# Awesome AI Auto-Research

A paper collection accompanying a survey on AI-assisted and automated scientific research, organized around the full research lifecycle from idea generation through writing, peer review and dissemination.

Awesome AI Auto-Research accompanies the survey paper AI for Auto-Research: Roadmap & User Guide and tracks papers on AI-assisted and automated scientific research across the full research lifecycle. It organizes that lifecycle into eight stages grouped into four phases: creation, covering idea generation, literature review, coding and experiments, and tables and figures; writing, covering drafting, editing and polishing manuscripts; validation, covering automated peer review, reviewer-paper matching and AI-assisted rebuttals; and dissemination, covering turning papers into slides, posters, videos, websites and social media content.

Each stage's table of contents further splits into sub-topics, for example idea generation into knowledge-based generation, external-signal-driven generation, multi-agent collaborative generation, and novelty and feasibility assessment, with a parallel assessment sub-topic for reproducibility and fidelity at each stage.

Website: https://worldbench.github.io/awesome-ai-auto-research