Schedule

9 am to 9:30 am - Introduction: Saptarashmi Bandyopadhyay

PhD Candidate of Computer Science at the University of Maryland, College Park, PhD Student Researcher, Google AI AR and Google DeepMind

9:30 am to 10:20 am - Keynote Speaker: Milind Tambe

Harvard University Gordon McKay Professor of Computer Science and Director of Center for Research on Computation and Society (CRCS), Principal Scientist at Google DeepMind

10:20 to 11:00 am - Keynote Speaker: Federico Pecora 

Senior Manager, Applied Science at Amazon Robotics

11:00 am to 12:00 pm - Poster Session I

Converging to Stability in Two-Sided Bandits: The Case of Unknown Preferences on Both Sides of a Matching Market

Two-Player Zero-Sum Differential Games with One-Sided Information

Learning Robust Policies via Interpretable Hamilton-Jacobi Reachability-Guided Disturbances

Dynamics as Prompts: In-Context Learning for Sim-to-Real System Identifications

MobileAgentBench: An Efficient and User-Friendly Benchmark for Mobile LLM Agents

Multi-Agent Reinforcement Learning with Long-Term Performance Objectives for Service Workforce Optimization

Scaling Multi-Agent RL through Mean Field Games and Incremental Learning

Aligning Compound AI Systems via System-level DPO

Value of Assistance for Grasping

Centralized Policy Learning for Consensus Control of Connected and Automated Vehicles

Accelerating Manufacturing Scale-Up from Material Discovery Using Agentic Web Navigation and Retrieval-Augmented AI for Process Engineering Schematics Design 

GitTemporalAI: Leveraging Temporal Knowledge Graphs and LLMs for Multi-Agent Repository Intelligence

1:00pm to 1:40 pm - Keynote Speaker: Sanmay Das

Virginia Tech Innovation Campus Professor of Computer Science and Associate Director, AI for Social Impact, Sanghani Center for AI and Data Analytics, Chair ACM SIGAI

1:40pm to 2:40 pm - Oral: Best Papers*

Converging to Stability in Two-Sided Bandits: The Case of Unknown Preferences on Both Sides of a Matching Market 

Two-Player Zero-Sum Differential Games with One-Sided Information 

Mean-Field Sampling for Cooperative Multi-Agent Reinforcement Learning 

Robust Policy Design in Agent-Based Simulators using Adversarial Reinforcement Learning 

2:50pm to 3:50pm - Poster Session II

Mean-Field Sampling for Cooperative Multi-Agent Reinforcement Learning

Robust Policy Design in Agent-Based Simulators using Adversarial Reinforcement Learning

The First International Maritime Capture the Flag Competition: Lessons Learned and Future Directions

Improving Real-World Applicability of Networked Mean-Field Games using Function Approximation and Empirical Mean-Field Estimation

Learning Multi-Agent Multi-Machine Tending by Mobile Robots

Multi-Agent Decision S4: Leveraging State Space Models for Offline Multi-Agent Reinforcement Learning

LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative Planning

Multi-Agent Collaboration in Incident Response with Large Language Models

Multi-modal Contrastive Training for Robust VQA

TradingAgents: Multi-Agents LLM Financial Trading Framework

Unraveling Complex Sequential Social Dilemmas: In a Risky World with A2C Decision Transformer

3:50pm to 4:50 pm - Oral: JMLR Track*

Learning Robust Policies via Interpretable Hamilton-Jacobi Reachability-Guided Disturbances

Dynamics as Prompts: In-Context Learning for Sim-to-Real System Identifications

MobileAgentBench: An Efficient and User-Friendly Benchmark for Mobile LLM Agents

Multi-Agent Reinforcement Learning with Long-Term Performance Objectives for Service Workforce Optimization

Scaling Multi-Agent RL through Mean Field Games and Incremental Learning

Aligning Compound AI Systems via System-level DPO

The First International Maritime Capture the Flag Competition: Lessons Learned and Future Directions

Improving Real-World Applicability of Networked Mean-Field Games using Function Approximation and Empirical Mean-Field Estimation

Learning Multi-Agent Multi-Machine Tending by Mobile Robots

Multi-Agent Collaboration in Incident Response with Large Language Models

TradingAgents: Multi-Agents LLM Financial Trading Framework

LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative Planning

4:50pm to 5:00pm - Conclusion and Acknowledgments: Saptarashmi Bandyopadhyay

PhD Candidate of Computer Science at the University of Maryland, College Park, PhD Student Researcher, Google AI AR and Google DeepMind

*Best Papers, presented from 1:40 to 2:40 pm, will also be included in the JMLR submission.