Skip to content

Source paper

PaperOrchestra: A Multi-Agent Framework for Automated AI Research Paper Writing

Yiwen Song, Yale Song, Tomas Pfister, Jinsung Yoon
arXiv 2604.05018 · 20269 upvotes on Hugging Face

Research ideas from this paper (3)

Generated by AI. The paper’s authors did not write these.

AI summary

PaperOrchestra is a multi-agent framework that autonomously converts unconstrained research materials, such as high-level idea summaries and raw experimental logs, into submission-ready LaTeX manuscripts. It orchestrates specialized agents to plan paper outlines, generate conceptual and data figures, synthesize literature reviews using search and citation verification, draft core text sections, and iteratively refine manuscripts via simulated peer review. Evaluated on PaperWritingBench, a benchmark of 200 CVPR and ICLR papers, PaperOrchestra significantly outperforms autonomous baselines in literature review quality and overall paper coherence.

How it works (AI summary)

The framework coordinates five modular agent steps: an Outline Agent that generates visualization plans, citation strategies, and section plans; a Plotting Agent (PaperBanana) for diagrams and charts; a Hybrid Literature Review Agent that discovers candidate citations via web search and verifies them through the Semantic Scholar API; a Section Writing Agent that populates remaining sections and tables from experimental logs; and a Content Refinement Agent that conducts score-driven revisions using simulated reviewer feedback (AgentReview).