External pipelines · RISE project catalogue
MARG (Multi-Agent Review Generation)
A research artifact (arXiv:2401.04259) and reusable demo for generating peer reviews of scientific papers using multiple specialized agents. Ships with a web interface and reproduction scripts for the published user study comparing MARG-S to single-LLM baselines (SARG-B, LiZCa). Sits at the referee-simulation stage of the RISE pipeline.
Where it sits
left: what it builds on · right: what builds on it · pale: exampleContributed by Allen Institute for AI
How studies reach it
No published study reaches it yet.
Disciplines it reaches
No study reaches it yet.
Solid: published studies. Light: examples.
Computed from the records on this site: what each study, template and specialist names as used, which study extends which, and who contributed what. 0 studies in total.
What it does
Among the earliest peer-reviewed treatments of agentic peer review, with an explicit user study comparing review quality across multiple generation strategies. The repository functions as both a runnable demo and a reproducibility package for the paper.
- Focus
- review
- Inputs
- submitted-paper
- Outputs
- generated-review, alignment-metrics
- Architecture
- multi-agent, tool-use
- Maintained by
- Allen Institute for AI
- Started
- 2024
Description
Data model- Discipline
- General
- Method family
- not specified
- Design
- not specified
- Research stage
- Review
- Contributors
- Allen Institute for AI
- Usage
- not used in published research yet
- Source
- RISE project catalogue · projects/landscape · @4c17bae
- Record
- pipeline:marg · 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.