Almagro, AlbertoLlamas-Núñez, Juan CarlosSánchez Ruiz-Granados, Antonio AlejandroDíaz Agudo, María Belén2025-06-262025-06-262024-10-2910.1109/TG.2024.3487309https://hdl.handle.net/20.500.14352/121893Geometry Friends is a collaborative platform game featuring two agents, a circle and a rectangle, navigating through physics-driven levels to collect diamonds. Each level presents challenges in the form of obstacles and diamonds arranged in different configurations that forces the agents to cooperate. In this article, we describe the Universidad Complutense de Madrid (UCM) agents, that participated in the 2023 Geometry Friends AI Competition with excellent results, especially in the collaborative track. Our approach combines level analysis, motion simulation, abstract planning, scripted actions, reinforcement learning, and different types of agent interaction. The contributions are versatile and potentially applicable to other collaborative platform games.engAttribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/journal articlehttps://doi.org/10.1109/TG.2024.3487309open accessCollaborative agentsGeometry FriendsSymbolic AIAction planningReinforcement LearningInteligencia artificial (Informática)1203.04 Inteligencia Artificial