Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AgentChemist: A Multi-Agent Experimental Robotic Platform Integrating Chemical Perception and Precise Control

Xiangyi Wei, Fei Wang, Haotian Zhang, Xin An, Haitian Zhu, Lianrui Hu, Yang Li, Changbo Wang, Xiao He

Abstract

Chemical laboratory automation has long been constrained by rigid workflows and poor adaptability to the long-tail distribution of experimental tasks. While most automated platforms perform well on a narrow set of standardized procedures, real laboratories involve diverse, infrequent, and evolving operations that fall outside predefined protocols. This mismatch prevents existing systems from generalizing to novel reaction conditions, uncommon instrument configurations, and unexpected procedural variations. We present a multi-agent robotic platform designed to address this long-tail challenge through collaborative task decomposition, dynamic scheduling, and adaptive control. The system integrates chemical perception for real-time reaction monitoring with feedback-driven execution, enabling it to adjust actions based on evolving experimental states rather than fixed scripts. Validation via acid-base titration demonstrates autonomous progress tracking, adaptive dispensing control, and reliable end-to-end experiment execution. By improving generalization across diverse laboratory scenarios, this platform provides a practical pathway toward intelligent, flexible, and scalable laboratory automation.

AgentChemist: A Multi-Agent Experimental Robotic Platform Integrating Chemical Perception and Precise Control

Abstract

Chemical laboratory automation has long been constrained by rigid workflows and poor adaptability to the long-tail distribution of experimental tasks. While most automated platforms perform well on a narrow set of standardized procedures, real laboratories involve diverse, infrequent, and evolving operations that fall outside predefined protocols. This mismatch prevents existing systems from generalizing to novel reaction conditions, uncommon instrument configurations, and unexpected procedural variations. We present a multi-agent robotic platform designed to address this long-tail challenge through collaborative task decomposition, dynamic scheduling, and adaptive control. The system integrates chemical perception for real-time reaction monitoring with feedback-driven execution, enabling it to adjust actions based on evolving experimental states rather than fixed scripts. Validation via acid-base titration demonstrates autonomous progress tracking, adaptive dispensing control, and reliable end-to-end experiment execution. By improving generalization across diverse laboratory scenarios, this platform provides a practical pathway toward intelligent, flexible, and scalable laboratory automation.
Paper Structure (30 sections, 9 equations, 8 figures, 4 tables, 1 algorithm)

This paper contains 30 sections, 9 equations, 8 figures, 4 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Results
  3. Problem Definition
  4. AgentChemist workflow
  5. Agents Design
  6. Planner Agent
  7. Vision Supervisor Agent
  8. Action Agent
  9. Audio Supervisor Agent
  10. Summarizer Agent
  11. Statistics-based Chemical Quantity Logger
  12. High-Confidence Quantity Logging Mechanism
  13. An example of a closed-loop titration experiment driven by AgentChemist
  14. Acid-base titration experiment
  15. Complexometric titration experiment
  16. ...and 15 more sections

Figures (8)

  • Figure 1: The motivation for a multi-agent experimental robotic platform. Traditional rigid automation (left) is characterized by fixed protocols, blind execution, and fragile adaptation. In contrast, AgentChemist introduces dynamic workflows through multi-agent task decomposition, adaptive perception with real-time monitoring, and robust, instrument-integrated resilience to address long-tail challenges in the laboratory.
  • Figure 2: AgentChemist Workflow: AgentChemist receives user instructions, plans experimental protocols, drives robots to perform specific experimental operations, records results in real time, and finally returns the experimental report to the user.
  • Figure 3: AgentChemist workflow
  • Figure 4: State Machine of the Statistics-based Chemical Quantity Logger
  • Figure 5: The Process of AgentChemist Driving the Evolution of FSM $\mathcal{S}$ in Acid-Base Titration Experiments
  • ...and 3 more figures