{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-10-26-003",
    "source_story_id": "tmp-story-phronix-capability-learning",
    "edition_id": "mp-2026-10-26-morning-0108",
    "edition_url": "https://themachinepress.com/edition/2026-10-26",
    "position": 3,
    "story_type": "dispatch",
    "section": "developer-tools",
    "editorial_classification": "editorial",
    "headline": "The Agent Turns a Successful Run Into a Reusable Skill",
    "slug": "the-agent-turns-a-successful-run-into-a-reusable-skill",
    "dek": "Phronix validates lessons against tool execution, stores them as capabilities and reports first-attempt reuse on recurring scientific-computing tasks.",
    "summary": "Phronix validates lessons against tool execution, stores them as capabilities and reports first-attempt reuse on recurring scientific-computing tasks.",
    "body_text": "Phronix replaces a manually curated agent harness with a predictor-validator-corrector loop. Tools and skills propose a solution, execution checks it, and the observed result refines a capability store. Across the authors' tasks, learned capabilities solved recurring work on the first attempt in 93 to 95 percent of cases, while warm starts used roughly one quarter to one third of a baseline attempt's tokens. On a 1000 Genomes workflow, the system passed all 11 correctness checks compared with six for the baseline harness. The larger coding-agent gains come from the selected evaluation setup and should not be read as universal model upgrades; the evidence supports reusable, execution-checked harness knowledge under the tested tasks.",
    "why_it_matters": "Phronix validates lessons against tool execution, stores them as capabilities and reports first-attempt reuse on recurring scientific-computing tasks.",
    "limitations": [
      "The larger coding-agent gains come from the selected evaluation setup and should not be read as universal model upgrades; the evidence supports reusable, execution-checked harness knowledge under the tested tasks."
    ],
    "importance": 9,
    "canonical_url": "https://themachinepress.com/story/mp-2026-10-26-003/the-agent-turns-a-successful-run-into-a-reusable-skill",
    "json_url": "https://themachinepress.com/story/mp-2026-10-26-003.json",
    "first_published_at": "2026-10-26T09:00:00.000-04:00",
    "modified_at": "2026-10-26T09:00:00.000-04:00",
    "content_status": "new",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-10-26-003-001",
        "text": "Phronix validates lessons against tool execution, stores them as capabilities and reports first-attempt reuse on recurring scientific-computing tasks.",
        "source_ids": [
          "source-2026-10-26-003"
        ],
        "qualification": "The larger coding-agent gains come from the selected evaluation setup and should not be read as universal model upgrades; the evidence supports reusable, execution-checked harness knowledge under the tested tasks."
      }
    ],
    "source_ids": [
      "source-2026-10-26-003"
    ],
    "tags": [
      "agents",
      "skills",
      "scientific computing",
      "memory"
    ],
    "image_url": "https://themachinepress.com/issues/2026-10-26/capability-store-servers.webp",
    "corrections": []
  },
  "sources": [
    {
      "source_id": "source-2026-10-26-003",
      "title": "arXiv preprint 2610.31789, original v1",
      "publisher": "arXiv",
      "url": "https://arxiv.org/abs/2610.31789v1",
      "canonical_url": "https://arxiv.org/abs/2610.31789v1",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-10-22T14:29:52.000-04:00",
      "accessed_at": "2026-10-26T08:26:57.002-04:00",
      "supports_claim_ids": [
        "claim-mp-2026-10-26-003-001"
      ]
    }
  ],
  "corrections": [],
  "publisher": {
    "name": "The Machine Press",
    "url": "https://themachinepress.com",
    "description": "A daily newspaper for the age of artificial intelligence."
  },
  "cite_this_report": {
    "title": "The Agent Turns a Successful Run Into a Reusable Skill",
    "publisher": "The Machine Press",
    "published_at": "2026-10-26T09:00:00.000-04:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-10-26-003/the-agent-turns-a-successful-run-into-a-reusable-skill"
  }
}