Metraipolis › archive › dc_902dbade3029

LabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery — arXiv:2610.00675

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.00675
License (as archived)
CC0-1.0
Archived
2026-10-06T12:10:42.851Z
SHA-256 of the archived text
14b3cb70ecff9bc661c273eba4675c163dbc9cac26475c1bdbd25b943378696a
Stable URL of this page
https://metraipolis.com/documento/dc_902dbade3029

How to cite

LabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery — arXiv:2610.00675 — arXiv (en), https://arxiv.org/abs/2610.00675 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_902dbade3029 (Metraipolis archive dc_902dbade3029, sha256 14b3cb70ecff9bc661c273eba4675c163dbc9cac26475c1bdbd25b943378696a)
BibTeX
@misc{dc902dbade3029,
  title = {LabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery — arXiv:2610.00675},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00675},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_902dbade3029; sha256 14b3cb70ecff9bc661c273eba4675c163dbc9cac26475c1bdbd25b943378696a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00675. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Evolutionary approaches to LLM-driven discovery often generate new programs from a small set of selected ancestors. This keeps contexts manageable but can omit useful evidence from other experiments, whereas including the full experimental history produces long, redundant contexts. We introduce a simple, single-agent discovery harness built around LabBook, an agent-maintained memory that serves two complementary roles: guiding retrieval of relevant evidence from a complete experimental log and informing the generation of new solutions. At each iteration, the same agent combines its memory with retrieved evidence and jointly produces the next program and an updated LabBook. This separates complete history retention from selective context construction, without requiring an explicit population or branching search structure. On 49 Frontier-CS problems, LabBook improves the observed quality-cost trade-off over the evaluated evolutionary baselines with two backbones, while remaining competitive across nine additional mathematical, systems, and heuristic-design tasks. Code will be released at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.00675 — 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 2026-10-06T10:21:28.100Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).