Preprint · 2026

Transferable knowledge graphs with executable learned operators for algorithm design

Camilo Chacón Sartori¹ · José H. García¹ · Andrei Voicu Tomut¹ · Christian Blum²

¹Catalan Institute of Nanoscience and Nanotechnology (ICN2), CSIC and BIST, Campus UAB, Bellaterra, Barcelona  ·  ²Artificial Intelligence Research Institute (IIIA-CSIC), Bellaterra

The PDF on this page carries the main text and the Supplementary Information in a single file. Earlier postings kept them as two separate documents.

Abstract

Procedural knowledge in algorithm design is embedded in source code and rebuilt for each new domain. We introduce Generative Executable Algorithm Knowledge Graphs (GEAKG), a representation in which this knowledge is stored as a generative, executable, transferable graph: typed nodes hold validated operators, edges encode admissible compositions, and learned edge weights record effective sequences. The same engine instantiates the structure across domains by changing only a role ontology (RoleSchema) and a binding. We study GEAKG as a representation mechanism rather than a state-of-the-art optimizer, asking what transfers and when. Layer ablations localize transfer by granularity: within a neural-architecture-search family the learned snapshot transfers across 70 dataset pairs — its weights stay correlated across datasets and one frozen snapshot remains competitive with Regularized Evolution at zero deployment-token cost; across combinatorial domains only the ontology-constrained executable structure transfers, not the learned weights. That structure pays off where target-side search is expensive — a Traveling Salesman snapshot beats an equally untuned from-scratch search on large scheduling instances even at one-fifth its budget — but does not improve on an effective local search where one is cheap, as in assignment and linear ordering. Executable procedural knowledge can thus be acquired offline, compacted, inspected, and reused without runtime language-model calls.

Keywords

procedural knowledge graphs · executable knowledge graphs · transfer learning · automated algorithm design · neural architecture search · combinatorial optimization

Cite

@misc{chaconsartori2026geakg,
  author       = {Chac\'{o}n Sartori, Camilo and
                  Garc\'{i}a, Jos\'{e} H. and
                  Tomut, Andrei Voicu and
                  Blum, Christian},
  title        = {Transferable knowledge graphs with executable learned
                  operators for algorithm design},
  year         = {2026},
  eprint       = {2603.27922},
  archivePrefix= {arXiv},
  url          = {https://arxiv.org/abs/2603.27922}
}

camilochacon.com