GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents

TL;DR

GLM-5V-Turbo is a multimodal foundation model designed for agents that integrates perception with reasoning, planning, and tool use, enabling effective handling of heterogeneous contexts like images and videos.

Contribution

It introduces a model that embeds multimodal perception into core reasoning and agentic tasks, advancing the development of native multimodal foundation models for agents.

Findings

Strong performance in multimodal coding and visual tool use.

Effective integration of perception with reasoning and planning.

Maintains competitive text-only coding capabilities.

Abstract

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.