Integration of Constraint Programming, Artificial Intelligence, and Operations Research

This two-volume set LNCS 15762-15763 constitutes the proceedings of the 22nd International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research, CPAIOR 2025, held in Melbourne, VIC, Australia, November 1013, 2025.
The 30 full papers and the 2 short papers presented in the proceedings were carefully reviewed and selected from a total of 68 submissions.
The conference featured a masterclass and several joint invited talks that covered topics of interest at the intersection of constraint programming, artificial Intelligence, operations research, planning and scheduling, and knowledge representation.

Inhalt

Combining Constraint Programming and Metaheuristics for Aircraft Maintenance Routing with a Distribution Objective.- Reducing Income Variability in Natural Resource Portfolios via Integer Programming.- Analyzing the numerical correctness of branch-and-bound decisions for mixed-integer programming.- LLMs for Cold-Start Cutting Plane Separator Configuration.- A Dynamic Programming Approach for the Job Sequencing and Tool Switching Problem.- Time-dependent Orienteering for High Altitude UAVs to Monitor Greenhouse Gases.- Multi-depot Electric Bus Scheduling with a Column Generation Heuristic.- On the Effciency of Algebraic Simplex Algorithms for Solving MDPs.- Reinforcement Learning-based Heuristics to Guide Domain-Independent Dynamic Programming.- Acquiring and Selecting Implied Constraints with an Application to the BinSeq and Partition Global Constraints.- Integer and Constraint Programming for the Offine Nanosatellite Partition Scheduling Problem.- Accelerated Discovery of Set Cover Solutions via Graph Neural Networks.- Constrained Machine Learning Through Hyperspherical Representation.- PySCIPOpt-ML: Embedding Trained Machine Learning Models into Mixed-Integer Programs.- Satellite Communication Resources Management in a Earth Observation Federation of Constellations.- Shaping Reward Signals in Reinforcement Learning Using Constraint Programming.