Paper detail

Graph Memory for Literature Agents: Persistent Neighborhoods for Scientific Search

We show that persistent graph neighborhoods and operator-facing retrieval memory improve literature navigation across papers, people and opportunities.

Preprint2026arXivOpen access

Diego Santana Lena Hartmann Mira Alvarez

Large Language Models Scientific Knowledge Graphs

21citations

0reviews

0saves

Yescode

Nodataset

2institutions

Next steps

Decide what to do with this paper

Like0 Dislike0Score 0

Use like or dislike for the fast social read. The more specific scholarly feedback stays available below when needed.

Save to reading list0

Keep the important signals around this paper in one place: votes, save state, collection context, reviews and the metadata you need before deciding what to do next.

Authors

Diego Santana Lena Hartmann Mira Alvarez

Institutions

ETH Zurich Massachusetts Institute of Technology

Add specific reaction

Move through nearby people, institutions, topics and adjacent work without leaving the paper page.

Drag to move the map, use wheel or controls to zoom.Selected work: Graph Memory for Literature Agents: Persistent Neighborhoods for Scientific Search

worksignal 104 adjacent