Yufeng Zheng

Ph.D. Candidate · Operations Management & Statistics
Rotman School of Management, University of Toronto

Yufeng Zheng

How will AI agents change the way firms, society, and science operate, and how should they be managed? Agents at Work

Can machine learning solve operations problems at scale, learning from feedback and from the analytical models the field already has? And can a model read a problem’s description and write the analytical policy itself? Operations Models

Work toward these questions appears in Operations Research, Marketing Science, ICML, and NeurIPS.

CV Google Scholar
Toronto, ON 

Selected Publications

All papers →

  1. Operations Research 2025

    A Doubly Stochastic Simulator with Applications in Arrivals Modeling and Simulation

    Yufeng Zheng, Zeyu Zheng, Tingyu Zhu

    Journal

  2. Marketing Science 2025

    LOLA: LLM-Assisted Online Learning Algorithm for Content Experiments

    Zikun Ye, Hema Yoganarasimhan, Yufeng Zheng

    Journal Code

  3. ICML 2023

    Robust Situational Reinforcement Learning in Face of Context Disturbances

    Jinpeng Zhang, Yufeng Zheng, Chuheng Zhang, et al.

    PDFPaper page

  4. NeurIPS 2022

    An Adaptive Deep RL Method for Non-Stationary Environments with Piecewise Stable Context

    Xiaoyu Chen, Xiangming Zhu, Yufeng Zheng, et al.

    PDFPaper page

Working Papers

  1. Draft available soon 2026

    Training and Deploying Machine Learning Services under the Neural Scaling Law

    Yufeng Zheng, Ningyuan Chen, Rafid Mahmood

Research

All papers →

AI Agents in the Economy, Organizations, and Science

AI agents now do work that once belonged to software, to staff, and to researchers.

2 papers

Foundation Models and Learning for Operational Decisions

Queues, inventories, service networks, and platforms make decisions that repeat at scale, and they produce data as they run.

6 papers

OperationsAI agentsFoundation modelsScalingReinforcement learningOnline learningSimulationExperimentsMarkets & games

Talks & Awards

  1. 2026-07
    talk

    INFORMS RMP Conference, Ann Arbor

    When to stop scaling

  2. 2026-06
    talk

    CORS Annual Conference, Kingston

    When to stop scaling

  3. 2026-06
    talk

    CORS Annual Conference, Kingston

    Counterfactual evaluation from queue event logs · presented on behalf of the team

  4. 2025-03
    talk

    INFORMS Computing Society Conference, Toronto

    Generative differentiable discrete event simulation

  5. 2024-10
    talk

    INFORMS Annual Meeting, Seattle

    LLM-assisted A/B tests

  6. 2024
    award

    TD MDAL Research Grant, Rotman School of Management

    When to stop scaling · with Ningyuan Chen

  7. 2018
    award

    Finalist, M&SOM Data Driven Research Challenge

    Forecast-driven fulfillment

Ask my research

Open chat →

A research guide grounded in my papers. It answers with citations to the exact passages it used.