aiqbench analysis
This paper applies latent recursion, where one small network repeatedly refines its internal representations, to the capacitated vehicle routing problem, a standard logistics benchmark. The 0.53M-parameter model reaches 8.3% to 13.4% gaps against a classical solver on CVRP-100, and zero-shot generalization to larger instances (15.6% and 21.7% gaps) is the most interesting result. Readers should note that these are heuristic gaps against a reference solver, not optimality claims, and that the work is a workshop-stage proof of concept.
RELAGRAM: Recursive Latent Graph Model for the Capacitated Vehicle Routing Problem
arXiv:2610.15106v1 Announce Type: new Abstract: Latent recursion repeatedly processes internal representations through the same neural network. Recent work has shown this approach to be effective on structured reasoning tasks such as Sudoku and maze solving. However, whether latent recursion can support neural routing remains unclear. We introduce RELAGRAM (Recursive Latent Graph Model), a novel approach that brings latent recursion to graph combinatorial optimization. RELAGRAM encodes a capacitated vehicle routing problem (CVRP) instance as edge tokens; a compact transformer recurrently updates the latent representations of these tokens. An output head maps the answer state to an edge heatmap, from which an autoregressive decoder constructs a feasible solution. On CVRP-100 instances, the 0.53M-parameter RELAGRAM achieves gaps to a PyVRP reference of 13.4%, 9.8%, and 8.3% under greedy decoding, eightfold symmetry augmentation, and 256-candidate search, respectively. Trained only on CVRP-100, RELAGRAM generalizes zero-shot to CVRP-500 and CVRP-1000, achieving gaps of 15.6% and 21.7% under 256-candidate search. Together, these results demonstrate that latent recursion is a promising approach to neural routing.
Abstract:Latent recursion repeatedly processes internal representations through the same neural network. Recent work has shown this approach to be effective on structured reasoning tasks such as Sudoku and maze solving. However, whether latent recursion can support neural routing remains unclear. We introduce RELAGRAM (Recursive Latent Graph Model), a novel approach that brings latent recursion to graph combinatorial optimization. RELAGRAM encodes a capacitated vehicle routing problem (CVRP) instance as edge tokens; a compact transformer recurrently updates the latent representations of these tokens. An output head maps the answer state to an edge heatmap, from which an autoregressive decoder constructs a feasible solution. On CVRP-100 instances, the 0.53M-parameter RELAGRAM achieves gaps to a PyVRP reference of 13.4%, 9.8%, and 8.3% under greedy decoding, eightfold symmetry augmentation, and 256-candidate search, respectively. Trained only on CVRP-100, RELAGRAM generalizes zero-shot to CVRP-500 and CVRP-1000, achieving gaps of 15.6% and 21.7% under 256-candidate search. Together, these results demonstrate that latent recursion is a promising approach to neural routing.
Accepted to the NeurIPS 2026 MLxOR workshop. Paper contains 6 pages (4 main text, 1 references, 1 appendix); 1 figure and 3 tables
Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE); Optimization and Control (math.OC)
arXiv:2610.15106 [cs.LG]
(or arXiv:2610.15106v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.15106 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 288 words
Related coverage
[AINews] Muse Spark 1.3 matches GPT-5.6-Sol, confirming Meta Superintelligence as the newest Frontier Lab, >90% discount for training
Latent Space · Sep 3, 2026
GREAT: A Graph Edge Attention Network for the Electric Vehicle Routing Problem with Asymmetric Costs
arXiv · Oct 15, 2026
[AINews] Here are 6 Clones of Jev in 2 days
Latent Space · Sep 19, 2026
Understanding Decision-Making Mechanisms in Neural Routing Solvers
arXiv · Sep 30, 2026