# EchoVLM 2.0
**Technical Report: Coming Soon!** π§
EchoVLM 2.0 is a major update to our vision-language model, introducing a **brand-new Agent architecture**. This version is designed to enhance autonomous problem-solving and tool-use capabilities, pushing the boundaries of what VLMs can achieve in complex visual tasks.
## π Key Features
- **Brand-New Agent Architecture**: Built from the ground up for advanced agentic workflows.
- **Versatile Task Support**: Compared to V1, EchoVLM 2.0 now supports a wider range of tasks, including:
- Multiple-choice questions
- True/False questions
- Open-ended question answering
- **Enhanced Instruction Following**: Significantly improved capability to understand and follow complex user instructions accurately.
- **Tool Integration**: Currently, the model officially supports the **`ImageZoomInTool`** (click [here](https://github.com/QwenLM/Qwen-Agent/blob/main/qwen_agent/tools/image_zoom_in_qwen3vl.py) to view the implementation details).
## οΏ½β¦
---
license: apache-2.0
language:
- en
pipeline_tag: image-text-to-text
tags:
- agent
- vision-language
- EchoVLM
---
# EchoVLM 2.0
**Technical Report: Coming Soon!** π§
EchoVLM 2.0 is a major update to our vision-language model, introducing a **brand-new Agent architecture**. This version is designed to enhance autonomous problem-solving and tool-use capabilities, pushing the boundaries of what VLMs can achieve in complex visual tasks.
## π Key Features
- **Brand-New Agent Architecture**: Built from the ground up for advanced agentic workflows.
- **Versatile Task Support**: Compared to V1, EchoVLM 2.0 now supports a wider range of tasks, including:
- Multiple-choice questions
- True/False questions
- Open-ended question answering
- **Enhanced Instruction Following**: Significantly improved capability to understand and follow complex user instructions accurately.
- **Tool Integration**: Currently, the model officially supports the **`ImageZoomInTool`** (click [here](https:β¦
