Welcome to my website! I am Runyu (Cathy) Zhang, and I am a Postdoc for Engineering Excellence at MIT and I’m working with Prof. Asu Ozdaglar and Prof. Gioele Zardini. I earned my Ph.D. degree at Harvard University, School of Engineering and Applied Sciences, under the supervision of Prof. Na Li. Prior to pursuing Ph.D., I earned a B.S. degree in Scientific and Engineering Computing in the Mathematics department at Peking University in 2019.
My research interest lies in learning, control and decision making in multi-agent systems. The high-level objective is to design scalable, efficient and provable learning/control algorithms for multi-agent systems under challenges such as communication constraints, strategic behavior and model uncertainty. My research sits at the intersection of various domains, utilizing tools from reinforcement learning (RL), game theory, control theory and optimization. As an ultimate goal, my research is dedicated to providing both theoretical insights and engineering tools for AI-enabled multi-agent societal systems design and operation. For more detailed research projects and research interests please refer to the research tab and publication tab.
I am on the job market for both academic and industry positions starting as early as fall 2026! Let’s connect. Please email me at runyuzha@mit.edu
Recent Updates
Aug 2026 🎤 I am excited to give a talk at the Artificially Intelligent Cities Workshop , held at New York University on August 27–29. See you in New York! Aug 2026 🎉 Excited that our paper Cooperative Multi-Agent Graph Bandits: UCB Algorithm and Regret Analysis was accepted to IEEE Transactions on Automatic Control (TAC)! Congratulations to Phevos and Aryan! Jul 2026 🎉 Excited that our paper Random-Subspace Sequential Quadratic Programming for Constrained Zeroth-Order Optimization was accepted to the IEEE Conference on Decision and Control (CDC) 2026! This work provides a random-subspace perspective on our zeroth-order constrained optimization work . See you in Hawaii! Jul 2026 🎤 We are excited to organize the CDC 2026 workshop Generative AI Meets Control and Optimization: Theory, Algorithms, and Systems ! Join us in Honolulu on December 14—register here . Jun 2026 🎉 Excited that our paper Adaptive-Horizon Conflict-Based Search for Closed-Loop Multi-Agent Path Finding was accepted to IEEE Robotics and Automation Letters (RA-L)! Congratulations to Jiarui! May 2026 🚀 Excited to share our new paper Implementation-Based Incentive Design for Autonomous Mobility-on-Demand and Transit Systems ! This work studies incentive design for aligning autonomous mobility-on-demand and transit systems with broader system-level objectives. May 2026 🚀 Excited to share our new paper Muon-OGD: Muon-based Spectral Orthogonal Gradient Projection for LLM Continual Learning ! This work explores a spectral-geometry-inspired approach to orthogonal gradient projection for continual learning in large language models. May 2026 🚀 Excited to share our new paper AdamFLIP: Adaptive Momentum Feedback Linearization Optimization for Hard Constrained PINN Training ! We demonstrate that our constrained optimization algorithm works well for physics-informed neural networks. Mar 2026 🎤 I am excited to co-organize the ACC 2026 workshop Toward Safe and Scalable Multi-Agent Systems: Bridging Control, RL, and Generative AI ! See you in New Orleans — register here ! Jan 2026 🎉 Excited that our paper Optimism as Risk-Seeking in Multi-Agent Reinforcement Learning was accepted to IEEE Control Systems Letters (L-CSS) and the American Control Conference (ACC) 2026. See you in New Orleans! Dec 2025 🌟 I was featured in IEEE PhDs in Control ! Honored to be part of and recognized by the control community. Nov 2025 🚀 Excited to share our new paper FICO: Finite-Horizon Closed-Loop Factorization for Unified Multi-Agent Path Finding ! FICO reframes multi-agent path finding through a closed-loop control lens and leverages factorization to enable millisecond-start execution at scale, with robustness to real-time uncertainties. Sep 2025 🎉 Thrilled that our paper Constrained Optimization From a Control Perspective via Feedback Linearization was accepted to NeurIPS 2025! The paper leverages control techniques such as feedback linearization to analyze existing methods and design novel constrained optimization solvers. See you in San Diego! Also, check out our zeroth-order extension , which was the key motivation that sparked this line of research. Sep 2025 🌟 Honored to be selected for the Rising Stars program at the 2025 Northeast Robotics Colloquium (NERC) . See you at Cornell! Apr 2025 🏆 I am honored to receive the MIT Postdoctoral Fellowship Program for Engineering Excellence ! Jan 2025 🎉 Excited that our paper on distributed control and reinforcement learning for network systems, Scalable Spectral Representations for Multi-agent Reinforcement Learning in Network MDPs , was accepted to AISTATS 2025! Sep 2024 🎉 Excited that our paper — one of my favorite works — On the Optimal Control of Network LQR with Spatially-Exponential Decaying Structure was accepted to Automatica! Aug 2024 🌟 Very honored to be selected as an EECS Rising Star 2024 ! Jun 2024 🚀 Excited to share our new paper Equilibrium Selection for Multi-agent Reinforcement Learning ! 