---
title: "Language agents achieve superhuman synthesis of scientific knowledge"
license: CC-BY-4.0
license_url: https://creativecommons.org/licenses/by/4.0/
license_note: 'paper is CC BY-SA 4.0 (verified on arXiv abs page 2026-11-12); this pointer note is our own words and is CC BY 4.0; we link to the paper rather than reproduce it'
source: https://iinventedlight.com/library/notes/2409-13740-paperqa2.md
source_license: "CC BY-SA 4.0"
attribution: 'Pointer by iinventedlight (AI-assisted). Source: Michael D. Skarlinski, Sam Cox, Jon M. Laurent, and 6 coauthors, Language agents achieve superhuman synthesis of scientific knowledge (CC BY-SA 4.0). This note links to the paper rather than reproducing it.'
author: 'iinventedlight (AI-assisted)'
date: 2026-11-12
status: published
approved_by: "Cole Withington, 2026-11-12 14:44 PT, Librarian chat widget t51s316: \"Yes, publish all 100 second-list arXiv notes\""
checked_on: 2026-11-12
as_of: 2026-11-12
confidence: medium
untested: 'Pointer note only. Paper not reproduced. Abs page and license checked 2026-11-12.'
category: arxiv
topic_area: 'ai-research: AI-for-science'
tags: arxiv, ai-for-science, literature-review, paperqa2, agents
arxiv_id: 2409.13740
alias: 2409-13740-paperqa2
type: pointer
format: pointer
sources:
  - id: S1
    title: "Language agents achieve superhuman synthesis of scientific knowledge"
    publisher: arXiv
    authors: "Michael D. Skarlinski and 8 coauthors (listed on the arXiv abs page)"
    url: https://arxiv.org/abs/2409.13740
    version_read: "v2 (26 Sep 2024)"
    accessed: 2026-11-12
    license: "CC BY-SA 4.0"
---
# Language agents achieve superhuman synthesis of scientific knowledge

## Summary
[Language agents achieve superhuman synthesis of scientific knowledge](https://arxiv.org/abs/2409.13740) (2024) is the PaperQA2 paper. It asks whether a language-model agent can do real literature work — search, summarization, and contradiction finding — well enough to match subject-matter experts who have no limits on tools or time.

What it introduced: PaperQA2, an agent tuned for cited, factual answers over scientific papers, plus LitQA2, a hard literature-research benchmark used to guide that design. The authors also describe Wikipedia-style topic summaries with citations, and a study that looks for contradictions in a sample of biology papers and then has experts check those flags.

What it led to: a widely cited example of agentic literature review on top of retrieval-augmented generation. Live notes on the earlier PaperQA system and on retrieval and evaluation include [2312-07559-paperqa](https://iinventedlight.com/library/notes/2312-07559-paperqa/), [2005-11401-retrieval-augmented-generation](https://iinventedlight.com/library/notes/2005-11401-retrieval-augmented-generation/), and [2309-15217-ragas-rag-evaluation](https://iinventedlight.com/library/notes/2309-15217-ragas-rag-evaluation/). STORM, another writing-from-research system, is a pointer note in this week's batch H.

Where to read it: https://arxiv.org/abs/2409.13740 (v2, last revised 26 Sep 2024).

The paper is posted under CC BY-SA 4.0. This note links to it rather than reproducing it, so the note can stay CC BY 4.0. The note itself is CC BY 4.0.

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Pointer by iinventedlight (AI-assisted). Paper license: CC BY-SA 4.0; 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).
