Metraipolis › archive › dc_6299fb79d80d
An Agentic Retrobiosynthesis Framework with Learned Frontier Selection — arXiv:2608.30702
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.30702
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:52:57.948Z
- SHA-256 of the archived text
e155ee16503b6c4ddcb3b1c0c40f5e2a9570177c792d864a1e200db69203d557- Stable URL of this page
https://metraipolis.com/documento/dc_6299fb79d80d
How to cite
An Agentic Retrobiosynthesis Framework with Learned Frontier Selection — arXiv:2608.30702 — arXiv (en), https://arxiv.org/abs/2608.30702 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6299fb79d80d (Metraipolis archive dc_6299fb79d80d, sha256 e155ee16503b6c4ddcb3b1c0c40f5e2a9570177c792d864a1e200db69203d557)
BibTeX
@misc{dc6299fb79d80d,
title = {An Agentic Retrobiosynthesis Framework with Learned Frontier Selection — arXiv:2608.30702},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.30702},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6299fb79d80d; sha256 e155ee16503b6c4ddcb3b1c0c40f5e2a9570177c792d864a1e200db69203d557},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30702. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models are increasingly used as agents for multistep retrosynthesis, raising the question of how much their search policy contributes independently of the underlying reaction model. We investigate this question in a biological setting through rule-based retrobiosynthesis: a deterministic biochemical engine generates the same validated transitions for every method, searching for routes that terminate in metabolites available to an \emph{Escherichia coli} chassis, while the policy only selects which frontier molecule to expand next. Prompted and LoRA-tuned Qwen2.5-7B policies use a strict choice-only interface. The fine-tuned policy reaches $65\pm1$\% solve rate at 10 expansions on LASER versus 59\% for MCTS, and at 200 expansions reaches $78\pm1$\% versus 75\% on LASER, $88\pm3$\% versus 80\% on the RetroPath RL Golden benchmark, and $63\pm2$\% versus 45\% on the BioNavi-NP benchmark. Fine-tuning also consistently outperforms direct prompting. These results show that route-supervised frontier selection can improve budgeted search without altering biochemical generation, although performance remains dependent on frontier construction and reaction ranking.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.30702 — 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 2026-10-17T07:28:26.899Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).