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

arXiv: https://arxiv.org/abs/2603.22904 · HTML: https://mlsanity.com/paper/2603.22904/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 9 of its 22 references that are in the map.
- First posted on arXiv 24 Mar 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 9 of 9)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives](https://mlsanity.com/paper/2312.11970/) (2023)
- [Explainability in Deep Reinforcement Learning](https://mlsanity.com/paper/2008.06693/) (2020)
- [Promptable Closed-loop Traffic Simulation](https://mlsanity.com/paper/2409.05863/) (2024)
- [Surrogate Modeling and Control of Medical Digital Twins](https://mlsanity.com/paper/2402.05750/) (2024)
- [Casevo: A Cognitive Agents and Social Evolution Simulator](https://mlsanity.com/paper/2412.19498/) (2024)
- [G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration](https://mlsanity.com/paper/2506.09272/) (2025)
- [Simulation Agent: A Framework for Integrating Simulation and Large Language Models for Enhanced Decision-Making](https://mlsanity.com/paper/2505.13761/) (2025)
- [Coordinated Pandemic Control with Large Language Model Agents as Policymaking Assistants](https://mlsanity.com/paper/2601.09264/) (2026)

## Built on by (most cited first, 1 of 1)

- [From Checker to Forecaster: Code-Owned Evaluation of Model-Generated Strategic Routes Under Delayed Ground Truth](https://mlsanity.com/paper/2607.10972/) (2026)

## Abstract (arXiv)

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.