Preview build on GitHub Pages. The open registry will live at e2er.org.
Skip to content
Demonstrator · items marked Example are invented · what exists today
E2ER

External pipelines · RISE project catalogue

STORM / Co-STORM

An LLM-powered knowledge-curation system that writes Wikipedia-style long-form articles from web search. STORM uses perspective-guided question asking and simulated conversations between a writer and a topic expert; Co-STORM (EMNLP 2024) adds a collaborative discourse protocol with human-in-the-loop and a dynamic mind map.

Indexed in RISE · dormantConformance with the standard plannedProject site

What it does

Treats the *pre-writing* problem (deciding what questions to ask) as the central bottleneck of automated long-form writing, and operationalizes it via perspective discovery and simulated expert dialogue. Co-STORM further makes the human–LLM curation loop a first-class architectural element.

Focus
literature
Inputs
topic
Outputs
long-form-article, citations, mind-map
Architecture
multi-agent, human-in-loop, tool-use, rag-knowledge-base, iterative-loop
Maintained by
Stanford OVAL
Started
2024

Description

Data model
Discipline
General
Method family
Literature review
Design
not specified
Research stage
Literature discoveryLiterature synthesisDrafting
Contributors
Stanford OVAL
Usage
not used in published research yet
Source
RISE project catalogue · projects/landscape · @4c17bae
Record
pipeline:storm · JSON

Solid tags are declared by the source or mapped from its terms; dashed tags are inferred by a published rule. Hover a tag for its provenance.

Bring it into the standard

A pipeline built outside E2ER can meet the standard by describing its steps as a template, attaching the floor of checks and publishing evaluation records. Its authors keep ownership and credit.