physics.chem-phNov 12, 2026

Vibe synthesis: hierarchical agentic decision-making for intent-driven multistep molecule synthesis

Authors: Jie Chen, Guikun Chen, Feng Wan, Ning Xu, Wen Liu, Yixiang Ruan, Yiyi Qiu, Haohua Li, 

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.

Explore similar work

CardsList
  1. Strategy-first synthesis planning for complex natural products

    Aug 7, 2026Daniel Armstrong, Xuan-Vu Nguyen, Octavian Susanu +15LLM Agent Planning

  2. My Chemical Harness: Evolutionary Molecular Design over Synthetic Pathways with Large Language Model Agents

    Jun 8, 2026César Ojeda, Darius A. Faroughy, Maryam Karimi +3Molecular OptimizationLLM Agents

  3. Hypothesis-Driven Autonomous Materials Synthesis with Multimodal LLM Agents

    Sep 16, 2026Izumi Takahara, Kazunori Nishio, Akira Aiba +4LLM Agent Skill LearningAutonomous Scientific Discovery