Sirui Li

Sirui Li

Senior Researcher at Microsoft Research

About Me

I’m a Senior Researcher in the Machine Learning and Optimization (MLO) group at Microsoft Research, where my research explores the intersection of large language models and optimization. I completed my PhD in Social and Engineering Systems (SES) and Statistics at Massachusetts Institute of Technology (MIT), advised by Prof. Cathy Wu. I was affiliated with MIT Laboratory for Information & Decision Systems (LIDS), Institute of Data, Systems and Society (IDSS), and MIT Statistics & Data Science Center (IDPS). I was fortunate to be supported by the Amazon Robotics Fellowship and the Michael Hammer Fellowship. During my PhD, I’ve spent time at Microsoft Research, Amazon AWS and MathWorks as an intern. Prior to MIT, I received my bachelor’s degrees in Computer Science and Mathematics from Washington University in St. Louis in 2019.

My research interest broadly lies in the intersection between machine learning, operations research, and transportation. I have developed learning-guided algorithms to speed up combinatorial optimization solvers for efficient large-scale optimization. I am also interested in control theory analysis and reinforcement learning for mixed-autonomy transportation systems.

Articles in Review

  • Multi-residual Mixture of Experts Learning for Cooperative Control in Multi-vehicle Systems
    Vindula Jayawardana, Sirui Li, Yashar Farid, Cathy Wu

Publications

Sort By: Date | Topic. Please see Google Scholar for the full list of publications.

  • Multi-Turn RL Makes Small Language Model Competitive for Optimization Modeling
    Xinzhi Zhang*, Zeyi Chen, Humishka Zope, Hugo Barbalho, Konstantina Mellou, Marco Molinaro, Janardhan Kulkarni, Ishai Menache, Sirui Li*
    The 40th Conference on Neural Information Processing Systems (NeurIPS), 2026. To Appear.
    ( preprint )
  • Interpreting Neural Combinatorial Optimization via Evolving Programmatic Bottlenecks
    Haocheng Duan, Yuxin Guo, Jieyi Bi, Anqi Xie, Sirui Li, Yining Ma, Cathy Wu
    The 40th Conference on Neural Information Processing Systems (NeurIPS), 2026. To Appear.
    ( preprint )
  • FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization
    Minwei Kong, Chonghe Jiang, Ao Qu, Wenbin Ouyang, Zhaoming Zeng, Xiaotong Guo, Zhekai Li, Junyi Li, Yi Fan, Xinshou Zheng, Xi Jing, Yikai Zhang, Zhiwei Liang, Seonghoo Kim, Runqing Yang, Sirui Li, Han Zheng, Wangyang Ying, Ou Zheng, Chonghuan Wang, Jinglong Zhao, Paul Pu Liang, Jinhua Zhao, Hai Wang
    The 40th Conference on Neural Information Processing Systems (NeurIPS), 2026. To Appear.
    ( preprint )
  • Learning to Segment for Vehicle Routing Problems
    Wenbin Ouyang, Sirui Li, Yining Ma, Cathy Wu
    The Fourteenth International Conference on Learning Representations (ICLR), 2026. Oral (top 1%)
    ( paper | preprint )
  • Coral: Towards Autonomous Multi-Agent Evolution for Open-ended Discovery
    Ao Qu, Han Zheng, Zijian Zhou, Yihao Yan, Yihong Tang, Shao Yong Ong, Fenglu Hong, Kaichen Zhou, Chonghe Jiang, Minwei Kong, Jiacheng Zhu, Xuan Jiang, Sirui Li, Cathy Wu, Bryan Kian Hsiang Low, Jinhua Zhao, Paul Pu Liang
    The Third Annual Conference on Language Modeling (COLM), 2026.
    ( paper | preprint )
  • Probability-Aware Parking Selection
    Cameron Hickert, Sirui Li, Zhengbing He, Cathy Wu
    IEEE Transactions on Intelligent Transportation Systems (T-ITS), 2026.
    ( preprint )
  • Towards Foundation Models for Mixed Integer Linear Programming
    Sirui Li, Janardhan Kulkarni, Ishai Menache, Cathy Wu, Beibin Li
    The Thirteenth International Conference on Learning Representations (ICLR), 2025.
    ( paper | preprint )
  • Learning-Guided Rolling Horizon Optimization for Flexible Job Shop Scheduling
    Sirui Li, Wenbin Ouyang, Yining Ma, Cathy Wu
    The Thirteenth International Conference on Learning Representations (ICLR), 2025.
    ( paper | preprint | 🎉 MIT News [Home Page Feature] )
  • Temporal Transfer Learning for Traffic Optimization with Coarse-grained Advisory Autonomy
    Jung-Hoon Cho, Sirui Li, Jeongyun Kim, Cathy Wu
    IEEE Transactions on Robotics (T-RO), 2025.
    ( preprint )
  • Hybrid System Stability Analysis of Multi-Lane Mixed-Autonomy Traffic
    Sirui Li, Roy Dong, Cathy Wu
    IEEE Transactions on Robotics (T-RO), 2024.
    ( paper | preprint )
  • Model-Based Transfer Learning for Contextual Reinforcement Learning
    Jung-Hoon Cho, Vindula Jayawardana, Sirui Li, Cathy Wu
    The 38th Conference on Neural Information Processing Systems (NeurIPS), 2024.
    ( paper | preprint | website | 🎉 MIT News )
  • Generalizing Eco-Lagrangian Control via Multi-residual Task Learning
    Vindula Jayawardana, Sirui Li, Cathy Wu, Yashar Farid, Kentaro Oguchi
    IEEE International Conference on Robotics and Automation (ICRA), 2024.
    ( paper | preprint | website )
  • Multi-Agent Reinforcement Learning for Assessing False-Data Injection Attacks on Transportation Networks
    Taha Eghtesad, Sirui Li, Yevgeniy Vorobeychik and Aron Laszka
    The 23rd International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), 2024.
    ( paper | preprint )
  • Learning to Configure Separators in Branch-and-Cut
    Sirui Li*, Wenbin Ouyang*, Max B. Paulus, and Cathy Wu
    The 37th Conference on Neural Information Processing Systems (NeurIPS), 2023.
    ( paper | preprint | website | 🎉 MIT News [Home Page Feature] )
  • Integrated Analysis of Human-compatible Control for Traffic Flow Stability
    Sirui Li, Roy Dong, and Cathy Wu
    IEEE Transactions on Control of Network Systems (TCNS), 2023.
    ( paper | preprint )
  • Cooperation for Scalable Supervision of Autonomy in Mixed Traffic
    Cameron Hickert, Sirui Li, Cathy Wu
    IEEE Transactions on Robotics (T-RO), 2023.
    ( paper | preprint | 🎉 MIT News )
  • The Impact of Task Underspecification in Evaluating Deep Reinforcement Learning
    Vindula Jayawardana, Catherine Tang, Sirui Li, Dajiang Suo, Cathy Wu
    The 36th Conference on Neural Information Processing Systems (NeurIPS), 2022.
    ( paper | preprint | website )
  • Learning to Delegate for Large-Scale Vehicle Routing
    Sirui Li*, Zhongxia Yan*, Cathy Wu
    The 35th Conference on Neural Information Processing Systems (NeurIPS), 2021. Spotlight (top 3%)
    ( paper | preprint | website | 🎉 MIT News )
  • Conditional Linear Regression
    Diego Calderon*, Brendan Juba*, Sirui Li*, Zongyi Li*, and Lisa Ruan*.
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2020.
    ( paper | preprint )
  • The Congressional Classification Challenge: Domain Specificity and Partisan Intensity
    Hao Yan, Sanmay Das, Allen Lavoie, Sirui Li, Betsy Sinclair
    ACM Conference on Economics and Computation (EC), 2019.
    ( paper )

Last Updated on 09/27/2026