pipette
ENEnglish

SEA-Lab: Experiment-grounded recursive self-improvement in an automated laboratory

Y. Jiang, R. Gong, H. Chen, X. Wang, B. Zhang, Q. Wang, T. Zhang, M. Fan, X. Mao, Z. Hou, Y. Hu, Y. Gao, C.-Z. Wang

Preprint

En palabras de los autores

AI scientists can generate hypotheses, plans, and protocols. Translating these outputs into reliable experiments requires adapting them to local equipment and resources using feedback from observed outcomes. A key challenge is to retain laboratory execution feedback as reusable knowledge for subsequent planning. We present SEA-Lab (Self-Evolving Autonomous Lab), which combines an environment-grounded Dry-Lab Harness that generates protocols and machine-readable procedures, a wet-lab execution harness that coordinates heterogeneous devices and records execution traces and experimental measurements, and a recursive self-improvement mechanism that uses physical feedback to revise reusable execution policies and experimental strategies. Across three rounds of review on 219 tasks, protocol-review pass rates reached 90.41%. On 66 automation-eligible tasks, mean virtual-validation pass rates increased from 16.7% to 87.7% after two revisions. On two liquid handlers, runtime fell by 45.8% for plate replication, 34.1% for well rearrangement, and up to 68.6% for sample normalization. We demonstrated the system in a phage-display experiment linking four automated experimental steps: molecular cloning, phage titration, sample normalization, and ELISA screening. Of 96 starting samples, 93 yielded a sequence-correct clone, and primary ELISA screening identified ten candidates. These results illustrate how laboratory feedback can guide planning around local resources, refine execution on different laboratory instruments, and inform method revision based on experimental results.

Resultado principalEl resumen no menciona limitaciones.

En palabras simples Resumen con IA

Los autores construyeron SEA-Lab, un sistema que permite a científicos de IA planificar experimentos, ejecutarlos en equipos de laboratorio reales y aprender de los resultados. En un experimento de exhibición de fagos con cuatro pasos automatizados, 93 de 96 muestras produjeron clones correctos. Los resultados muestran cómo la retroalimentación del laboratorio puede guiar la planificación, refinar la ejecución en diferentes instrumentos y mejorar los métodos basándose en los resultados.

Escrito por Kimi K2.5 usando solo el abstract de arriba. Jev verificó que cada oración esté respaldada por las oraciones del abstract que cita y eliminó las que no. Pasá el cursor por una oración para ver de dónde sale. Se eliminaron 2 oraciones por no estar respaldadas por el abstract.

Apareció: martes, 17 de noviembre. bioRxiv. Preprint, todavía sin revisión por pares.

DOI: 10.64898/2026.11.12.766090