Metraipolis › archive › dc_098a6bd4d0ec

Idea Search: Guiding Tree Search with Ideas to Explore Diverse Scientific Methods — arXiv:2608.08958

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.08958
License (as archived)
CC0-1.0
Archived
2026-10-19T09:35:52.496Z
SHA-256 of the archived text
29e3a486f70c355de4ede54e255a18add8c6dfa28fd494d35a55df905ea0d17d
Stable URL of this page
https://metraipolis.com/documento/dc_098a6bd4d0ec

How to cite

Idea Search: Guiding Tree Search with Ideas to Explore Diverse Scientific Methods — arXiv:2608.08958 — arXiv (en), https://arxiv.org/abs/2608.08958 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_098a6bd4d0ec (Metraipolis archive dc_098a6bd4d0ec, sha256 29e3a486f70c355de4ede54e255a18add8c6dfa28fd494d35a55df905ea0d17d)
BibTeX
@misc{dc098a6bd4d0ec,
  title = {Idea Search: Guiding Tree Search with Ideas to Explore Diverse Scientific Methods — arXiv:2608.08958},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.08958},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_098a6bd4d0ec; sha256 29e3a486f70c355de4ede54e255a18add8c6dfa28fd494d35a55df905ea0d17d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08958. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tree Search-based test-time scaling of LLMs is a powerful tool for automated scientific coding. However, pure Tree Search sometimes struggles with systematic exploration, becoming trapped in local optima, or unproductive loops, especially in the vast search space of scientific methods. To address this limitation, we propose Idea Search, a framework that systematically integrates a dynamic "Idea Bank" into Tree Search. Idea Search involves three steps: (1) decomposing existing methods into atomic ideas, (2) sampling from this bank of ideas to guide branches of code mutations, and (3) dynamically updating the bank with new ideas discovered through execution. On single-cell RNA-sequencing (scRNA-seq) batch integration, Idea Search reliably breaks the plateau of a strong pure Tree Search baseline, improving the mean score from 0.678 to 0.697 and reaching a best score of 0.728. We then characterize which design choices drive these gains: bank augmentation helps bandit sampling but not random sampling, "Exploratory" prompting that prioritizes new ideas surfaces the rare best-performing solutions, while increasing sampling-level exploration is counterproductive.

Tema degli esploratori: scienze della vita e salute (retro-catalogo arXiv: annunci del 2026-08-11 in q-bio.QM).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Genomics (q-bio.GN); Quantitative Methods (q-bio.QM).
Pagina del lavoro: https://arxiv.org/abs/2608.08958 — 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 2026-10-19T09:30:45.630Z dalla pagina https://arxiv.org/catchup/q-bio.QM/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).