Metraipolis › archive › dc_f1b61afa0deb

Solvent: Long-Horizon Reasoning for Multi-Step Retrosynthesis — arXiv:2610.32308

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.32308
License (as archived)
CC0-1.0
Archived
2026-10-26T19:50:33.894Z
SHA-256 of the archived text
c13d7ce38b5920a55836e2da0e12eaa5b50f6db50e72404e040a2250e9b92e3f
Stable URL of this page
https://metraipolis.com/documento/dc_f1b61afa0deb

How to cite

Solvent: Long-Horizon Reasoning for Multi-Step Retrosynthesis — arXiv:2610.32308 — arXiv (en), https://arxiv.org/abs/2610.32308 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f1b61afa0deb (Metraipolis archive dc_f1b61afa0deb, sha256 c13d7ce38b5920a55836e2da0e12eaa5b50f6db50e72404e040a2250e9b92e3f)
BibTeX
@misc{dcf1b61afa0deb,
  title = {Solvent: Long-Horizon Reasoning for Multi-Step Retrosynthesis — arXiv:2610.32308},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.32308},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f1b61afa0deb; sha256 c13d7ce38b5920a55836e2da0e12eaa5b50f6db50e72404e040a2250e9b92e3f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32308. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-step retrosynthesis requires recursively transforming a target molecule through successive reaction steps into purchasable building blocks, and recent work has begun to draw on large language model (LLM) reasoning to tackle the task. In its latest evolution, LLM reasoning has entered the long-horizon regime: models pursue objectives across interdependent steps, interact with environments, and adapt to feedback. This shift has markedly advanced LLM capabilities, as illustrated by breakthroughs in AI-driven mathematical research. At this frontier, we introduce Solvent, an 8B LLM that successfully extends long-horizon reasoning to multi-step retrosynthesis. Through a two-round post-training curriculum, Solvent learns to interleave iterative synthesis planning, external availability verification, and adaptive route revision. Experiments show that, following a $2.1\times$ performance boost from RL, Solvent scores 61.86% across four benchmarks, surpassing mid-scale language models and prior search-based retrosynthesis systems, and rivaling frontier trillion-parameter LLMs.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.32308 — 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 2026-10-26T19:45:33.306Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).