MiLoop: Selective Memory Propagation for Neural Combinatorial Optimization

arXiv:2610.01685 · cs.LG · Submitted 2026-10-01 · Read on arXiv

cs.LG

Submitted: 2026-10-01

Updated: 2026-10-01

Code: https://github.com/google/or-tools

Terminology

• Combinatorial Optimization — 1× in this paper · explained in 2 episodes

Sources

• Survey on Neural Routing Solvers
• Neural Combinatorial Optimization with Reinforcement Learning
• SPACE: Unifying Symmetric and Asymmetric Routing Problems for Generalist Neural Solver
• Universal Transformers
• Addressing Some Limitations of Transformers with Feedback Memory
• Efficient Decoder Scaling Strategy for Neural Routing Solvers
• Rethinking Constraint Awareness for Efficient State Embedding of Neural Routing Solver

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks