Linear genetic programming (LGP) is a technique that solves problems using a linear representation of programs. According to the arXiv abstract, LGP is powerful and can be applied to a variety of tasks, but it still has limitations. The abstract text cuts off before listing those limitations, so the specific weaknesses are not detailed in the available source.
Titled "Reinforced Linear Genetic Programming," the paper appears to introduce a reinforcement-based mechanism to mitigate these limitations. Because only the abstract was available, the write-up does not include implementation details or experimental results. This is a single-source summary, so there are no independent findings to compare or contrast.