CoChat

A Multiagent-Driven Robotic AI Chemist Enabling Autonomous Chemical Research On Demand

Open access

The DOI matches its Crossref record; 82 of the 82 references it cites were found in a registry or an index.

Abstract

The successful integration of large language models (LLMs) into laboratory workflows has demonstrated robust capabilities in natural language processing, autonomous task execution, and collaborative problem-solving. This offers an exciting opportunity to realize the dream of autonomous chemical research on demand. Here, we report a robotic AI chemist powered by a hierarchical multiagent system, ChemAgents, based on an on-board Llama-3.1-70B LLM, capable of executing complex, multistep experiments with minimal human intervention. It operates through a Task Manager agent that interacts with human researchers and coordinates four role-specific agents─Literature Reader, Experiment Designer, Computation Performer, and Robot Operator─each leveraging one of four foundational resources: a comprehensive Literature Database, an extensive Protocol Library, a versatile Model Library, and a state-of-the-art Automated Lab. We demonstrate its versatility and efficacy through six experimental tasks of varying complexity, ranging from straightforward synthesis and characterization to more complex exploration and screening of experimental parameters, culminating in the discovery and optimization of functional materials. Additionally, we introduce a seventh task, where ChemAgents is deployed in a new robotic chemistry lab environment to autonomously perform photocatalytic organic reactions, highlighting ChemAgents's scalability and adaptability. Our multiagent-driven robotic AI chemist showcases the potential of on-demand autonomous chemical research to accelerate discovery and democratize access to advanced experimental capabilities across academic disciplines and industries.

Overview

Integrity signals

Registry

Crossref · 10.1021/jacs.4c17738

Cites

82 of 82 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

The text we found for this paper looks like another document, so its claims and self-check weren’t run. The registry and citation checks still apply.

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The text we found for this paper looks like another document, so the self-check wasn’t run.

Citations

Cites

Show all 82 references

Research works printed but not linked: 4

  1. Chowdhery A., 2023, J. Mach. Learn. Res., 24, 1
  2. Shinn N., 2023, Adv. Neural Inf. Process. Syst., 36, 8634
  3. Shen Y., 2023, Adv. Neural Inf. Process. Syst., 36, 38154
  4. Driess D., 2023, Proc. 40th Int. Conf. Mach. Learn., 202, 8469

Cited by

Metadata

Authors
Song, T., Luo, M., Zhang, X., Chen, L., Huang, Y., Cao, J., Zhu, Q., Liu, D., Zhang, B., Zou, G., Zhang, G., Zhang, F., Shang, W., Fu, Y., Jiang, J., & Luo, Y.
Affiliations
University of Science and Technology of China (CN)
Corresponding author
  • Chen, Linjiang
  • Zhang, Fei
  • Shang, Weiwei
  • Fu, Yao
  • Jiang, Jun
  • Luo, Yi
Venue
Journal of the American Chemical Society
Published
2025-03-08
Volume
147
Issue
15
Pages
12534-12545
ISSN
  • 0002-7863 (ISSN-L)
  • 1520-5126
OpenAlex
W4408247476
Cited by
171
References
68
Citations by year
2026: 112 · 2025: 59
FWCI
36.12
Type
journal article
Language
en
Locations
  • Journal of the American Chemical Society (publishedVersion)
  • PubMed (publishedVersion)
  • University of Birmingham Research Portal (University of Birmingham) (publishedVersion, other-oa)
Funders
  • Natural Science Foundation of Henan Province (242300421138)
  • National Key Research and Development Program of China (2024YFB3817302)
  • National Natural Science Foundation of China (22025304, 22033007, 22103076, 22303091, U22A2056)
  • Natural Science Foundation of Anhui Province (2108085QB63)
  • Chinese Academy of Sciences (XDB0450302, YSBR-005)
  • USTC Research Funds of the Double First-Class Initiative (YD9990002032)
  • Joint Fund of Henan Province Science and Technology R&D Program (235200810107)
  • Innovation Program for Quantum Science and Technology (2021ZD0303303)
Topics
  • Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
  • Social Sciences › Education › Various Chemistry Research Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
Keywords
multi-agent systems, large language models, laboratory automation, task coordination, bibliographic databases, parameter screening

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

A second model labelled each claim on 2026-11-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.