ADK Go 2.0 ships a graph-based workflow engine with built-in human-in-the-loop
ADK Go 2.0 发布:构建可靠的多智能体应用,新增基于图的工作流引擎、人工参与循环与动态编排
ADK Go 2.0 models multi-agent workflows as a directed graph of nodes and edges. Nodes can be typed Go functions, LLM agents, or tools; edges handle routing, fan-out, and fan-in. A new emitting function node lets a single function pause for human approval without a separate dynamic node. The graph itself is an agent that runs in the existing runner, with persistent state that survives restarts. The post does not disclose performance benchmarks or latency figures.
Why it matters: Shows how Google's Go agent framework models multi-agent work as a graph, with a node type that pauses for human approval.