Learning to Solve and Optimize by Evolving Code

Semmelrock, Veronika; Strizzolo, Benedetta; Zuccato, Francesco; Friedrich, Gerhard; Rodler, Patrick; Schekotihin, Konstantin

doi:10.24963/ijcai.2026/451

Learning to Solve and Optimize by Evolving Code

Veronika Semmelrock, Benedetta Strizzolo, Francesco Zuccato, Gerhard Friedrich, Patrick Rodler, Konstantin Schekotihin

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 4054-4062.

https://doi.org/10.24963/ijcai.2026/451

Keywords

Knowledge Representation and Reasoning: Logic programming
Knowledge Representation and Reasoning: Applications
Search: Search and machine learning
Knowledge Representation and Reasoning: Learning and reasoning

Abstract

Combinatorial and optimization problems are fundamental to many industrial AI applications. Solving large-scale real-world instances of such problems typically requires careful problem formalization, specialized solvers, and expert-designed heuristics.

Thus, experts need to specify not only *what* solutions are, but also *how* they are derived.

By introducing the tool CheckMate, we show that algorithm generation via code evolution represents a paradigm shift by eliminating the need to formulate the *how*. CheckMate solely relies on the *what*. Specifically, a formal specification ensures solutions' correctness and enables systematic performance evaluation of the generated programs, while a natural language description guides the evolutionary process.

The effectiveness of our method is demonstrated on selected problems from two industrial domains: configuration and scheduling. In all cases, the evolved algorithms consistently outperform state-of-the-art solvers. This underscores the potential of formal methods in guiding code evolution for automatically solving complex real-world problems.

Veronika Semmelrock, Benedetta Strizzolo, Francesco Zuccato, Gerhard Friedrich, Patrick Rodler, and Konstantin Schekotihin. 2026. Learning to Solve and Optimize by Evolving Code. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 4054–4062. https://doi.org/10.24963/ijcai.2026/451

@inproceedings{ijcai2026p451,
  title     = {Learning to Solve and Optimize by Evolving Code},
  author    = {Semmelrock, Veronika and Strizzolo, Benedetta and Zuccato, Francesco and Friedrich, Gerhard and Rodler, Patrick and Schekotihin, Konstantin},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {4054--4062},
  year      = {2026},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2026/451},
  url       = {https://doi.org/10.24963/ijcai.2026/451},
}

TY  - CPAPER
TI  - Learning to Solve and Optimize by Evolving Code
AU  - Semmelrock, Veronika
AU  - Strizzolo, Benedetta
AU  - Zuccato, Francesco
AU  - Friedrich, Gerhard
AU  - Rodler, Patrick
AU  - Schekotihin, Konstantin
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 4054
EP  - 4062
DO  - 10.24963/ijcai.2026/451
UR  - https://doi.org/10.24963/ijcai.2026/451
ER  -