---
title: 'Emergent autonomous scientific research capabilities of large language models'
license: CC-BY-4.0
license_url: https://creativecommons.org/licenses/by/4.0/
license_note: 'This note is CC BY 4.0. It links to the paper and does not reproduce it. Paper license: arXiv non-exclusive distribution (verified on arXiv abs page 2026-11-11; http://arxiv.org/licenses/nonexclusive-distrib/1.0/).'
source: https://iinventedlight.com/library/notes/2304-05332-coscientist.md
source_license: 'arXiv default (non-exclusive distribution license)'
attribution: 'Pointer note by iinventedlight (AI-assisted). Links to: Daniil A. Boiko, Robert MacKnight, Gabe Gomes, Emergent autonomous scientific research capabilities of large language models (arXiv). This note does not reproduce the paper.'
author: 'iinventedlight (AI-assisted)'
date: 2026-11-11
status: published
approved_by: "Cole Withington, 2026-11-11 20:58 PT, Grok Bot chat widget t1717s7407: \"Publish all 100 including the LLMs Encode Clinical Knowledge note\""
checked_on: 2026-11-11
as_of: 2026-11-11
confidence: medium
untested: 'Pointer note only. Abs page read 2026-11-11. The paper is not reproduced here.'
category: arxiv
topic_area: 'ai-research: AI-for-science'
tags: arxiv, pointer, AI-for-science
arxiv_id: 2304.05332
alias: 2304.05332-coscientist
format: pointer
type: pointer
sources:
  - id: S1
    title: 'Emergent autonomous scientific research capabilities of large language models'
    publisher: arXiv
    authors: 'Daniil A. Boiko, Robert MacKnight, Gabe Gomes'
    url: https://arxiv.org/abs/2304.05332
    version_read: 'v1 (11 Apr 2023)'
    accessed: 2026-11-11
    license: 'arXiv default (non-exclusive distribution license)'
---
# Emergent autonomous scientific research capabilities of large language models

## Summary
Emergent autonomous scientific research capabilities of large language models (2023), by Daniil A. Boiko, Robert MacKnight, and Gabe Gomes, is at https://arxiv.org/abs/2304.05332. The authors present an Intelligent Agent system that combines multiple large language models for autonomous design, planning, and execution of scientific experiments. They describe three examples, and they say the most complex is the successful performance of catalyzed cross-coupling reactions. They also discuss the safety implications of such systems and propose measures to prevent misuse. Transformer-based large language models are rapidly advancing in machine learning research, with applications spanning natural language, biology, chemistry, and computer programming. Extreme scaling and reinforcement learning from human feedback have significantly improved the quality of generated text, enabling these models to perform various tasks and reason about their choices. Comments: Version 1, April 11, 2023. 48 pages. Title, authors, abstract, and comments were taken from the arXiv abs page. The version is v1 (11 Apr 2023), submitted 11 Apr 2023.

## Claims
Pointer notes do not quote the paper. See Verification and Sources for the link and license.

## Verification
- Format: pointer note only. The paper is not reproduced here.
- Why it matters: It matters as an early, widely discussed account of a language-model system used to design, plan, and carry out scientific experiments, often referred to as Coscientist in later commentary.
- Reproduced: not reproduced (2026-11-11).
- Related work: A related note already in the library is [The AI Scientist](https://iinventedlight.com/library/notes/2408-06292-the-ai-scientist/).
- Limits: This is a pointer note only, based on the 11 Apr 2023 abstract because a full HTML version was not available from arXiv. It does not describe experimental procedures. This pointer does not describe how experiments were performed and is not a laboratory protocol.
- License: arXiv default (non-exclusive distribution license) on the abs page (2026-11-11; http://arxiv.org/licenses/nonexclusive-distrib/1.0/). Submitted 11 Apr 2023 (v1). Sources: [S1] https://arxiv.org/abs/2304.05332, v1 (11 Apr 2023). checked_on: 2026-11-11. Paper license: arXiv non-exclusive distribution; this note links to it and does not reproduce it. The note itself is CC BY 4.0.

## When to apply
Use when you need the original Coscientist-style paper on language-model systems for planning scientific experiments, including the authors' safety discussion. It is not a protocol.

## Facts
- id: F1
  claim: 'The paper presents an Intelligent Agent system that combines multiple large language models for autonomous design, planning, and execution of scientific experiments.'
  confidence: medium
  date: 2026-11-11
  sources: [S1]
  license: CC-BY-4.0
- id: F2
  claim: 'The authors showcase three examples, with the most complex being the successful performance of catalyzed cross-coupling reactions.'
  confidence: medium
  date: 2026-11-11
  sources: [S1]
  license: CC-BY-4.0
- id: F3
  claim: 'They discuss the safety implications of such systems and propose measures to prevent their misuse.'
  confidence: medium
  date: 2026-11-11
  sources: [S1]
  license: CC-BY-4.0

## Sources
- [S1] arXiv 2304.05332, https://arxiv.org/abs/2304.05332. Paper license: arXiv default (non-exclusive distribution license). v1 (11 Apr 2023). Accessed 2026-11-11. This note links to the paper and does not reproduce it.

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Pointer by iinventedlight (AI-assisted). Paper license: arXiv non-exclusive distribution; this note links to it and does not reproduce it.

---

Agents: [/agents.md](/agents.md) | [/.well-known/agent-library.json](/.well-known/agent-library.json).