Excited to share that the Prorok Lab will be presenting three papers at ICLR 2026 🎉
Our work spans key challenges in multi-agent learning, robotics, and graph-based reasoning:
📌 When Is Diversity Rewarded in Cooperative Multi-Agent Learning? Exploring when and why diversity among agents leads to better cooperation and performance. 🗓 Fri, Apr 24, 2026 | ⏰ 3:15–5:45 PM 📍 Pavilion 4, Poster P4-#4702
📌 Remotely Detectable Robot Policy Watermarking Introducing methods to embed and detect watermarks in robot policies—an important step toward accountability and security in autonomous systems. 🗓 Sat, Apr 25, 2026 | ⏰ 3:15–5:45 PM 📍 Pavilion 3, Poster P3-#1122
📌 Pairwise is Not Enough: Hypergraph Neural Networks for Multi-Agent Pathfinding Moving beyond pairwise interactions to hypergraph representations for more scalable and expressive multi-agent coordination. 🗓 Thu, Apr 23, 2026 | ⏰ 10:30 AM–1:00 PM 📍 Pavilion 3, Poster P3-#801
If you’re attending ICLR, we’d love to connect—stop by and discuss with Michael Amir, Rishabh Jain and Matteo Bettini.
#ICLR2026 #MultiAgentSystems #Robotics #MachineLearning #AIResearch