GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
This work advances the development of native multimodal foundation models for agentic applications, addressing the need for integrated perception and reasoning in real-world environments.
GLM-5V-Turbo integrates multimodal perception as a core component of reasoning and action, achieving strong performance in multimodal coding, visual tool use, and agentic tasks while maintaining competitive text-only coding capability.
We present GLM-5V-Turbo, a step toward native foundation models for multimodal agents. As foundation models are increasingly deployed in real environments, agentic capability depends not only on language reasoning, but also on the ability to perceive, interpret, and act over heterogeneous contexts such as images, videos, webpages, documents, GUIs. GLM-5V-Turbo is built around this objective: multimodal perception is integrated as a core component of reasoning, planning, tool use, and execution, rather than as an auxiliary interface to a language model. This report summarizes the main improvements behind GLM-5V-Turbo across model design, multimodal training, reinforcement learning, toolchain expansion, and integration with agent frameworks. These developments lead to strong performance in multimodal coding, visual tool use, and framework-based agentic tasks, while preserving competitive text-only coding capability. More importantly, our development process offers practical insights for building multimodal agents, highlighting the central role of multimodal perception, hierarchical optimization, and reliable end-to-end verification.