stateful-online-sequential-grounding-and-replanning

Trigger this skill when the agent is assigned a multi-step mission where later steps depend on information discovered in earlier steps, or when testing if the agent knows how far it has progressed through an instruction sequence. Plain-language triggers include: 'follow these steps one by one', 'go to the first place then the second', 'which step am I currently on?', 'how much of the task is done?', 'remember where the items were', and 'fix the plan if you can't find the next object'.

By Dingxingdi schedule Updated 4/10/2026