STORM
LLM agent system synthesizing Wikipedia-like long-form research articles from scratch through multi-perspective question asking, web retrieval, and citation-grounded report generation, with Co-STORM extension for collaborative human-LLM knowledge curation conversations (Stanford OVAL, NAACL 2024 & EMNLP 2024)
- Repository
- github.com/stanford-oval/storm
Source attribution
- Awesome AI for Science — github.com/stanford-oval/storm
Related resources
High-accuracy RAG for scientific PDFs with citation support, agentic RAG, and contradiction detection
Retrieval-augmented LM synthesizing scientific literature from 45M papers with human-expert-level citation accuracy, outperforming GPT-4o by 5% on ScholarQABench (Nature 2026, UW & Ai2)
Self-hostable scientific claim-verification and literature-review tool combining Semantic Scholar retrieval, bibliometric scoring, and LLM-based evidence synthesis for large-batch validation workflows
Generate comprehensive reviews from arXiv papers and convert to blog posts