic provider channels (coding, selection, delay, effort, triage). An incentive sweep recovers classical health-economics findings as adjacent regimes -- up-coding and low-complexity-patient selection under profit pressure, and Goodhart-style drift where measured performance becomes anti-correlated with true outcomes -- and a single audit lever exposes pressure migration: closing the coding channel more than doubles low-complexity selection. LLM-guided evolutionary code search over the same rule-program space then synthesizes an inspectable mixed-objective program that eliminates up-coding, halves rejection, and retains most of the profit-oriented baseline's funds.

Problem

• healthcare mechanisms
• strategic provider response
• mechanism design
• multi-agent simulation
• incentive alignment

Innovation

• program synthesis
• multi-agent simulation
• strategic provider response
• LLM-guided search
• healthcare mechanism design