{
  "schema_version": "1.1",
  "id": "s13:https://arxiv.org/abs/2609.30249v1",
  "slug": "2609-30249v1-1y1rmv8",
  "url": "https://feed7.dev/p/2609-30249v1-1y1rmv8",
  "title": "RAPID: Robot Agentic Programming from Demonstrations",
  "why_included": "RAPID turns one visual demonstration into an executable, testable robot program, showing how agent loops can derive their own specifications, tools, and verification environment.",
  "summary": "RAPID infers a task specification, robot action primitives, and an execution environment from **one visual demonstration**, then generates, verifies, and refines a program.",
  "practical_implication": "The reusable pattern for coding-agent builders is the closed loop: derive executable tests and tools from an example, run the program, and refine it against observed behavior. Its object-centric representation also separates strategy from scene-specific geometry.",
  "agent_context": "RAPID infers a task specification, robot action primitives, and an execution environment from **one visual demonstration**, then generates, verifies, and refines a program.\n\nThe reusable pattern for coding-agent builders is the closed loop: derive executable tests and tools from an example, run the program, and refine it against observed behavior. Its object-centric representation also separates strategy from scene-specific geometry.\n\nThe evidence covers simulation and a Franka arm across **eight contact-rich tasks**, plus LIBERO-Pro evaluations. The abstract reports generalization across several variations but provides no comparative rates.",
  "source": {
    "name": "arXiv",
    "url": "https://arxiv.org/abs/2609.30249v1",
    "published_at": "2026-09-24T17:58:21.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Paper",
  "layer": "agent",
  "domains": [
    "coding",
    "image"
  ],
  "topics": [
    "coding-agents",
    "harness-engineering",
    "tool-use"
  ],
  "verification": {
    "status": "needs_review",
    "label": "Needs Review",
    "method": "unverified",
    "verified_at": null
  },
  "uncertainty": [
    "The evidence covers simulation and a Franka arm across **eight contact-rich tasks**, plus LIBERO-Pro evaluations. The abstract reports generalization across several variations but provides no comparative rates."
  ],
  "connected_context": {
    "meaning": "RAPID extends example-driven agent programming into physical control: one demonstration can seed not only a program but its task specification, action vocabulary, execution environment, and verification loop. The object-centric split between strategy and geometry provides a concrete route to reuse across scene variations, though eight tasks and unquantified comparative results leave the breadth of that reuse unsettled.",
    "corpus_size": 875,
    "generated_at": "2026-09-25T09:07:29.967Z",
    "connections": [
      {
        "title": "Show-Harness: Just a VLM Agent Can Play Robots",
        "source_name": "arXiv",
        "source_url": "https://arxiv.org/abs/2609.10522v1",
        "feed7_url": "https://feed7.dev/p/2609-10522v1-1lobtfw",
        "reason": "Both isolate model intent from robot-specific execution through a compact action layer; RAPID adds a method for inferring that layer and its environment from a single demonstration."
      },
      {
        "title": "Agents Without Code: Skills, YAML, and Filesystems Replaced Python — Philipp Schmid, Google DeepMind",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=fjF8EKnxKCU",
        "feed7_url": "https://feed7.dev/p/agents-without-code-skills-yaml-and-filesystems-replaced-python-philipp-0t7a4s8",
        "reason": "RAPID reinforces the idea that agent definitions can be reduced around reusable tools, while also confirming that generated programs still need an external execution-and-evaluation loop."
      },
      {
        "title": "From coding to Knowledge work agents — Karan Vaidya, Composio",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=xxfMT-bPEmU",
        "feed7_url": "https://feed7.dev/p/from-coding-to-knowledge-work-agents-karan-vaidya-composio-14b5s5w",
        "reason": "Its generate, verify, and refine cycle supplies a concrete embodied instance of the broader requirement for verification and preflight execution around consequential tool use."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-09-24T17:58:21.000Z",
  "modified_at": "2026-09-24T17:58:21.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/2609-30249v1-1y1rmv8",
    "json": "https://feed7.dev/p/2609-30249v1-1y1rmv8.json",
    "markdown": "https://feed7.dev/p/2609-30249v1-1y1rmv8.md"
  }
}