Vision Agents

A deep research agent framework optimized for complex research and prediction tasks, with MiroThinker-1.7 and MiroThinker-H1 models achieving 74.0 and 88.2 on BrowseComp benchmark, supporting multi-step reasoning and information retrieval.

Open-source deep research agent from Alibaba Tongyi Lab, using multi-stage iterative information retrieval and reasoning to conduct deep analysis, synthesis, and summarization of complex topics with web search and document analysis.

An end-to-end RL training framework by NVIDIA for orchestrating tools and agentic workflows. Optimizes multi-step agent decision-making and tool-use policies.

Conversational voice AI agents platform for building natural language phone interactions with multilingual speech synthesis and real-time dialogue management.