Mukesh Ghimire [CV]

I am an Applied Scientist at AWS AI Fundamental Research where I work on Multi-Agent Systems and Agentic AI. I received my PhD from Arizona State University, where I worked at the Design Informatics Lab at ASU. My research interests include multi-agent systems, game theory, reinforcement learning and optimization. My PhD focused on differential games, especially those with incomplete information on one side.

You can reach me at: mghimire(at)asu(dot)edu

News

• 2026-06-15: I am now an Applied Scientist at AWS AI Fundamental Research in the Bay Area!
• 2026-03-31: I successfully defended my PhD dissertation!
• Our paper "Solving Football by Exploiting Equilibrium Structure of 2p0s Differential Games with One-Sided Information" is accepted at ICLR 2026!
• I will be joining Mercedes-Benz Research and Development as a Machine Learning Intern in Fall 2025!
• I will be joining Amazon AWS as an Applied Scientist Intern in Summer 2025!

Publications

Solving Football by Exploiting Equilibrium Structure of 2p0s Differential Games with One-Sided Information
Mukesh Ghimire, Lei Zhang, Zhe Xu, Yi Ren
Accepted at ICLR 2026.
[Paper] [Code]

PRISM: A Unified Framework for Post-Training LLMs Without Verifiable Rewards
Mukesh Ghimire, Aosong Feng, Liwen You, Youzhi Luo, Fang Liu, Xuan Zhu
Under Review.
[Paper]

Two-Player Zero-Sum Differential Games with One-Sided Information
Mukesh Ghimire, Zhe Xu, Yi Ren
Multi-Agent AI in the Real World Workshop at AAAI, 2025. Best Paper Award
[Paper]

State-Constrained Zero-Sum Differential Games with One-Sided Information
Mukesh Ghimire, Lei Zhang, Zhe Xu, Yi Ren
International Conference on Machine Learning (ICML), 2024
[Paper] [Code]

Value Approximation for Two-Player General-Sum Differential Games with State Constraints
Lei Zhang, Mukesh Ghimire, Zhe Xu, Wenlong Zhang, Yi Ren
IEEE T-RO, 2024
[Paper] [Code]

Solving Two-Player General-Sum Games Between Swarms
Mukesh Ghimire, Lei Zhang, Wenlong Zhang, Yi Ren, Zhe Xu
American Control Conference (ACC), 2024
[Paper]

Pontryagin Neural Operator for Solving Parametric General-Sum Differential Games
Lei Zhang, Mukesh Ghimire, Zhe Xu, Wenlong Zhang, Yi Ren
Learning for Dynamics and Control (L4DC), 2024
[Paper]

Approximating Discontinuous Nash Equilibrial Values of Two-Player General-Sum Differential Games
Lei Zhang, Mukesh Ghimire, Zhe Xu, Wenlong Zhang, Yi Ren
International Conference on Robotics and Automation (ICRA), 2023
[Paper][Code]

When Shall I Estimate Your Intent? Costs and Benefits of Intent Inference in Multi-Agent Interactions
Sunny Amatya, Mukesh Ghimire, Yi Ren, Zhe Xu, Wenlong Zhang
American Control Conference (ACC), 2022
[Paper]