Papers

Sorry I do not have many publications. Please push me when you see this message.

Selected Preprints

• Service-Induced Congestion in Memory-Constrained LLM Serving [SSRN]
  Job Market Paper
  R. Ao, J. Dong, G. Luo, D. Simchi-Levi, under review at Operations Research, available at SSRN, finalist in the 2026 INFORMS Service Science Section Best Student Paper Award and the 2026 INFORMS Quality, Statistics and Reliability (QSR) Section Best Student Paper Competition

• Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints [SSRN]
  R. Ao, G. Luo, D. Simchi-Levi, X. Wang, major revision at Operations Research, finalist in Applied Probability 2025 Student Paper Award and POMS CSOM 2026 Best Student Paper Competition

• OptiRepair: Closed-Loop Diagnosis and Repair of Supply Chain Optimization Models with LLM Agents [arXiv]
  R. Ao, D. Simchi-Levi, X. Wang, major revision at Manufacturing & Service Operations Management, arXiv preprint arXiv:2602.19439

• Proactive Transfer Admission Control for Emergency Departments [PDF]
  R. Ao, J. Dong, A. Liu, M. Copenhaver, major revision at Manufacturing & Service Operations Management

• Prediction-Guided Active Experiments [SSRN]
  R. Ao, H. Chen, D. Simchi-Levi, minor revision at Management Science, available at SSRN

• Online Resource Allocation with Average Budget Constraints [arXiv]
  R. Ao, H. Chen, D. Simchi-Levi, F.Zhu, major revision at Operations Research, finalist in Revenue Management and Pricing 2024 Jeff McGill Student Paper Award

Conference Proceedings

• Solver-in-the-Loop: MDP-Based Benchmarks for Self-Correction and Behavioral Rationality in Operations Research [arXiv]
  R. Ao, D. Simchi-Levi, X. Wang, International Conference on Machine Learning (ICML), 2026

• PILOT-Bench: Probabilistic Interaction for LLM Operations in Tool-driven Scenarios
  R. Ao, Z. Min, T. Zhu, X. Wang, W. Yin, International Conference on Learning Representations (ICLR), 2026

• Learning to Price with Resource Constraints: From Full Information to Machine-Learned Prices [arXiv]
  R. Ao, J. Jiang, D. Simchi-Levi, Conference on Neural Information Processing Systems (Neurips), 2025

• Asynchronous Gradient Play in Zero-Sum Multi-agent Games [arXiv]
  R. Ao, S. Cen, and Y. Chi, International Conference on Learning Representations (ICLR), 2023.

Journals

• A Monte Carlo Policy Gradient Method with Local Search for Binary Optimization [arXiv]
  C. Chen, R. Chen, T. Li, R. Ao, Z. Wen, Mathematical Programming, 1-57

• Riemannian natural gradient methods [arXiv]
  J. Hu, R. Ao, AMC. So, M Yang, Z. Wen, SIAM Journal on Scientific Computing 46 (1), A204-A231