# Optimizing Service Operations via LLM-Powered Multi-Agent Simulation

arXiv: https://arxiv.org/abs/2604.04383 · HTML: https://mlsanity.com/paper/2604.04383/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 6 of its 62 references that are in the map.
- First posted on arXiv 6 Apr 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 6 of 6)

- [What Is Your AI Agent Buying? Evaluation, Biases, Model Dependence, & Emerging Implications for Agentic E-Commerce](https://mlsanity.com/paper/2508.02630/) (2025)
- [Online Scheduling for LLM Inference with KV Cache Constraints](https://mlsanity.com/paper/2502.07115/) (2025)
- [Throughput-Optimal Scheduling Algorithms for LLM Inference and AI Agents](https://mlsanity.com/paper/2504.07347/) (2025)
- [Auto-Formulating Dynamic Programming Problems with Large Language Models](https://mlsanity.com/paper/2507.11737/) (2025)
- [Robust and Adaptive Optimization under a Large Language Model Lens](https://mlsanity.com/paper/2501.00568/) (2024)
- [Simulating and Experimenting with Social Media Mobilization Using LLM Agents](https://mlsanity.com/paper/2510.26494/) (2025)

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

- [LLM-Powered Virtual Population for Demand Simulation and Pricing](https://mlsanity.com/paper/2606.16183/) (2026)

## Abstract (arXiv)

Service system performance depends on how participants respond to design choices, but modeling these responses is hard due to the complexity of human behavior. We introduce an LLM-powered multi-agent simulation (LLM-MAS) framework for optimizing service operations. We pose the problem as stochastic optimization with decision-dependent uncertainty: design choices are embedded in prompts and shape the distribution of outcomes from interacting LLM-powered agents. By embedding key numerical information in prompts and extracting it from LLM-generated text, we model this uncertainty as a controlled Markov chain. We develop an on-trajectory learning algorithm that, on a single simulation run, simultaneously constructs zeroth-order gradient estimates and updates design parameters to optimize steady-state performance. We also incorporate variance reduction techniques. In a sustainable supply chain application, our method outperforms benchmarks, including blackbox optimization and using LLMs as numerical solvers or as role-playing system designers. A case study on optimal contest design with real behavioral data shows that LLM-MAS is both as a cost-effective evaluator of known designs and an exploratory tool that can uncover strong designs overlooked by traditional approaches.