Paper
Separating Diagnosis from Control: Auditable Policy Adaptation in Agent-Based Simulations with LLM-Based Diagnostics
Authors
Shaoxin Zhong, Yuchen Su, Michael Witbrock
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.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.22904v1</id>\n <title>Separating Diagnosis from Control: Auditable Policy Adaptation in Agent-Based Simulations with LLM-Based Diagnostics</title>\n <updated>2026-03-24T07:52:10Z</updated>\n <link href='https://arxiv.org/abs/2603.22904v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.22904v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>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.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n <published>2026-03-24T07:52:10Z</published>\n <arxiv:comment>This paper has been accepted at AAMAS 2026 Workshop MABS</arxiv:comment>\n <arxiv:primary_category term='cs.AI'/>\n <author>\n <name>Shaoxin Zhong</name>\n </author>\n <author>\n <name>Yuchen Su</name>\n </author>\n <author>\n <name>Michael Witbrock</name>\n </author>\n </entry>"
}