Metraipolis › archive › dc_6587f2c3c8ec

LLM sequential decision making under uncertainty in biochemical domains — arXiv:2609.33061

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.33061
License (as archived): CC0-1.0
Archived: 2026-10-07T20:56:26.506Z
SHA-256 of the archived text: d29bad584f7b73be3e02961410ab51de91d8c7f89bdba750eeb300cb80c57317
Stable URL of this page: https://metraipolis.com/documento/dc_6587f2c3c8ec

How to cite

LLM sequential decision making under uncertainty in biochemical domains — arXiv:2609.33061 — arXiv (en), https://arxiv.org/abs/2609.33061 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6587f2c3c8ec (Metraipolis archive dc_6587f2c3c8ec, sha256 d29bad584f7b73be3e02961410ab51de91d8c7f89bdba750eeb300cb80c57317)

BibTeX

@misc{dc6587f2c3c8ec,
  title = {LLM sequential decision making under uncertainty in biochemical domains — arXiv:2609.33061},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33061},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6587f2c3c8ec; sha256 d29bad584f7b73be3e02961410ab51de91d8c7f89bdba750eeb300cb80c57317},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33061. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) are increasingly used to drive scientific discovery. Understanding how LLMs make decisions from new data and memory of the literature is vital before trusting them to design experiments under tight experimental budgets. However, their decision strategies are invisible in the current performance scores used to evaluate research agents. Here, we benchmark five frontier LLMs in a Bayesian Optimization setting against published statistical baselines on seven combinatorial datasets spanning protein engineering, reaction optimization, molecular design, peptide self-assembly, and catalysis. Performance is paired with direct measurements of model beliefs and actions, enabling highly resolved behavior analysis. A prompt ablation that progressively strips context separates memorization from chemical reasoning and from bare categorical optimization. Prior chemical knowledge helps in expectation, but with high variance and occasionally even harms performance. No configuration tested decisively beats a mean statistical baseline across domains. Belief-movement and Martingale diagnostics, corrected here for a measurement-noise bias that mislabels rational agents as irrational, show that models overreact to incoming data rather than entrenching on their priors in the contexts studied here. Interestingly, while LLM actions are exploitative, models sincerely intend to explore and consistently act on that intent. This failure is a competence gap arising from context-stickiness. Removing in-context history restores exploration, indicating that priors and data must be decoupled to achieve effective LLM-driven discovery.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.33061 — 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 2026-10-07T20:29:01.153Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).