ContextFlow: Hierarchical Task-State Alignment for Long-Horizon Embodied Agents
For embodied AI systems with multiple specialist executors, ContextFlow provides a principled way to maintain task coherence, though results are qualitative and lack concrete performance numbers.
ContextFlow addresses task-state misalignment in long-horizon embodied agents, where planner, memory, and executor disagree on the next step. The framework uses explicit contracts and evidence packets to detect and repair failures, reducing unsupported handoffs and replanning.
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. This failure can lead to unsupported handoffs, stage lock, executor-context mismatch, and unnecessary replanning. We propose ContextFlow, an inspectable alignment framework that represents stages as explicit contracts, converts runtime observations into evidence packets, and applies scoped updates including continue, refine, transfer, promote, and repair. ContextFlow keeps specialist executors responsible for local closed-loop control while making task-frontier alignment explicit and auditable. Experiments and demonstration traces on long-horizon embodied tasks illustrate how evidence-grounded scoped updates diagnose and mitigate recurring task-state failures.