EE March Seminar

Title: Multi-Agent AI for Fast and Controllable Real World Decisions

Speaker: Saptarashmi Bandyopadhyay, CCNY

Date & Time: March 17th, 2026, 12:00pm

Location: Steinman Hall, ST619

RSVP Link: https://docs.google.com/forms/d/e/1FAIpQLSdzKQ8Vuy52NLE-ZylO5a5RowXeYwI4rquZbHPmnNzqkItugg/viewform
 

Abstract: Artificial Intelligence (AI) Agents are increasingly being deployed in Robotics, Augmented Reality (AR), Self-Driving Cars, Supply Chains Business, Stock Portfolio Finances and other domains. These Agents need to reliably cooperate with humans using evolving algorithms such as Multi-Agent Reinforcement Learning (MARL), Imitation Learning and Computational Game Theory. In this talk, Saptarashmi will introduce an imitate-then-commit algorithm for AI Agents to cooperate and align in settings where they have similar goals but different priorities. He will show bounds of successful cooperation among AI agents are stronger with this approach than with a naive reduction of the alignment problem to Imitation Learning. 

Saptarashmi will then share a Multimodal Agentic Model Predictive Control framework to allow fine-grained tuning of Imitation Learning demonstrations, using Vision-Language Models (VLMs), to train autonomous vehicles with better spatio-temporal reasoning and improved control dynamics, which are also useful for smart grid orchestration. Saptarashmi will share real-world applications of AI Agents, including YETI (YET-to-Intervene) Multimodal Agents which efficiently detect when to autonomously intervene while interacting with users in AR for fixing mistakes or other daily tasks. Saptarashmi will highlight the importance of training AI Agents at scale efficiently and introduce JAXMARL, the fastest distributed open-source MARL library with up to 12,500× speedup over alternatives. Together, his talk shows the promise of Multi-Agent AI and Human-AI interaction to solve real-world problems with efficient and generalizable algorithms that add new capabilities to AI Agents such as planning, reasoning and navigation.

Bio: Saptarashmi Bandyopadhyay is a Tenure-Track Assistant Professor of Computer Science at the City University of New York at the City College of New York and the Graduate Center. He graduated with his Ph.D. in Computer Science at the University of Maryland, College Park (UMD) advised by Prof. John Dickerson and Prof. Tom Goldstein, in Summer 2025. His research on Multi-Agent AI for Autonomous Decision Making in the Real World addresses the challenges and opportunities of building AI Agents to plan, reason, and navigate in AR/VR, Supply Chains, Recommender Systems, Robotics, Self-Driving Cars, Climate Conservation, and other domains. He works with Reinforcement Learning, Imitation Learning, Model Predictive Control, LLMs, VLMs, and Game Theory algorithms to train AI Agents with Social Intelligence to take actions and provide insights at scale. He has been a Ph.D. Student Researcher at Google Augmented Reality and Google DeepMind in the Multimodal Conversational AI and Astra AR teams creating Multimodal (Audio, Vision and Language) AI Agents to proactively assist users. Saptarashmi has published twenty-six research papers in top AI venues including AAAI, ACM AAMAS, NeurIPS, EMNLP, ACL, SPIE, and others. He chaired the Multi-Agent AI in the Real World Workshop at AAAI-25 and created the MARL Seminar at UMD, hosting prominent speakers from industry and academia including Turing Award Laureates. Further research details can be found on his websites https://sites.google.com/view/saptarashmi/about and https://www.gc.cuny.edu/people/saptarashmi-bandyopadhyay.