Mohamed Aghzal
محمد أغزال
ⵎⵓⵃⴰⵎⴷ ⴰⵖⵣⴰⵍ

About Me

I am a Ph.D. student at George Mason University, where I have the fortune of being co-advised by Dr. Ziyu Yao and Dr. Gregory J. Stein. I also collaborate frequently with Dr. Erion Plaku.

My research focuses on building intelligent agents that can reason, plan, and act effectively in complex real-world environments. Working at the intersection of natural language processing, foundation models, and automated planning, I investigate how to overcome the limitations of Large Language Models in agentic applications—grounding them in both physical domains like robotics and digital environments like computer use agents. A central thrust of my work is enabling these systems to understand, predict, and manipulate dynamic environments with transparency and robustness. By integrating neural foundation models with classical planning approaches and using interpretability techniques to look into their failures, I aim to design AI systems capable of safe, interpretable, and reliable human-AI collaboration. Ultimately, my research advances autonomous agents that combine language understanding and perception with human-like cognitive abilities for problem-solving and decision-making.

Research Interests

Planning and Reasoning: Planning and reasoning are crucial components of human intelligence, enabling us to navigate complex environments, make informed decisions, and achieve our goals. A central research inquiry in my work involves exploring ways to leverage foundation models to build systems that can reason and plan.

Explainability and Interpretability: As AI agents are increasingly used for complex and real-world tasks, it is crucial to develop methods for better explaining their decision-making processes in order to develop safer and more reliable systems.

Causal Inference: A crucial aspect of human intelligence is our capacity to discern cause-effect relationships and construct causal models of the world. This ability allows us to understand, predict, and manipulate our environment effectively and transfer this knowledge into novel situations. My goal is to develop systems that can reason in terms of causal relationships, mirroring this fundamental human cognitive skill.

News

[March 2026] Check out our new preprint on hierarchical evaluation of LLM Web Agents.
[June 2025] Attended IEEE/CVF CVPR 2025 in Nashville, TN 🎸
[April 2025] Received a Travel Award for IEEE/CVF CVPR 2025.
[February 2025] Attended AAAI 2025 in Philadephia, PA.
[February 2025] Paper accepted to IEEE/CVF CVPR 2025.
[February 2025] Check out our new survey on the use of LLMs in Planning.
[November 2024] Check out our new preprint
[June 2024] Paper accepted to IEEE CASE 2024.
[March 2024] Paper accepted to LLM Agents at ICLR 2024.
[October 2023] New preprint available on ArXiv.
[April 2023] Presented a poster at MASC-SLL 2023.

Publications