arXiv AI
Jun 10
Baseline-Free Policy Optimization for Neural Combinatorial Optimization
arXiv:2606. 10321v1 Announce Type: cross Abstract: Neural combinatorial optimization (NCO) trains autoregressive policies to solve routing problems.
SSPO: Structure-Aware Similarity-Weighted Preference Optimization for Neural Combinatorial Optimization
arXiv:2608. 12443v1 Announce Type: cross Abstract: Neural combinatorial optimization (NCO) relies on parallel solution sampling for training, yet existing methods fail to fully exploit the rich information latent in a co-sampled solution group.
Related stories
arXiv Machine Learning
Jul 28
WeCon: An Efficient Weight-Conditioned Neural Solver for Multi-Objective Combinatorial Optimization Problems
arXiv:2605. 22876v2 Announce Type: replace Abstract: Existing neural solvers for Multi-Objective Combinatorial Optimization Problems (MOCOPs) commonly adopt decomposition-based strategies that scalarize a MOCOP into multiple subproblems associated with distinct weight vectors.
arXiv Machine Learning
Jul 31
AutoPref: Automatic Discovery of Task-Specific Preference Objectives for Neural Combinatorial Optimization
arXiv:2607. 27953v1 Announce Type: new Abstract: Combinatorial optimization problems (COPs) underpin many real-world decisions, but their exponentially large search spaces make high-quality solutions costly to obtain.
arXiv Machine Learning
Aug 12
Pair-Centric Graph Rewiring for Over-Squashing via Optimal Transport-Guided Communication Alignment
arXiv:2608. 10619v1 Announce Type: new Abstract: Message-passing neural networks (MPNNs) often struggle when task-relevant information is distributed across distant regions of a graph, since local propagation must compress remote signals through limited structural interfaces.
arXiv AI
Jun 2
Margin Adaptive DPO: Leveraging Reward Model for Granular Control in Preference Optimization
arXiv:2510. 05342v2 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO) has emerged as a simple and effective method for aligning large language models.
arXiv Machine Learning
Jul 21
Rethinking Efficiency in Neural Combinatorial Optimization: Batched Preference Optimization with Mamba
arXiv:2602. 20730v3 Announce Type: replace Abstract: We study efficiency as a first-class objective in Neural Combinatorial Optimization (NCO) and present ECO, an efficient learning framework that combines batched preference optimization with a Mamba backbone.
arXiv AI
Sep 1
Personalized Group Relative Policy Optimization for Heterogenous Preference Alignment
The paper introduces Personalized Group Relative Policy Optimization (P‑GRPO), a new alignment framework for large language models that separates advantage estimation from immediate batch statistics. By normalizing advantages using preference‑group‑specific reward histories instead of the concurrent generation group, P‑GRPO maintains contrastive signals for distinct user preferences. Experiments across various tasks show that P‑GRPO converges faster and yields higher rewards than standard GRPO, improving alignment with heterogeneous human preferences while preserving general capabilities.
arXiv Machine Learning
Sep 14
Learning-Augmented Optimization for Strategic Two-Echelon Spare Parts Network Design
The paper presents a conservative learning‑augmented framework for designing a two‑echelon spare‑parts inventory network. It combines a graph neural network ensemble, variable neighborhood search, and set‑partitioning recombination to select cluster centers while limiting optimistic surrogate errors. In a case study on Amazon’s North American fulfillment network, the method achieves a 30.5% increase in combined savings over an exact‑evaluation baseline while preserving 99.8% service levels.
arXiv Machine Learning
Aug 13
Mind the Gap: Structure-Aware Consistency in Preference Learning
arXiv:2604. 27733v2 Announce Type: replace Abstract: Aligning Large Language Models (LLMs) with human intent, whether through explicit reward modeling or direct methods such as DPO, fundamentally relies on minimizing a surrogate loss as a proxy for the true pairwise ranking objective.
arXiv Machine Learning
Jun 16
DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical Reasoning
arXiv:2505. 09655v5 Announce Type: replace-cross Abstract: Post-training LLMs with Reinforcement Learning, specifically Group Relative Policy Optimization (GRPO), has emerged as a paradigm for enhancing mathematical reasoning.
arXiv Machine Learning
Jun 10
Mechanistic Analysis of Alignment Algorithms in Language Models
arXiv:2606. 09850v1 Announce Type: new Abstract: Post-training alignment algorithms are predominantly evaluated as black boxes, obscuring how they reshape language models' internal computations.
arXiv AI
Aug 18
Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization
arXiv:2608. 16072v1 Announce Type: cross Abstract: Reinforcement learning (RL) with group-relative advantages has become the de facto standard for post-training language model reasoners.