Agentic generation of verifiable rules for deterministic, self-expanding reaction classification
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 i
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorDaniel Armstrong →
Agentic generation of verifiable rules for deterministic, self-expanding reaction classification
- Linked via arxiv authorMaarten Dobbelaere →
Agentic generation of verifiable rules for deterministic, self-expanding reaction classification
- Linked via arxiv authorValentas Olikauskas →
Agentic generation of verifiable rules for deterministic, self-expanding reaction classification
- Linked via arxiv authorHelena Avila →
Agentic generation of verifiable rules for deterministic, self-expanding reaction classification
- Linked via arxiv authorOctavian Susanu →
Agentic generation of verifiable rules for deterministic, self-expanding reaction classification
- Linked via arxiv authorJérôme Waser →
Agentic generation of verifiable rules for deterministic, self-expanding reaction classification
- Linked via arxiv authorPhilippe Schwaller →
Agentic generation of verifiable rules for deterministic, self-expanding reaction classification