Metraipolis › archive › dc_7acdc514f4c1

RxnOptBench: Benchmarking LLMs for Reaction-Condition Optimization in Organic Methodology — arXiv:2610.02242

Source
arXiv
Original
https://arxiv.org/abs/2610.02242
License (as archived)
CC0-1.0
Archived
2026-10-05T22:49:51.133Z
SHA-256 of the archived text
35d564b23b28ad4f32403998472341c84357931dfa066904d9406e664b3478d4
Stable URL of this page
https://metraipolis.com/documento/dc_7acdc514f4c1

How to cite

RxnOptBench: Benchmarking LLMs for Reaction-Condition Optimization in Organic Methodology — arXiv:2610.02242 — arXiv, https://arxiv.org/abs/2610.02242 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7acdc514f4c1 (Metraipolis archive dc_7acdc514f4c1, sha256 35d564b23b28ad4f32403998472341c84357931dfa066904d9406e664b3478d4)
BibTeX
@misc{dc7acdc514f4c1,
  title = {RxnOptBench: Benchmarking LLMs for Reaction-Condition Optimization in Organic Methodology — arXiv:2610.02242},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02242},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7acdc514f4c1; sha256 35d564b23b28ad4f32403998472341c84357931dfa066904d9406e664b3478d4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02242. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Chemical reaction-condition optimization -- choosing the catalyst, ligand, solvent, reagent, temperature, time, and atmosphere that jointly maximize yield and stereoselectivity -- is a central, judgement-laden subtask of organic methodology research that large language models are increasingly expected to support. Yet existing chemistry benchmarks evaluate reaction-class labelling, retrosynthesis, or SMILES manipulation, and do not ask models to read a real condition-screening table and pick the best set. We introduce RxnOptBench, a benchmark whose every option and precedent is a real wet-lab entry mined from the optimization tables of organic-methodology papers published in 2025, graded by a continuous relative score derived from a declared headline utility that combines reported yield with enantiomeric excess (ee), diastereomeric ratio (dr), and regioisomeric ratio (rr), and equipped with a paired precedents-vs-no-precedents design that isolates in-context use of literature evidence from parametric memorization. Across nine frontier LLMs and three Chemistry LLMs, even the best models leave substantial headroom: chemistry-specialized models fall to the random-baseline floor on multi-axis selection, while open-weight models have closed most of the gap to proprietary frontier models. We release the final human-reviewed benchmark test set and evaluation code.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Chemical Physics (physics.chem-ph) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.02242 — 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 2026-10-05T22:45:55.729Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).