{"total":17,"items":[{"citing_arxiv_id":"2607.01185","ref_index":21,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Neural Certificate Pricing for Combinatorial Optimization Problems","primary_cat":"cs.LG","submitted_at":"2026-07-01T17:17:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"NCP trains a neural network to predict certificate-level dual prices for CO problems, enabling structured primal recovery with a local second-order error guarantee when consistency holds.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.29725","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Optimizing Nursing Care Taxi Dispatch Leveraging Integer Linear Programming Solvers and Machine Learning","primary_cat":"cs.LG","submitted_at":"2026-06-29T03:05:58+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A Transformer model trained via supervised learning on ILP solutions for a new nursing care taxi dispatch VRP variant reduces operating time by up to 8% on small instances while keeping constraint violations low.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.26873","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Scalable Message-Passing Quantum Graph Neural Networks in the Weisfeiler-Leman Hierarchy","primary_cat":"quant-ph","submitted_at":"2026-06-25T10:58:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"The work constructs a permutation-equivariant quantum GNN that implements message passing at selectable Weisfeiler-Leman levels, supports pre-training on small graphs, and demonstrates readout scalability with simulations up to 56 qubits on synthetic, molecular, and TSP datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.22776","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"GeoRouteNet: A Geometry-Aware Non-Autoregressive Neural Solver for the Euclidean Traveling Salesman Problem","primary_cat":"cs.LG","submitted_at":"2026-06-22T02:31:22+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A geometry-enhanced non-autoregressive neural TSP solver with multi-candidate RL cuts the TSPLIB optimality gap from 17.12% to 3.60% while solving in milliseconds per instance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.19185","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"AGDN: Learning to Solve Traveling Salesman Problem with Anisotropic Graph Diffusion Network","primary_cat":"cs.LG","submitted_at":"2026-06-17T15:24:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"AGDN is a new GNN framework using a MixScore matrix and anisotropic graph diffusion to outperform prior methods on TSP instances across sizes and distributions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.10431","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Vision-Assisted Foundation Model for Solving Multi-Task Vehicle Routing Problems","primary_cat":"cs.CV","submitted_at":"2026-06-09T05:15:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"VaFM encodes constraint-specific VRP images via CNN into patch embeddings fused with graph nodes, using an auxiliary task to handle pixel imbalance, and reports better performance than prior methods on 16 VRP variants.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.02294","ref_index":62,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Regularized Large Neighborhood Search","primary_cat":"cs.LG","submitted_at":"2026-06-01T14:16:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"RLNS regularizes LNS to perform block Gibbs sampling under entropy, interpolating between pseudolikelihood and exact MLE for differentiable combinatorial optimization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.26776","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Towards Generalization-Oriented Models for Vehicle Routing Problems with Mixture-of-Experts","primary_cat":"cs.LG","submitted_at":"2026-05-26T09:46:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"R2E-IG combines residual refined experts with instance-level gating and mixed-distribution training using dynamic weight adaptation to improve generalization of DRL solvers for vehicle routing problems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.24484","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SPACE: Unifying Symmetric and Asymmetric Routing Problems for Generalist Neural Solver","primary_cat":"cs.AI","submitted_at":"2026-05-23T09:12:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"SPACE framework unifies symmetric and asymmetric VRPs via bidirectional Frechet representations and weight-decomposed decoding for zero-shot generalization across 110 variants.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.23395","ref_index":8,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Convex Compositional Reasoning Models","primary_cat":"cs.LG","submitted_at":"2026-05-22T09:04:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"CCEM parameterizes compositional energy factors with input-convex neural networks and optimizes over a convex relaxation to enable deterministic scaling from small to large combinatorial reasoning instances.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.19119","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"GOAL: Graph-based Objective-Aligned Diffusion Solvers for Dynamic Multi-Objective Optimization","primary_cat":"cs.NE","submitted_at":"2026-05-18T21:11:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"GOAL uses conditioned diffusion on relational graphs with typed edges to produce feasible multi-objective solutions for scheduling problems, reporting 100% feasibility and sub-0.2% MAPE on FSP, JSP, and FJSP up to 20 jobs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17539","ref_index":18,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Memory-Guided Tree Search with Cross-Branch Knowledge Transfer for LLM Solver Synthesis","primary_cat":"cs.AI","submitted_at":"2026-05-17T16:47:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"MEMOIR adds branch-local and global memory with a reflection step to tree search for LLM solver synthesis, reaching 96.7% solution validity and 7.3-point score gains over baselines on seven CO problems with lower run-to-run variance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.20236","ref_index":18,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Machine Learning-based Two-Stage Graph Sparsification for the Travelling Salesman Problem","primary_cat":"cs.LG","submitted_at":"2026-04-22T06:40:05+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A two-stage ML pipeline unions α-Nearest and POPMUSIC candidate edges then prunes single-source edges via a classifier, cutting TSP graph density 37-47% with ≥99.69% optimal-tour recall.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"order is essential; reversing it would force the ML model to work on allN (N− 1)/2 edges without structural guidance, and the heuristic applied afterwards could not recover edges the model already discarded. We design all features to be distance-type agnostic, so the method works for any TSPLIB distance convention. Following the multi-metric evaluation principle advocated by Kerschke et al. [18], we report density, coverage, and downstream solver performance jointly. Our contributions are: -We propose a two-stage graph sparsification pipeline that applies learned pruning to already-sparse heuristic candidate graphs rather than to the complete graph. A single model, trained once on a mixed dataset comprising 4 distance types and 5 instance distributions, reduces density by up to47%"},{"citing_arxiv_id":"2510.20169","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Empowering Targeted Neighborhood Search via Hyper Tour for Large-Scale TSP","primary_cat":"cs.LG","submitted_at":"2025-10-23T03:30:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"HyperNS clusters TSP cities with a sparse heatmap, builds a hyper tour over supernodes, and restricts neighborhood search to hyper-tour-relevant edges to improve solution quality on large instances.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2406.03099","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Supplementary Materials to Graph Convolutional Branch and Bound","primary_cat":"cs.LG","submitted_at":"2024-06-05T09:42:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Supplementary results on 1-tree relaxation performance inside a GCN-augmented branch-and-bound solver for TSP.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2405.16409","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Network Interdiction Goes Neural","primary_cat":"cs.AI","submitted_at":"2024-05-26T02:34:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Multipartite GNN learns MILP formulations of network interdiction to outperform baselines on bi-level combinatorial tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2405.15314","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Output-Constrained Decision Trees","primary_cat":"cs.LG","submitted_at":"2024-05-24T07:54:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Presents three new training procedures for regression trees that enforce convex output constraints at training time and validates them on synthetic and hierarchical time-series data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}