Metraipolis › archive › dc_e5a36ff348f5

LabCompiler: A Framework for Verifiable Human-Machine Laboratory Execution from Imperfect Protocols — arXiv:2610.19550

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.19550
License (as archived)
CC0-1.0
Archived
2026-10-15T20:01:45.906Z
SHA-256 of the archived text
d8089c3f5c48db0434c4c6e9f3e195ea966d422623f180d84fbca66a2addfb93
Stable URL of this page
https://metraipolis.com/documento/dc_e5a36ff348f5

How to cite

LabCompiler: A Framework for Verifiable Human-Machine Laboratory Execution from Imperfect Protocols — arXiv:2610.19550 — arXiv (en), https://arxiv.org/abs/2610.19550 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e5a36ff348f5 (Metraipolis archive dc_e5a36ff348f5, sha256 d8089c3f5c48db0434c4c6e9f3e195ea966d422623f180d84fbca66a2addfb93)
BibTeX
@misc{dce5a36ff348f5,
  title = {LabCompiler: A Framework for Verifiable Human-Machine Laboratory Execution from Imperfect Protocols — arXiv:2610.19550},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19550},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e5a36ff348f5; sha256 d8089c3f5c48db0434c4c6e9f3e195ea966d422623f180d84fbca66a2addfb93},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19550. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Closing the loop of AI-driven science requires reliably translating natural-language protocols into executable laboratory workflows despite protocol defects and heterogeneous hardware. Existing approaches often couple scientific interpretation with device-specific code generation, making errors difficult to localize and limiting reuse across laboratory platforms. We introduce LabCompiler, a robust protocol-to-execution framework that transforms imperfect natural-language protocols into verifiable human-machine workflows. Its protocol firewall diagnoses and repairs defects before compilation while preserving unaffected content, guided by troubleshooting knowledge accumulated through perturbation-guided self-evolution. A two-level, device-agnostic graph representation separates experimental semantics from hardware-specific implementation and supports capability-based device assignment with coordinated human execution. We further introduce a protocol recovery benchmark covering four controlled perturbation types and naturally occurring errors collected from protocols written by iGEM participants. Experiments show that LabCompiler outperforms frontier LLMs in protocol error correction while enabling coordinated human-machine execution across heterogeneous, partially automated laboratory settings.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.19550 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T19:35:48.245Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).