24 papers
Multi-Turn LLM Conversations under the Least-Recently-Used Policy: Mean-Field Asymptotics and Hit Ratio Approximation
Heyuan Yao, Chutong Gao, Yuan Lyu +2
The major workloads in modern large language model (LLM) serving systems have shifted from single-shot LLM calls to multi-turn conversations, where new responses are generated base…
Refined Thompson Learning for Adaptive Bandits: Power-Efficient Flexibility Scheduling Across Data Centers
Zixi Chen, Yifu Ding, Ruicheng Ao +2
The rapid growth of large-scale AI workloads in data centers has placed increasing pressure on power grids in recent years. Since power systems must continuously balance supply and…
Semiparametric Efficiency in Sequential Experiments: Characterization and Design via Average Propensity
Jiachun Li, David Simchi-Levi
Modern experiments, including evaluations of AI-enabled services and platform interventions, often depart from independent and identically distributed (i.i.d.) sampling because ass…
Service-Induced Congestion in Memory-Constrained LLM Serving
Ruicheng Ao, Jing Dong, Gan Luo +1
In large language model (LLM) serving, each request accumulates persistent graphics processing unit (GPU) memory during service as its key-value cache grows with every generated to…
Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
Jiachun Li, David Simchi-Levi
Adaptive experiments for average treatment effects (ATE) require randomized allocations balancing valid inference with statistical efficiency. The oracle design is a covariate-depe…
Adaptive Inference for Resource-Constrained Dynamic Pricing
Ruicheng Ao, Jiashuo Jiang, David Simchi-Levi
We study dynamic pricing over a finite selling horizon when limited resource capacity determines revenue and the observations available for inference at a prespecified price. Resou…
On the Reliability Limits of LLM-Based Multi-Agent Planning
Ruicheng Ao, Siyang Gao, David Simchi-Levi
This technical note studies the reliability limits of LLM-based multi-agent planning as a delegated decision problem. We model the LLM-based multi-agent architecture as a finite ac…
The Value of Information in Resource-Constrained Pricing
Ruicheng Ao, Jiashuo Jiang, David Simchi-Levi
Firms that price perishable resources -- airline seats, hotel rooms, seasonal inventory -- now routinely use demand predictions, but these predictions vary widely in quality. Under…
Designing Service Systems from Textual Evidence
Ruicheng Ao, Hongyu Chen, Siyang Gao +2
Designing service systems requires selecting among alternative configurations -- choosing the best chatbot variant, the optimal routing policy, or the most effective quality contro…
OptiRepair: Closed-Loop Diagnosis and Repair of Supply Chain Optimization Models with LLM Agents
Ruicheng Ao, David Simchi-Levi, Xinshang Wang
Supply chain optimization models frequently become infeasible because of modeling errors. Diagnosis and repair require scarce OR expertise: analysts must interpret solver diagnosti…
AI-Generated Measurements for Identification and Inference with Missing Data: A Weak Shadow Variable Approach
Hongyu Chen, David Simchi-Levi, Ruoxuan Xiong
Across business and social science applications, outcomes are often missing in ways that depend on the unobserved outcomes themselves. In service systems, for example, whether a cu…
Best Arm Identification with LLM Judges and Limited Human
Ruicheng Ao, Hongyu Chen, Siyang Gao +2
We study fixed-confidence best-arm identification (BAI) where a cheap but potentially biased proxy (e.g., LLM judge) is available for every sample, while an expensive ground-truth…
PPI-SVRG: Unifying Prediction-Powered Inference and Variance Reduction for Semi-Supervised Optimization
Ruicheng Ao, Hongyu Chen, Haoyang Liu +2
We study semi-supervised stochastic optimization when labeled data is scarce but predictions from pre-trained models are available. PPI and SVRG both reduce variance through contro…
ORLoopBench: Solver-in-the-Loop Benchmarks for Self-Correction and Behavioral Rationality in Operations Research
Ruicheng Ao, David Simchi-Levi, Xinshang Wang
Operations Research practitioners debug infeasible models through an iterative process: inspecting Irreducible Infeasible Subsystems ( IIS), identifying constraint conflicts, and r…
Designing Information Delays in Supply Chains
Prem Talwai, Rene Caldentey, Avi Giloni +3
This paper studies how a downstream retailer in a decentralized two-tier supply chain can implicitly transmit demand information to an upstream supplier through the structure of it…
Beyond ATE: Multi-Criteria Design for A/B Testing
Jiachun Li, Kaining Shi, David Simchi-Levi
In the era of large-scale AI deployment and high-stakes clinical trials, adaptive experimentation faces a ``trilemma'' of conflicting objectives: minimizing cumulative regret (welf…
Large Language Models for Supply Chain Decisions
David Simchi-Levi, Konstantina Mellou, Ishai Menache +1
Supply Chain Management requires addressing a variety of complex decision-making challenges, from sourcing strategies to planning and execution. Over the last few decades, advances…
Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints
Ruicheng Ao, Gan Luo, David Simchi-Levi +1
Large language models now serve millions of users daily, with providers incurring costs exceeding $700,000 per day. Each request requires token-by-token inference, making GPU sched…
Learning to Price with Resource Constraints: From Full Information to Machine-Learned Prices
Ruicheng Ao, Jiashuo Jiang, David Simchi-Levi
We study the dynamic pricing problem with knapsack, addressing the challenge of balancing exploration and exploitation under resource constraints. We introduce three algorithms tai…
Nonparametric Regression in Dirichlet Spaces: A Random Obstacle Approach
Prem Talwai, David Simchi-Levi
In this paper, we consider nonparametric estimation over general Dirichlet metric measure spaces. Unlike the more commonly studied reproducing kernel Hilbert space, whose elements…
Prediction-Guided Active Experiments
Ruicheng Ao, Hongyu Chen, David Simchi-Levi
In this work, we introduce a new framework for active experimentation, the Prediction-Guided Active Experiment (PGAE), which leverages predictions from an existing machine learning…
Optimal Adaptive Experimental Design for Estimating Treatment Effect
Jiachun Li, David Simchi-Levi, Yunxiao Zhao
Given n experiment subjects with potentially heterogeneous covariates and two possible treatments, namely active treatment and control, this paper addresses the fundamental questio…
Two-stage Online Reusable Resource Allocation: Reservation, Overbooking and Confirmation Call
Ruicheng Ao, Hengyu Fu, David Simchi-levi
We study a two-stage online reusable resource allocation problem over T days involving advance reservations and walk-ins. Each day begins with a reservation stage (Stage I), where…
Privacy Preserving Adaptive Experiment Design
Jiachun Li, Kaining Shi, David Simchi-Levi
Adaptive experiment is widely adopted to estimate conditional average treatment effect (CATE) in clinical trials and many other scenarios. While the primary goal in experiment is t…