解决长时程智能体任务状态不一致问题，提升多阶段协作的稳定性。
ContextFlow: Hierarchical Task-State Alignment for Long-Horizon Embodied Agents
- 用显式契约管理任务阶段，实现跨模块状态对齐。
- 通过证据包和五类定向更新，有效缓解任务失败现象。
- 适用于需要长期规划与多执行器协同的机器人系统。
长时程具身智能体逐渐将导航、搜索、接近和操作等任务交由专业执行器完成。随着这些执行器能力增强，主要瓶颈已从局部技能执行转向跨规划、监控、记忆与执行的连贯性维护。本文研究任务-状态错位问题：规划器的当前阶段、运行时证据、记忆上下文与委派执行器不再支持相同下一步决策，可能导致任务交接失效、阶段卡死、执行器-上下文不匹配及重复规划。为此，提出可检查的对齐框架 ContextFlow，将阶段表示为显式契约，将运行时观察转化为证据包，并应用包括继续、细化、转移、提升和修复在内的范围化更新策略。ContextFlow 保持专业执行器负责局部闭环控制的同时，使任务前沿对齐过程显式且可审计。在长时程具身任务上的实验与演示轨迹表明，基于证据的范围化更新能有效诊断并缓解反复出现的任务状态失败。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。