Metraipolis › archive › dc_79c675eec751
La Agente Óptima: Towards Agentic Self-Driving Laboratories — arXiv:2609.04564
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.04564
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T22:18:19.428Z
- SHA-256 of the archived text
c2c95969d5162a6ae1c1325e2c02f6687338558a44db27e8f7ea0d291ca206ee- Stable URL of this page
https://metraipolis.com/documento/dc_79c675eec751
How to cite
La Agente Óptima: Towards Agentic Self-Driving Laboratories — arXiv:2609.04564 — arXiv (en), https://arxiv.org/abs/2609.04564 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_79c675eec751 (Metraipolis archive dc_79c675eec751, sha256 c2c95969d5162a6ae1c1325e2c02f6687338558a44db27e8f7ea0d291ca206ee)
BibTeX
@misc{dc79c675eec751,
title = {La Agente Óptima: Towards Agentic Self-Driving Laboratories — arXiv:2609.04564},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.04564},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_79c675eec751; sha256 c2c95969d5162a6ae1c1325e2c02f6687338558a44db27e8f7ea0d291ca206ee},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04564. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Self-driving laboratories (SDLs) combine automated experimentation with adaptive decision-making to accelerate scientific discovery. Their operation nevertheless often depends on human specialists who translate scientific objectives into executable closed-loop campaigns. Specialists adjust them as data and operating conditions change. Here, we present La Agente Óptima, an agentic framework that constructs and supervises Bayesian optimization campaigns across computational and experimental systems while maintaining a persistent optimization state. By separating large language model (LLM) reasoning from executed campaigns, Óptima runs repetitive optimization loops consistently, returns control to the agent only when progress requires interpretation or campaign revision, and keeps every decision auditable. We evaluate Óptima across ablation studies, five digital discovery tasks, and two physical platforms. Throughout, Óptima maintained executable campaigns as both the scientific problem and execution environment evolved. In a closed-loop contact angle optimization campaign, Óptima identified and corrected a mid-run measurement failure, bringing the contact angle from 71.4 to 67.8 degrees, just above the 64-66 degree range. From this result, Óptima correctly inferred that the target was likely unattainable with the available reagents and recommended changing the formulation. In a five-day multi-objective flow-chemistry campaign, Óptima increased the yield from 30% to 59% over 23 experiments. Despite substantial inference costs, it cost less and used substantially less starting material than a human-directed campaign, while selecting a more mass-efficient operating point. These results show that LLM-based agents can make rigorous, long-running optimization campaigns accessible to domain scientists without specialist setup, expanding the scope of SDLs. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.MA). Categorie arXiv: Artificial Intelligence (cs.AI) ; Multiagent Systems (cs.MA); Chemical Physics (physics.chem-ph). Pagina del lavoro: https://arxiv.org/abs/2609.04564 — 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 2026-10-16T22:09:19.002Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).