deepeyesv2-agentic-multimodal-tool-use

【开发与工程】Train multimodal agents to dynamically invoke tools (code execution, web search) within reasoning loops through a two-stage pipeline combining cold-start supervised learning with reinforcement learning—enabling task-adaptive tool invocation for perception, reasoning, and retrieval tasks.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准