12.215 papers · continuously updated · last export: 28 Jun 2026livingmeta.ai

Living Meta-Analysis

AI in Research

Erasmus University Rotterdam — AI@EUR

A living meta-analysis platform that continuously monitors, classifies, and analyzes research on generative AI in academic research practice — including literature review automation, AI-assisted writing, peer review, research integrity, institutional governance, and human-AI collaboration in scholarly workflows.

What that means in practice: every new paper in ai-in-research is classified, cross-validated, and tagged with methodology and evidence type as it enters the corpus. Evidence gaps and research priorities emerge from the literature itself, and update continuously. Researchers can browse papers, discover datasets and instruments others have used, or open a thread in The Lab to work through a question alongside an AI research agent.

12.215
Papers
2.481
Sources
Explore PapersThe Lab

On the LivingMeta platform

What you'll find inside this instance

Four surfaces, one continuously updated pipeline. Each one is populated directly from the literature — no manual curation backlog.

Papers

Browse the Literature

Every paper in the field, classified by relevance and cross-validated by multiple AI perspectives. Filter by methodology or evidence model; agreement scores flag where the AI is confident, and disagreement shows where human judgment belongs.

Resources

Curated Datasets & Tools

Datasets, questionnaires, measurement instruments, and research tools surfaced across the corpus, each linked back to the papers that use them. Reusable building blocks for the next study.

Agenda

Priority Research Agenda

A ranked list of high-impact evidence gaps, generated from the literature itself and scored for frequency, depth, and feasibility. Updates as the field evolves.

The Lab

Collaborative Research Threads

Work alongside an AI agent — from exploring a question to designing a study to writing it up. Uploaded documents, cited papers, and findings stay with the thread. Role-adaptive coaching scales the scaffolding to your expertise.

Frequently Asked Questions

Every paper is analyzed from multiple independent perspectives, each with a different cognitive focus. They extract the same structured fields, and a consensus algorithm resolves disagreements field-by-field. Every factual claim must include a verbatim quote from the source — extractions without textual evidence are automatically flagged. Agreement scores are visible on each paper card.
The agenda is built automatically from the evidence in this instance. Research gaps identified across all extracted papers are clustered into themes, scored on frequency, source quality, feasibility, recency, and field-wide coverage. An AI then filters the top-ranked themes against the instance context — only priorities relevant to the broader field survive. The list updates with every new paper added.
Datasets, questionnaires, measurement instruments, tools, and code repositories discovered across the extracted papers. Each is linked back to the paper that uses it, so you can see the evidence base before deciding whether to adopt it. Resources are refreshed continuously as new papers are added.
Yes — The Lab provides AI-coached research guidance through a multi-phase journey, from exploring the literature to writing your manuscript. Select the 'Junior Researcher' role when starting a thread, and the system scaffolds your process with Socratic questions. You can export papers to CSV or BibTeX at any time.
Those tools address individual stages — Elicit does per-paper extraction, Consensus searches abstracts, Cochrane produces static reviews. LivingMeta integrates extraction, gap analysis, coached investigation, and resource discovery into a single continuously updated workflow. The platform is the methodology.
Start a thread in The Lab describing what you found. The instance owner reviews submissions and can trigger corrections or additions. Papers flow through the same classification and extraction pipeline as all other content.

Built on the LivingMeta platform. Read the foundation paper for methodology and architecture details.

Explore PapersBrowse Resources