Implement Agentic logoImplement Agentica Clouda Company

    Reviewed current signal · 2026-05-14

    LongAct: long-horizon household task execution

    Reviewed through September 18, 2026

    2026-05-14 · Reviewed current signal

    LongAct: long-horizon household task execution

    Era
    Current reviewed signal
    Theme
    Physical AI & world models
    Evidence form
    Preprint
    Source of record
    arXiv
    Source tier
    A
    Impact
    High
    School / paradigm
    Not recorded — current signals carry no formal school
    Application
    Household robotics and embodied assistants
    Researchers
    Not recorded

    Understand

    Plain-language record, transferred from the reviewed source module.

    What changed. LongAct isolates high-level household planning; its HoloMind agent combines a DAG planner, multimodal spatial memory, episodic memory, and a global critic. Top systems reached 59% goal completion but only 16% full-task success.

    Technique / discovery. DAG planning, spatial and episodic memory, VLM control, and reflective supervision.

    Apply

    Professional implication, only where the reviewed record states one.

    Why it matters. Hierarchical plans and persistent memory improve partial progress, yet error accumulation makes full long-horizon success rare.

    Application. Household robotics and embodied assistants

    Verify

    Evidence status, stated limitations, and the external sources this record actually carries.

    Evidence maturity. Preprint (source tier A)

    Identified bottleneck. Dependency tracking, memory consistency, and recovery from early mistakes.

    Caveat / evidence note. Preprint on an abstracted benchmark; low-level physical control is intentionally excluded.

    Review status. Reviewed. User requested: Yes.

    Reproduce

    A reproduction tutorial is linked only when one exists for this exact record.

    A reproduction tutorial is not yet available for this entry. The closest reviewed material is Embodied AI and world models and Agent planning and cognitive architectures.

    Cite or share

    Related