paper-orchestra: A multi-agent framework for automated AI research paper writing.
What problem it solves
Researchers often need to turn unconstrained ideas and experimental logs into complete research manuscripts with literature synthesis, structured sections, refinements, and figures. PaperOrchestra addresses this gap by coordinating specialized agents across the paper-writing workflow and producing LaTeX manuscripts that follow target conference templates.
Key features
Multi-Agent Paper-Writing Pipeline — Specialized agents cover outline generation, literature review, section writing, content refinement, and plotting as an end-to-end paper-generation workflow.
Source: README, methods
Literature Synthesis — The framework searches for relevant literature, prioritizes it, and integrates the results into the manuscript.
Source: README
Generated Visuals — The plotting workflow can generate figures from code, while the framework also supports conceptual diagrams.
Source: README
LaTeX Manuscript Automation — PaperOrchestra produces submission-ready LaTeX manuscripts that adhere to target conference templates, with a template directory for adding conference-specific formats.
Source: README, templates
Quick start
Copied verbatim from the project's README.
./paper_writing_cli.shWho it may suit
This project may suit researchers who want to transform ideas and experimental logs into structured LaTeX manuscripts, as well as teams interested in extending multi-agent research-writing workflows.
Topics to discuss
How should specialized agents divide responsibilities during manuscript generation?
Which methods can improve literature selection and synthesis quality?
How can generated papers remain faithful to source experimental results?
Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.
Read the original README https://github.com/google-research/paper-orchestra#readme
ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.
Comments
…