Radar / AI agents / PaperOrchestra

PaperOrchestra: five agents that turn lab notes into a submission-ready paper

Google Research's multi-agent framework turns an idea file and an experiment log into a full LaTeX manuscript — verified-citation literature review, generated figures, and three rounds of simulated peer review.

trendingagents · frameworksJEV traction 0.74google-research/paper-orchestra · 5,193 ★added 2026-11-18
Open PaperOrchestra →View on the radar

Why it matters

The literature review is grounded, not hallucinated: candidate papers are checked against Semantic Scholar before they reach the bibliography — and it beat baselines by 50-68% on review quality.

What you could build with it

A research lab could turn each experiment run's log into a draft manuscript overnight, so the literature review and figures are waiting when the researcher sits down to write.

Does it hold up?

Runnable today with a Gemini or OpenAI key, but a paper costs ~40 minutes and ~60 LLM calls on paid Pro models, and the benchmark dataset isn't released yet — best for drafting, not for unsupervised submission.

Built with PaperOrchestra

Learn more

hands-on tutorial →

First spotted on github: source.

More AI agents

CLI-Anything: make any app agent-native with a generated CLIFrom HKU's Data Intelligence Lab: a seven-phase pipeline that generates a real CLI harness for any GUI application…agents · JEV 0.78DeepSeek Harness: 1.54M daily users and 35,000 plugins into its everything-is-a-plugin runtimeDeepSeek's open-source agent harness where models, tools, sandboxes, sessions and even the UI are all plugins — now…agents · JEV 0.76Dify 1.20.0: OpenTelemetry trace export and malware scanning for LLM appsThe open-source LLM app platform's 1.20.0 release adds trace export to any OpenTelemetry collector, keeps Langfuse…agents · JEV 0.76AG-UI: the open protocol connecting AI agents to user interfacesEvent-based protocol that streams agent activity — text, tool calls, state — to any frontend over 16 standard event…agents · JEV 0.74Superpowers: the skills framework that makes coding agents work like careful developersA free Claude Code plugin of 15 skills that forces a disciplined workflow — brainstorm, plan, test-first, review…agents · JEV 0.73Multica: an open-source workspace where humans and AI agents work as one teamSelf-hostable workspace that treats humans and AI agents as teammates on the same projects, with support for multiple…agents · JEV 0.73

Get the week's best AI launches, plus 3 ideas worth building

One email every Saturday. Ranked by traction, not hype. Free.