liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
AI-Generated Hypotheses and the Emergence of Autonomous Scientific Discovery
Linköping University, Department of Physics, Chemistry and Biology, Electronic and photonic materials. Linköping University, Faculty of Science & Engineering.ORCID iD: 0000-0002-4317-2879
2026 (English)In: ACS Materials Letters, E-ISSN 2639-4979, Vol. 8, no 6, p. 1457-1464Article in journal (Refereed) Published
Abstract [en]

Hypothesis generation plays a central role in scientific discovery, yet it has remained one of the least formalized and least automated components of the research process. While advances in automation, machine learning, and self-driving laboratories have transformed how hypotheses are tested, their formulation has largely remained a human endeavor. Recent progress in AI, particularly LLMs, challenges this assumption by enabling the large-scale generation of novel, plausible, and actionable hypotheses through computational recombination of existing knowledge. We argue here that coupling AI-driven hypothesis generation with agentic reasoning systems and autonomous laboratory platforms opens a realistic pathway toward end-to-end automated scientific discovery. We discuss what defines a good scientific hypothesis, assess the opportunities and limitations of contemporary AI systems, and outline how hypothesis generation can be integrated into closed-loop experimental workflows. We conclude by identifying key challenges that must be addressed for such a Hypothesis-Driven Autonomous Discovery System (HADS) to truly accelerate material science.

Place, publisher, year, edition, pages
AMER CHEMICAL SOC , 2026. Vol. 8, no 6, p. 1457-1464
National Category
Computer Systems
Identifiers
URN: urn:nbn:se:liu:diva-224074DOI: 10.1021/acsmaterialslett.6c00224ISI: 001758544900001OAI: oai:DiVA.org:liu-224074DiVA, id: diva2:2060719
Note

Funding Agencies|Carl Tryggers Stiftelse f?r Vetenskaplig Forskning [CTS 24: 3375]; Swedish Government Strategic Research Area in Materials Science on Advanced Functional Materials at Link?ping University [SFO-Mat-LiU No. 2009-00971]

Available from: 2026-05-19 Created: 2026-05-19 Last updated: 2026-07-01

Open Access in DiVA

fulltext(3201 kB)14 downloads
File information
File name FULLTEXT01.pdfFile size 3201 kBChecksum SHA-512
a492008768c8f8e222ca2530e87cdcbcf86ec1185d5a1c8f8ab6dfd6467b04b2b94a399abff3caf3d24cb4932d341fdd16c3192035da0c80205b28fbd091410e
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Jacobsson, Jesper
By organisation
Electronic and photonic materialsFaculty of Science & Engineering
In the same journal
ACS Materials Letters
Computer Systems

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 117 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf