PaperOrchestra: A Multi-Agent Framework for Automated AI Research Paper Writing
arXiv AIArchived Apr 08, 2026✓ Full text saved
arXiv:2604.05018v1 Announce Type: new Abstract: Synthesizing unstructured research materials into manuscripts is an essential yet under-explored challenge in AI-driven scientific discovery. Existing autonomous writers are rigidly coupled to specific experimental pipelines, and produce superficial literature reviews. We introduce PaperOrchestra, a multi-agent framework for automated AI research paper writing. It flexibly transforms unconstrained pre-writing materials into submission-ready LaTeX m
Full text archived locally
✦ AI Summary· Claude Sonnet
Computer Science > Artificial Intelligence
[Submitted on 6 Apr 2026]
PaperOrchestra: A Multi-Agent Framework for Automated AI Research Paper Writing
Yiwen Song, Yale Song, Tomas Pfister, Jinsung Yoon
Synthesizing unstructured research materials into manuscripts is an essential yet under-explored challenge in AI-driven scientific discovery. Existing autonomous writers are rigidly coupled to specific experimental pipelines, and produce superficial literature reviews. We introduce PaperOrchestra, a multi-agent framework for automated AI research paper writing. It flexibly transforms unconstrained pre-writing materials into submission-ready LaTeX manuscripts, including comprehensive literature synthesis and generated visuals, such as plots and conceptual diagrams. To evaluate performance, we present PaperWritingBench, the first standardized benchmark of reverse-engineered raw materials from 200 top-tier AI conference papers, alongside a comprehensive suite of automated evaluators. In side-by-side human evaluations, PaperOrchestra significantly outperforms autonomous baselines, achieving an absolute win rate margin of 50%-68% in literature review quality, and 14%-38% in overall manuscript quality.
Comments: Project Page: this https URL
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Multiagent Systems (cs.MA)
Cite as: arXiv:2604.05018 [cs.AI]
(or arXiv:2604.05018v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2604.05018
Focus to learn more
Submission history
From: Yiwen Song [view email]
[v1] Mon, 6 Apr 2026 18:00:00 UTC (29,008 KB)
Access Paper:
view license
Current browse context:
cs.AI
< prev | next >
new | recent | 2026-04
Change to browse by:
cs
cs.LG
cs.MA
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Export BibTeX Citation
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Demos
Related Papers
About arXivLabs
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)