To address the challenge of recognizing unlabeled 3D models in open-set domain, this paper proposes a multi-agent collaborative algorithm for open-set multimodal 3D model recognition. The algorithm employs a reinforcement learning framework to simulate human cognitive processes. Within this framework, a multi-agent system is utilized to extract and fuse multimodal information, enabling a comprehensive understanding of the feature space while leveraging the similarity of multimodal samples to enhance model training. Additionally, a progressive label generation method is introduced in the reinforcement learning environment. It dynamically adjusts clustering constraints to generate reliable pseudo-labels for a subset of unlabeled data during training, mimicking human exploratory learning of unknown data. These mechanisms collectively update the network parameters based on environmental feedback rewards, effectively controlling the extent of exploratory learning and ensuring accurate learning for unknown categories. Experimental evaluations on the OS-MN40, OS-MN40-Miss, and CIFAR10 datasets demonstrate that the proposed algorithm achieves competitive results, validating its robustness and generalization capabilities across diverse scenarios.