RELAGRAM: Recursive Latent Graph Model for the Capacitated Vehicle Routing Problem

Name: RELAGRAM: Recursive Latent Graph Model for the Capacitated Vehicle Routing Problem
Uploaded: 2026-10-18T21:29:06.610090+00:00
Duration: 423 s
Description: RELAGRAM introduces a Recursive Latent Graph Model for solving complex vehicle routing problems by treating routes as edge tokens. It uses a compact transformer that updates latent representations of these tokens recursively, maintaining two states to guide the search. This approach demonstrates that latent recursion is a promising method for neural routing in combinatorial optimization.

RELAGRAM introduces a Recursive Latent Graph Model for solving complex vehicle routing problems by treating routes as edge tokens. It uses a compact transformer that updates latent representations of these tokens recursively, maintaining two states to guide the search. This approach demonstrates that latent recursion is a promising method for neural routing in combinatorial optimization.

Open the full episode