- author = "Giovanni Squillero and Alberto Tonda and Roman Kalkreuth and Fabricio {Olivetti de Franca}",
- title = "{TinyLGP}: A Minimalist Implementation of Linear Genetic Programming",
- booktitle = "Recent Advances in Linear Genetic Programming",
- publisher = "Springer",
- year = "2026",
- editor = "Wolfgang Banzhaf and Ting Hu",
- chapter = "5",
- pages = "85--102",
- note = "forthcoming",
- keywords = "genetic algorithms, genetic programming, Linear Genetic Programming, Software, Program Synthesis, Tiny-LGP",
-
code_url = "
https://github.com/gpbench/tinyversegp",
- abstract = "Linear Genetic Programming is a type of Genetic Programming (GP) where the individual is encoded as a sequence of assembly-like instructions. Its first proposal dates back from the 1980s and has been improved throughout the decades playing unimportant role in the understanding of the search space of computer programs. Despite its relevance in the constellations of GP techniques, after almost two decades is still lacking a public reference implementation. TinyverseGP, introduced in 2025, is a GP framework that provides support to multiple representations and problem domains, such as symbolic regression, logic synthesis and policy search. This chapter presents TinyLGP, the Linear GP module integrated in TinyverseGP. The text details the main architectural choices and provides an experimental evaluation together with a discussion on the current limitations and the possible future improvements.",
-
notes = "part of \cite{Banzhaf:2026:raLGP_book}
Table 5.1 reported software URLs",
