AI RESEARCH

ContextFlow: Hierarchical Task-State Alignment for Long-Horizon Embodied Agents

arXiv CS.AI

ArXi:2605.19314v1 Announce Type: cross Long-horizon embodied agents increasingly delegate navigation, search, approach, and manipulation to specialist executors. As these executors become stronger, the main bottleneck shifts from local skill execution to maintaining a coherent task frontier across planning, monitoring, memory, and execution. We study task-state misalignment, a task-level consistency failure in which the planner's active stage, runtime evidence, remembered context, and delegated executor no longer justify the same next-step decision.