Paper combines Jev-style decision models with ActiveGraph for recommenders
New research turns user activity into a knowledge graph where agents propose candidates for decision models like Jev to select from, an approach the author says agent builders should explore.

came across new research that combines decision models like Jev with @activegraphai to build recommender systems they turn user activity into a knowledge graph that agents use to propose candidates for the decision models to select from ActiveGraph isn’t my most popular open source project, but I think it’s directionally the type of approach all agent builders should be exploring today the most fun and inspiring thing about open source is collaborating w ppl you’ve never met to push tech forward :) the paper: https://arxiv.org/abs/2610.26035