{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-10-16-002",
    "source_story_id": "tmp-feature-libero-perm-personalization",
    "edition_id": "mp-2026-10-16-morning-0098",
    "edition_url": "https://themachinepress.com/edition/2026-10-16",
    "position": 2,
    "story_type": "secondary",
    "section": "robotics",
    "editorial_classification": "editorial",
    "headline": "Finishing the Chore Is Not the Same as Doing It Your Way",
    "slug": "finishing-the-chore-is-not-the-same-as-doing-it-your-way",
    "dek": "LIBERO-PeRM separates task success from preference satisfaction across 312 simulated manipulation tasks—and current policies struggle before adaptation.",
    "summary": "LIBERO-PeRM separates task success from preference satisfaction across 312 simulated manipulation tasks—and current policies struggle before adaptation.",
    "body_text": "A household robot can put an object in the right place and still ignore how its user wanted the task done. LIBERO-PeRM turns that distinction into a controlled benchmark spanning motion, skill and user-profile preferences across five suites and 312 tasks. The authors test zero-shot following, learning from demonstrations, data efficiency, generalization, composition and conflict handling. Current vision-language-action policies struggled with zero-shot personalization, while supervised fine-tuning made preferences learnable. Mixed training preserved more of the no-preference behavior than sequential adaptation and benefited from contextual prompts, but it could weaken motion-preference learning; generalization and conflicting preferences remained difficult. The benchmark is simulated and limited to language-expressible preferences that can be evaluated automatically, so it does not establish safe household deployment. Its useful contribution is to stop counting mere completion as proof that a robot served the person using it.",
    "why_it_matters": "LIBERO-PeRM separates task success from preference satisfaction across 312 simulated manipulation tasks—and current policies struggle before adaptation.",
    "limitations": [
      "The benchmark is simulated and limited to language-expressible preferences that can be evaluated automatically, so it does not establish safe household deployment."
    ],
    "importance": 9,
    "canonical_url": "https://themachinepress.com/story/mp-2026-10-16-002/finishing-the-chore-is-not-the-same-as-doing-it-your-way",
    "json_url": "https://themachinepress.com/story/mp-2026-10-16-002.json",
    "first_published_at": "2026-10-16T09:00:00.000-04:00",
    "modified_at": "2026-10-16T09:00:00.000-04:00",
    "content_status": "new",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-10-16-002-001",
        "text": "LIBERO-PeRM separates task success from preference satisfaction across 312 simulated manipulation tasks—and current policies struggle before adaptation.",
        "source_ids": [
          "source-2026-10-16-002"
        ],
        "qualification": "The benchmark is simulated and limited to language-expressible preferences that can be evaluated automatically, so it does not establish safe household deployment."
      }
    ],
    "source_ids": [
      "source-2026-10-16-002"
    ],
    "tags": [
      "robotics",
      "personalization",
      "preference learning",
      "benchmarks"
    ],
    "image_url": "https://themachinepress.com/issues/2026-10-16/feature-personalized-manipulation.png",
    "corrections": []
  },
  "sources": [
    {
      "source_id": "source-2026-10-16-002",
      "title": "arXiv preprint 2610.22372, original v1",
      "publisher": "arXiv / submitting research authors",
      "url": "https://arxiv.org/abs/2610.22372v1",
      "canonical_url": "https://arxiv.org/abs/2610.22372v1",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-10-15T13:59:59.000-04:00",
      "accessed_at": "2026-10-16T08:26:36.400-04:00",
      "supports_claim_ids": [
        "claim-mp-2026-10-16-002-001"
      ]
    }
  ],
  "corrections": [],
  "publisher": {
    "name": "The Machine Press",
    "url": "https://themachinepress.com",
    "description": "A daily newspaper for the age of artificial intelligence."
  },
  "cite_this_report": {
    "title": "Finishing the Chore Is Not the Same as Doing It Your Way",
    "publisher": "The Machine Press",
    "published_at": "2026-10-16T09:00:00.000-04:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-10-16-002/finishing-the-chore-is-not-the-same-as-doing-it-your-way"
  }
}