Optimizing Service Operations via LLM-Powered Multi-Agent Simulation

• URL: http://arxiv.org/abs/2604.04383v1
• Date: Mon, 06 Apr 2026 03:14:33 GMT
• Title: Optimizing Service Operations via LLM-Powered Multi-Agent Simulation
• Abstract summary: We introduce an LLM-powered multi-agent simulation framework for optimizing service operations.<n>We pose the problem as optimization with decision-dependent uncertainty.<n>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.
• Score: 1.2997358113120427
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• LLMDE: A Large Language Model-Driven Differential Evolution Algorithm for Portfolio Optimization [23.197379864220295]
  This study proposes a Large Language Model-Driven Differential Evolution (LLMDE) algorithm to reduce the reliance on handcrafted hyper parameter design.<n>We evaluate the performance of LLMDE on the CEC2022 benchmark suite, comparing it with standard DE and representative metaheuristics.<n> Experimental results demonstrate that LLMDE achieves competitive performance on the benchmark suite while continuously generating high-quality solutions.
  arXiv  Detail & Related papers  (2026-09-15T08:39:44Z)
• Execution-Verified Reinforcement Learning for Optimization Modeling [49.171122807323634]
  Execution-verified learning framework treats a mathematical programming solver as a deterministic, interactive verifier.<n>Experiments on NL4OPT, MAMO, IndustryOR, and OptiBench across Gurobi, OR-Tools, and COPT show that EVOM matches or outperforms process-supervised SFT.
  arXiv  Detail & Related papers  (2026-04-01T03:39:11Z)
• Human-LLM Collaborative Feature Engineering for Tabular Data [22.2647889885109]
  Large language models (LLMs) are increasingly used to automate feature engineering in tabular learning.<n>Current approaches typically assign the LLM as a black-box, responsible for both proposing and selecting operations.<n>In this paper, we propose a human-LLM collaborative feature engineering framework.
  arXiv  Detail & Related papers  (2026-01-28T21:33:42Z)
• SOCRATES: Simulation Optimization with Correlated Replicas and Adaptive Trajectory Evaluations [25.18297372152296]
  SOCRATES is a novel two-stage procedure that automates the design of tailored SO algorithms.<n>An ensemble of digital replicas of the real system is used as a testbed to evaluate a set of baseline SO algorithms.<n>An LLM acts as a meta-optimizer, analyzing the performance trajectories of these algorithms to iteratively revise and compose a final, hybrid optimization schedule.
  arXiv  Detail & Related papers  (2025-11-01T19:57:38Z)
• LLM4CMO: Large Language Model-aided Algorithm Design for Constrained Multiobjective Optimization [54.35609820607923]
  Large language models (LLMs) offer new opportunities for assisting with algorithm design.<n>We propose LLM4CMO, a novel CMOEA based on a dual-population, two-stage framework.<n>LLMs can serve as efficient co-designers in the development of complex evolutionary optimization algorithms.
  arXiv  Detail & Related papers  (2025-08-16T02:00:57Z)
• Large Language Model-Driven Surrogate-Assisted Evolutionary Algorithm for Expensive Optimization [22.024630467760264]
  Surrogate-assisted evolutionary algorithms (SAEAs) are a key tool for addressing costly optimization tasks.<n>This paper proposes LLM-SAEA, a novel approach that integrates large language models (LLMs) to configure both surrogate models and infill sampling criteria online.
  arXiv  Detail & Related papers  (2025-06-20T13:44:21Z)
• Efficient Model Selection for Time Series Forecasting via LLMs [52.31535714387368]
  We propose to leverage Large Language Models (LLMs) as a lightweight alternative for model selection.<n>Our method eliminates the need for explicit performance matrices by utilizing the inherent knowledge and reasoning capabilities of LLMs.
  arXiv  Detail & Related papers  (2025-04-02T20:33:27Z)
• Scaling Autonomous Agents via Automatic Reward Modeling And Planning [52.39395405893965]
  Large language models (LLMs) have demonstrated remarkable capabilities across a range of tasks.<n>However, they still struggle with problems requiring multi-step decision-making and environmental feedback.<n>We propose a framework that can automatically learn a reward model from the environment without human annotations.
  arXiv  Detail & Related papers  (2025-02-17T18:49:25Z)
• Can Large Language Models Be Trusted as Evolutionary Optimizers for Network-Structured Combinatorial Problems? [8.431866560904753]
  Large Language Models (LLMs) have shown strong capabilities in language understanding and reasoning across diverse domains.<n>In this work, we propose a systematic framework to evaluate the capability of LLMs to engage with problem structures.<n>We adopt the commonly used evolutionary (EVO) and propose a comprehensive evaluation framework that rigorously assesses the output fidelity of LLM-based operators.
  arXiv  Detail & Related papers  (2025-01-25T05:19:19Z)
• EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration [76.66831821738927]
  Large language models (LLMs) remain under-studied in scenarios requiring optimal decision-making under uncertainty.<n>We measure LLMs' (in)ability to make optimal decisions in bandits, a state-less reinforcement learning setting relevant to many applications.<n>Motivated by the existence of optimal exploration algorithms, we propose efficient ways to integrate this algorithmic knowledge into LLMs.
  arXiv  Detail & Related papers  (2024-10-08T17:54:03Z)
• FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models [50.331708897857574]
  We introduce FactorLLM, a novel approach that decomposes well-trained dense FFNs into sparse sub-networks without requiring any further modifications. FactorLLM achieves comparable performance to the source model securing up to 85% model performance while obtaining over a 30% increase in inference speed.
  arXiv  Detail & Related papers  (2024-08-15T16:45:16Z)
• From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning [52.257422715393574]
  We introduce a self-guided methodology for Large Language Models (LLMs) to autonomously discern and select cherry samples from open-source datasets. Our key innovation, the Instruction-Following Difficulty (IFD) metric, emerges as a pivotal metric to identify discrepancies between a model's expected responses and its intrinsic generation capability.
  arXiv  Detail & Related papers  (2023-08-23T09:45:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.