{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-11-11-009",
    "source_story_id": "tmp-story-one-policy-household-challenge",
    "edition_id": "mp-2026-11-11-morning-0124",
    "edition_url": "https://themachinepress.com/edition/2026-11-11",
    "position": 9,
    "story_type": "dispatch",
    "section": "robotics",
    "editorial_classification": "editorial",
    "headline": "One Policy Takes On a Hundred Household Tasks",
    "slug": "one-policy-takes-on-a-hundred-household-tasks",
    "dek": "An independent BEHAVIOR Challenge team trained one checkpoint across 211 million demonstration frames, then routed fourteen hard tasks to a coding agent.",
    "summary": "An independent BEHAVIOR Challenge team trained one checkpoint across 211 million demonstration frames, then routed fourteen hard tasks to a coding agent.",
    "body_text": "An independent team reports a single vision-language-action checkpoint for all 100 long-horizon tasks in the 2026 BEHAVIOR Challenge. Its learned policy scored 0.392 Q across the full set after a roughly one-pass, 200,000-step run over 211 million demonstration frames. Fourteen tasks were separately routed to a coding agent with observation and motion tools; on those tasks the authors report mean Q of 0.639 versus 0.108 for the learned policy. The public submission included only part of those agent results and finished with 0.446 Q and 27.3% full-task success.",
    "why_it_matters": "An independent BEHAVIOR Challenge team trained one checkpoint across 211 million demonstration frames, then routed fourteen hard tasks to a coding agent.",
    "limitations": [
      "The public submission included only part of those agent results and finished with 0.446 Q and 27.3% full-task success."
    ],
    "importance": 7,
    "canonical_url": "https://themachinepress.com/story/mp-2026-11-11-009/one-policy-takes-on-a-hundred-household-tasks",
    "json_url": "https://themachinepress.com/story/mp-2026-11-11-009.json",
    "first_published_at": "2026-11-11T09:00:00.000-05:00",
    "modified_at": "2026-11-11T09:00:00.000-05:00",
    "content_status": "new",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-11-11-009-001",
        "text": "An independent BEHAVIOR Challenge team trained one checkpoint across 211 million demonstration frames, then routed fourteen hard tasks to a coding agent.",
        "source_ids": [
          "source-2026-11-11-009"
        ],
        "qualification": "The public submission included only part of those agent results and finished with 0.446 Q and 27.3% full-task success."
      }
    ],
    "source_ids": [
      "source-2026-11-11-009"
    ],
    "tags": [
      "behavior",
      "challenge",
      "one",
      "policy",
      "hundred",
      "household"
    ],
    "image_url": null,
    "corrections": []
  },
  "sources": [
    {
      "source_id": "source-2026-11-11-009",
      "title": "arXiv:2611.14432v1",
      "publisher": "arXiv / Cornell University",
      "url": "https://arxiv.org/abs/2611.14432v1",
      "canonical_url": "https://arxiv.org/abs/2611.14432v1",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-11-10T13:06:16.000-05:00",
      "accessed_at": "2026-11-11T08:26:32.531-05:00",
      "supports_claim_ids": [
        "claim-mp-2026-11-11-009-001"
      ]
    }
  ],
  "corrections": [],
  "publisher": {
    "name": "The Machine Press",
    "url": "https://themachinepress.com",
    "description": "A daily newspaper for the age of artificial intelligence."
  },
  "cite_this_report": {
    "title": "One Policy Takes On a Hundred Household Tasks",
    "publisher": "The Machine Press",
    "published_at": "2026-11-11T09:00:00.000-05:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-11-11-009/one-policy-takes-on-a-hundred-household-tasks"
  }
}