{"ID":5551601,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-04T15:13:22.648032999Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.01061","arxiv_id":"2607.01061","title":"Agentic generation of verifiable rules for deterministic, self-expanding reaction classification","abstract":"Computer-assisted synthesis planning breaks target molecules into accessible precursors using large libraries of reaction rules that assign each transformation a deterministic, interpretable label. But chemistry is long-tailed, making manual encoding intractable, and existing tools rely on fixed rulesets that cannot adapt to new chemistries. Here we present a fully automated pipeline in which a multi-agent framework of large language models (LLMs) classifies reactions and writes the rules themselves across 665,901 US patent reactions, generating each rule under a verification loop that tests it against the corpus. It expands a standard taxonomy from 68 to 14,073 classes without human curation. With a lightweight fingerprint classifier, it classifies 97.7\\% of unseen reactions, matching a leading proprietary classifier while resolving chemistry more finely and extending on demand to chemistry outside its training distribution. The result is a living reactivity database and a general route to turning generative models into reliable, self-expanding symbolic systems.","short_abstract":"Computer-assisted synthesis planning breaks target molecules into accessible precursors using large libraries of reaction rules that assign each transformation a deterministic, interpretable label. But chemistry is long-tailed, making manual encoding intractable, and existing tools rely on fixed rulesets that cannot ad...","url_abs":"https://arxiv.org/abs/2607.01061","url_pdf":"https://arxiv.org/pdf/2607.01061v1","authors":"[\"Daniel Armstrong\",\"Maarten Dobbelaere\",\"Valentas Olikauskas\",\"Helena Avila\",\"Octavian Susanu\",\"Jérôme Waser\",\"Philippe Schwaller\"]","published":"2026-07-01T15:24:06Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}