About Me

I am a Ph.D. Candidate at the David R. Cheriton School of Computer Science, University of Waterloo (expected completion: Winter 2027). I am fortunate to work with Professor Raouf Boutaba (supervisor), Professor Mina Tahmasbi Arashloo, and Professor Bo Sun. My Ph.D. research lies at the intersection of reinforcement learning, multi-agent decision-making, verifying learning-augmented systems, and AI-driven optimization in networked systems.

Alongside my doctoral research, which has included an NSERC/MITACS collaboration with Rogers Communications, I have worked in industry research labs as a Research Intern at Huawei Cloud R&D (Markham, Canada) on post-training small language model judges and enterprise data agents, and at Nokia Bell Labs (Paris, France) on graph neural multi-agent reinforcement learning.

Prior to joining Waterloo, I received my B.Sc. in Electrical Engineering with a minor in Computer Science from Sharif University of Technology (Tehran, Iran).

Research Interests:
LLM-Driven Heuristic Discovery LLM Post-Training Multi-Agent Systems Formal Verification

Experience

Huawei Cloud R&D Markham, ON, Canada
Research Intern (Applied AI) May 2026 – Dec. 2026
University of Waterloo Waterloo, ON, Canada
Ph.D. Candidate (NSERC/MITACS/Rogers Comm.) Sept. 2021 – Winter 2027 (Expected)
Nokia Bell Labs Paris, France
Research Intern (Applied AI) Oct. 2024 – Sept. 2025
TAPSI Co. Tehran, Iran
Data Analyst (Pricing, Mapping, and Dispatch Systems) Feb. 2021 – Sept. 2021
Sharif University of Technology Tehran, Iran
B.Sc. in Electrical Engineering (Minor in Computer Science) Sept. 2016 – Feb. 2021

Publications

Full citation metrics are available on Google Scholar.

  1. Counterfactual Pairwise Augmentation Improves Small Pointwise LLM Judges

    M. Zangooei, P. Teymoori, M. R. Shirzad, S. Shahtalebi

    NeurIPS Workshop on Small Language Models (SLMs) for Agentic Systems, 2026

  2. Analyzing Symbolic Properties for DRL Agents in Systems and Networking

    M. Zangooei, J. Weil, A. Rizk, M. Tahmasbi Arashloo, R. Boutaba

    ACM SIGMETRICS, 2026

  3. HyRA: A Hybrid Resource Allocation Framework for RAN Slicing based on Bi-level Stochastic Optimization

    M. Zangooei, B. Sun, N. Limam, R. Boutaba

    IEEE/IFIP Network Operations and Management Symposium (NOMS), 2026

  4. Graph-Neural Multi-Agent Coordination for Distributed Access-Point Selection in Cell-Free Massive MIMO

    M. Zangooei, L. Salaün, C. S. Chen, R. Boutaba

    arXiv Preprint (Under Review), 2026

  5. Flexible RAN Slicing in Open RAN with Constrained Multi-Agent Reinforcement Learning

    M. Zangooei, M. Golkarifard, M. Rouili, N. Saha, R. Boutaba

    IEEE Journal on Selected Areas in Communications (JSAC), 2024

  6. Evaluating Open-Source 5G SA Testbeds: Unveiling Performance Disparities in RAN Scenarios

    M. Rouili, N. Saha, M. Golkarifard, M. Zangooei, R. Boutaba, E. Onur, A. Saleh

    IEEE/IFIP Network Operations and Management Symposium (NOMS), 2024

  7. Towards Verifying Monotonicity and Robustness Properties for Domain-Specific DRL Algorithms

    M. Zangooei, M. Tahmasbi Arashloo, R. Boutaba

    ICML Workshop on Formal Verification of Machine Learning, 2023

  8. Reinforcement Learning for Radio Resource Management in RAN Slicing: A Survey

    M. Zangooei, N. Saha, M. Golkarifard, R. Boutaba

    IEEE Communications Magazine, 2023

  9. Deep Reinforcement Learning Approaches to Network Slice Scaling and Placement: A Survey

    N. Saha, M. Zangooei, M. Golkarifard, R. Boutaba

    IEEE Communications Magazine, 2023