Vibe synthesis: hierarchical agentic decision-making for intent-driven multistep molecule synthesis
Organizations: College of Chemical and Biological Engineering, Zhejiang University, Hangzhou 310027, China. · Key Laboratory of Intelligent Manufacturing for Functional Chemicals, ZJU-Hangzhou Global Scientific and Technological Innovation Center, Hangzhou 311215, China. · The State Key Lab of Brain-Machine Intelligence, Zhejiang University, Hangzhou, 311121, China. · Harvard Medical School, Boston 02115, USA. ·
Abstract
The ability to construct complex molecules underpins advances in medicine and the molecular sciences. Yet long-horizon multistep synthesis requires decisions to be revised as evidence accumulates across chemically dependent operations, a capability not readily supported by artificial-intelligence tools and automated platforms organized around predefined tasks and hard-coded workflows. Here we propose and demonstrate a vibe synthesis system (VibeSyn), an intent-driven architecture in which hierarchical agents translate chemist-defined molecular objectives and accumulating evidence into adaptive decisions executed through computational tools and laboratory automation. We evaluate VibeSyn in three demonstrations of increasing scope and autonomy, progressing from evidence-grounded experimental decisions to adaptive execution of a ten-step total synthesis of catharanthine and structure-to-compound synthesis of cyclic peptides containing unnatural amino acids (uAAs). Across the long-horizon campaigns, active human input and simple confirmation account for less than 7.5% and 5.2%, respectively, of recorded workflow actions and outcomes. VibeSyn points towards a future in which chemists define synthetic intent and agent-directed laboratories autonomously navigate the evolving experimental trajectory required to deliver the target compound.
Scientific Workflow Automation
Scientific workflow automation uses software, AI agents, and laboratory systems to plan, execute, validate, and reproduce research tasks.
See all 174 papers