Concept智能体执行图 / Agent Execution Graph
Execution Graph
A concept that models an agent's execution flow as a directed graph, in which nodes represent model calls, tool calls, or conditional judgments, and edges represent state transitions. It supports inserting validation, logging, and human pause points between nodes.
Timeline (last 90 days)
Nov 5
Dependency-aware execution graphs typically organize task nodes as a directed acyclic graph (DAG), with edges representing data dependencies or precedence constraints.
Unverified50%