LoRe: Adaptive Interaction-Evaluation Routing with Per-Step Interaction Budgets for Iterative Graph Solvers
Beijing Key Laboratory of Fault-Tolerant Quantum Computing, Beijing Academy of Quantum Information Sciences, Beijing, China(北京容错量子计算重点实验室,量子信息科学北京市院,北京,中国);Beijing National Laboratory for Condensed Matter Physics, Institute of Physics, CAS, Beijing, China(北京凝聚态物理国家实验室,物理研究所,中国科学院,北京,中国);Beijing Key Laboratory of Advanced Quantum Technology, Beijing, China(北京先进量子技术重点实验室,北京,中国);Hefei National Laboratory, Hefei, China(合肥国家实验室,合肥,中国)
Diffusion-based neural solvers for combinatorial optimization repeatedly re-evaluate dense edge/factor interactions, making inference expensive in wall-clock time and often memory-bound at scale. Inspired by the computational methodologies of many-body physics, we introduce LoRe, a training-free, inference-time drop-in wrapper that enforces per-step interaction-evaluation budgeting: at each iteration, it evaluates only a fixed fraction of interactions by dynamically routing computation to high-conflict or high-uncertainty interactions, instead of using a fixed sparsification (e.g., static kNN graphs or static masks). Under fully inclusive end-to-end wall-clock accounting, LoRe substantially improves scalability on the Maximum Independent Set (MIS) problem, extending feasible inference more than $3\times$ beyond the baseline's out-of-memory limit, delivering a $\sim 8\times$ speedup and a $\sim 12\times$ peak-memory reduction, with solution quality preserved in this regime. Demonstrating cross-task generality on the large-scale Traveling Salesperson Problem (TSP) and zero-shot robustness to topology shifts, LoRe achieves a $\sim 15\times$ speedup at $n=1000$ with a $44\times$ memory reduction and competitive tour quality.
LMask: Learn to Solve Constrained Routing Problems with Lazy Masking
Beijing International Center for Mathematical Research, Peking University(北京大学北京国际数学研究中心);Academy of Mathematics and Systems Science, Chinese Academy of Sciences(中国科学院数学与系统科学研究院);Department of Statistics and Data Science, University of Pennsylvania(宾夕法尼亚大学统计与数据科学系)
Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory
Nanyang Technological University(南洋理工大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of Illinois Chicago(伊利诺伊大学香槟分校);Tsinghua University(清华大学);Sun Yat-sen University(中山大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州))
Learning Graph-Indexed Trajectory Patterns for Stochastic On-Time Arrival Routing
Sichuan University-Pittsburgh Institute(四川大学匹兹堡研究院);Sichuan University(四川大学);College of Computer Science(计算机科学学院);University College Dublin(都柏林大学);School of Electrical and Electronic Engineering(电子与电气工程学院);School of Electronics and Information Engineering(电子与信息工程学院)
MPFlow: Learning Budgeted Max-Flow Optimization on the Lightning Network with Deep Graph Reinforcement Learning
Amboss Technologies(Amboss技术公司);CISPA Helmholtz Center for Information Security(CISPA海德堡信息安全中心);Stillmark(Stillmark公司);Sapienza University of Rome(罗马萨皮恩扎大学)
Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference
National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, National University of Defense Technology(国防科技大学并行与分布计算国家重点实验室,计算机科学与技术学院)