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

2026/04/29 by GLM-V Team, :, Wenyi Hong +95 · 10 voices · 1 citation
#cs.CV

paper · pdf

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.

Citations

• Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification
• Better & Faster Large Language Models via Multi-token Prediction
• V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs

Cited by

• EvoGUI: An Evolution-Aware Benchmark for GUI State-Transition Understanding

Discussions

• GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents [hn, 163 points, 32 comments]
• GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents https://arxiv.org/abs/2604.26752 (https://news.ycombinator.com/item?id=48026021) [bsky, 1 points, 0 comments]
• GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents https://arxiv.org/abs/2604.26752 https://news.ycombinator.com/item?id=48026021 [bsky, 1 points, 0 comments]
• [6/30] 284 Upvotes, 36 Comments, 3 Posts, arXiv:2604.26752 🆕GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents V Team, Wenyi Hong, Xiaotao Gu, Ziyang Pan, Zhen Yang, Yuting Wang [bsky, 1 points, 1 comments]
• GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents https://arxiv.org/abs/2604.26752 [bsky, 0 points, 0 comments]
• 📰 GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents 🔗 https://arxiv.org/abs/2604.26752 💬 Discuss on HN [bsky, 0 points, 0 comments]
• GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents https://arxiv.org/abs/2604.26752 (https://news.ycombinator.com/item?id=48026021) [bsky, 0 points, 0 comments]
• 📰 GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents 🔗 https://arxiv.org/abs/2604.26752 #Tech #Dev [bsky, 0 points, 0 comments]
• GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents #HackerNews https://arxiv.org/abs/2604.26752 [bsky, 0 points, 0 comments]
• GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents https:// arxiv.org/abs/2604.26752 # arxiv [mastodon, 0 points, 0 comments]

Related

• GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
• Agent-Omni: Test-Time Multimodal Reasoning via Model Coordination for Understanding Anything
• MageBench: Bridging Large Multimodal Models to Agents
• Seed1.5-VL Technical Report
• Be My Eyes: Extending Large Language Models to New Modalities Through Multi-Agent Collaboration