The new capabilities combine visual reasoning with Python code to improve image analysis and enable active investigations.

1月27日，DeepSeek刚刚发布了DeepSeek-OCR2，搭载核心黑科技 DeepEncoder V2 。它抛弃了传统的机械扫描，让AI学会了像人类一样「按逻辑顺序阅读」，仅用几百个Token就实现了对复杂排版和图表的完美理解。

Google's new ‘Agentic Vision’ capability in Gemini Flash 3 claims to reduce hallucinations and provide more accurate ...

Gemini 3 Flash adds active vision with Python code execution, lifting accuracy by 5 to 10%, so you can trust verified results.

Google DeepMind has added Agentic Vision to Gemini 3 Flash, enabling active image exploration through Python code execution with 5-10% quality improvements.

Google has introduced Agentic Vision for Gemini 3 Flash, a new capability that improves how the model understands and ...

Google DeepMind has introduced Agentic Vision in Gemini 3 Flash, a new capability that changes how the model understands ...

Gemini’s Agentic Vision adds a think, act, observe loop and Python tools, helping teams audit images faster and cut counting errors.