# Separating Diagnosis from Control: Auditable Policy Adaptation in Agent-Based Simulations with LLM-Based Diagnostics

Source: [Separating Diagnosis from Control: Auditable Policy Adaptation in Agent-Based Simulations with LLM-Based Diagnostics](<https://www.sota2.com/research/paper/69c36c3e0636e5bf4afc6664>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-26T05:00:04.122Z

Authors: Shaoxin Zhong, Yuchen Su, Michael Witbrock

Published: 2026-03-24T07:52:10.000Z

## Abstract

Mitigating elderly loneliness requires policy interventions that achieve both adaptability and auditability. Existing methods struggle to reconcile these objectives: traditional agent-based models suffer from static rigidity, while direct large language model (LLM) controllers lack essential traceability. This work proposes a three-layer framework that separates diagnosis from control to achieve both properties simultaneously. LLMs operate strictly as diagnostic instruments that assess population state and generate structured risk evaluations, while deterministic formulas with explicit bounds translate these assessments into traceable parameter updates. This separation ensures that every policy decision can be attributed to inspectable rules while maintaining adaptive response to emergent needs. We validate the framework through systematic ablation across five experimental conditions in elderly care simulation. Results demonstrate that explicit control rules outperform end-to-end black-box LLM approaches by 11.7\\% while preserving full auditability, confirming that transparency need not compromise adaptive performance.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Loneliness Mitigation on Agent-based Loneliness Simulation seeds (holdout)](<https://www.sota2.com/research/sota/loneliness-mitigation-on-agent-based-loneliness-simulation-seeds-holdout.md>): Loneliness Mitigation; Agent-based Loneliness Simulation seeds (holdout); Mean Loneliness: 0.607.

- [Loneliness Simulation on Loneliness Simulation 200 days, N=30](<https://www.sota2.com/research/sota/loneliness-simulation-on-loneliness-simulation-200-days-n-30.md>): Loneliness Simulation; Loneliness Simulation 200 days, N=30; Mean Difference: -0.081.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.22904>)

[PDF](<https://arxiv.org/pdf/2603.22904.pdf>)