arXiv Machine Learning August 18, 2026 By Alessandro Barro

Pointer Networks with Q-Learning for Combinatorial Optimization

Read the original on arXiv Machine Learning →

arXiv:2311. 02629v5 Announce Type: replace Abstract: We introduce the Pointer Q-Network (PQN), a hybrid neural architecture that integrates model-free Q-value policy approximation with Pointer Networks (Ptr-Nets) to enhance the optimality of attention-based sequence generation, focusing on long-term outcomes.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 28

Understanding Human-like Solutions in Combinatorial Optimization via Learning and Search

arXiv:2607. 23854v1 Announce Type: new Abstract: Humans often find good solutions to combinatorial optimization problems that are computationally hard even for advanced computer algorithms.

By Haijiang Yan, Jian-Qiao Zhu, Liqiang Huang, Ming Meng

reinforcement-learning fine-tuning

arXiv Machine Learning

Sep 2

Recurrent State Encoders for Efficient Neural Combinatorial Optimization

arXiv:2509.05084v2 Announce Type: replace Abstract: The primary paradigm in Neural Combinatorial Optimization (NCO) consists of construction methods, where a neural network is trained to sequentially...

By Tim Dernedde, Daniela Thyssens, Lars Schmidt-Thieme

rag

arXiv Machine Learning

Sep 24

Attention Routing Stabilizes Early: Working-Set Inference for Recurrent Language Models

The paper investigates how attention dynamics evolve across recurrent depth in language models, finding that attention support stabilizes early while hidden states and outputs take longer. It proposes WISE, a training‑free method that uses full attention in early steps and then reuses the discovered sparse working set for later steps, preserving performance on multi‑hop QA tasks. Experiments show that WISE maintains quality up to 2K context, offers measurable speedups, and highlights the importance of recurrent discovery of attention support.

By Ke Wan, Chen Chen

llms benchmarks

arXiv AI

Jul 7

Graph Neural Networks are Heuristics

arXiv:2601. 13465v4 Announce Type: replace Abstract: Graph neural networks are usually treated as auxiliaries for combinatorial optimization: they imitate algorithms, guide search, or supply scores to classical procedures.

By Yimeng Min, Carla P. Gomes

arXiv AI

Aug 10

Aftab: A Comprehensive Benchmark of CNN Encoders and Advanced Value Functions in Parallelized Q-Networks

arXiv:2608. 07335v1 Announce Type: cross Abstract: Recent advancements in deep reinforcement learning have increasingly favored simplified, highly parallelized paradigms.

By Taha Shieenavaz, Shabnam Zareshahraki, Loris Nanni

reinforcement-learning benchmarks

arXiv Machine Learning

Jun 10

Latent Guided Sampling for Combinatorial Optimization

arXiv:2506. 03672v2 Announce Type: replace-cross Abstract: Combinatorial Optimization problems are widespread in domains such as logistics, manufacturing, and drug discovery, yet their NP-hard nature makes them computationally challenging.

By Sobihan Surendran (LPSM), Adeline Fermanian (LPSM), Sylvain Le Corff (LPSM)

diffusion reinforcement-learning benchmarks

One email a morning, machine-written

Related stories

Understanding Human-like Solutions in Combinatorial Optimization via Learning and Search

Recurrent State Encoders for Efficient Neural Combinatorial Optimization

Attention Routing Stabilizes Early: Working-Set Inference for Recurrent Language Models

Graph Neural Networks are Heuristics

Aftab: A Comprehensive Benchmark of CNN Encoders and Advanced Value Functions in Parallelized Q-Networks

Latent Guided Sampling for Combinatorial Optimization