# Embodied Planning on WorldLines 21 action-dense samples downstream planning probe Source: [Embodied Planning on WorldLines 21 action-dense samples downstream planning probe]() Collection index: [llms.txt]() Data updated: 2026-06-18T08:15:00.629Z Evaluation of embodied planning performance using the WorldLines 21 action-dense samples downstream planning probe dataset, assessed using metrics related to plan quality, state consistency, precondition validity, memory usage, and action ordering. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Embodied Planning | | Dataset (including any stated split) | WorldLines 21 action-dense samples downstream planning probe | | Metric | Plan Judge | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 5 of 5 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Plan Judge](): Higher is better; unit: PERCENT. - [State Consistency](): Higher is better; unit: PERCENT. - [Precondition Validity](): Higher is better; unit: PERCENT. - [Memory Use](): Lower is better; unit: SCALAR. - [Action Order](): Higher is better; unit: PERCENT. ## Recorded results | Method | Plan Judge | Result date | Report paper | | --- | --- | --- | --- | | ObsMem | 68.4 | Not recorded | 6a337b82206542251d7c4fc6 | | A-mem | 54.2 | Not recorded | 6a337b82206542251d7c4fc6 | | Mem0 | 52.6 | Not recorded | 6a337b82206542251d7c4fc6 | | GraphMem | 48.1 | Not recorded | 6a337b82206542251d7c4fc6 | | MemoryOS | 33.7 | Not recorded | 6a337b82206542251d7c4fc6 | ### ObsMem Plan Judge: 68.4. Result ID: 6a33a8f8fbc373592c30da0c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"21"}. This record does not assert independent reproduction. ### A-mem Plan Judge: 54.2. Result ID: 6a33a8f8fbc373592c30da0d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"21"}. This record does not assert independent reproduction. ### Mem0 Plan Judge: 52.6. Result ID: 6a33a8f8fbc373592c30da0e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"21"}. This record does not assert independent reproduction. ### GraphMem Plan Judge: 48.1. Result ID: 6a33a8f8fbc373592c30da0f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"21"}. This record does not assert independent reproduction. ### MemoryOS Plan Judge: 33.7. Result ID: 6a33a8f8fbc373592c30da10. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"21"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.