arXiv subjects

Dominik Sobania

Publications and source records attributed to Dominik Sobania.

At least 19 recordsLinked to original sources

arXiv2026

SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering

Agent skills are increasingly used to configure coding agents for software engineering (SE) tasks, yet current practice treats them as static, hand-crafted assets, or evolved on pass rate alone. This is insufficient: a skill can improve task success while substantially raising token cost, or introducing misleading guidance. We argue that SE agent skill bundles can be treated as multi-objective search objects and present SkillMOO, a framework that evolves skill bundles through LLM-proposed edits and NSGA-II Pareto selection on pass rate and inference cost. Evaluated across all 16 SkillsBench SE tasks, SkillMOO achieves the top pass rate rank on 11 of 12 non-zero-pass tasks while achieving cost reductions of up to 31.7% over static bundles, with pass rate gains up to 21 percentage points. Analysis of 38 skill edits shows that pruning and substitution dominate successful operations, offering actionable principles for skill bundle design. Thereby, the current practice of deploying skills without cost-aware validation leaves better skill configurations unexplored, motivating a new class of cost-aware, search-based skill engineering.

cs.SE↗

arXiv2026

ROIDS: Robust Outlier-Aware Informed Down-Sampling

Informed down-sampling (IDS) is known to improve performance in symbolic regression when combined with various selection strategies, especially tournament selection. However, recent work found that IDS's gains are not consistent across all problems. Our analysis reveals that IDS performance is worse for problems containing outliers. IDS systematically favors including outliers in subsets which pushes GP towards finding solutions that overfit to outliers. To address this, we introduce ROIDS (Robust Outlier-Aware Informed Down-Sampling), which excludes potential outliers from the sampling process of IDS. With ROIDS it is possible to keep the advantages of IDS without overfitting to outliers and to compete on a wide range of benchmark problems. This is also reflected in our experiments in which ROIDS shows the desired behavior on all studied benchmark problems. ROIDS consistently outperforms IDS on synthetic problems with added outliers as well as on a wide range of complex real-world problems, surpassing IDS on over 80% of the real-world benchmark problems. Moreover, compared to all studied baseline approaches, ROIDS achieves the best average rank across all tested benchmark problems. This robust behavior makes ROIDS a reliable down-sampling method for selection in symbolic regression, especially when outliers may be included in the data set.

cs.NE↗

arXiv2025

Transformer Semantic Genetic Programming for d-dimensional Symbolic Regression Problems

Transformer Semantic Genetic Programming (TSGP) is a semantic search approach that uses a pre-trained transformer model as a variation operator to generate offspring programs with high semantic similarity to a given parent. Unlike other semantic GP approaches that rely on fixed syntactic transformations, TSGP aims to learn diverse structural variations that lead to solutions with similar semantics. We find that a single transformer model trained on millions of programs is able to generalize across symbolic regression problems of varying dimension. Evaluated on 24 real-world and synthetic datasets, TSGP significantly outperforms standard GP, SLIM_GSGP, Deep Symbolic Regression, and Denoising Autoencoder GP, achieving an average rank of 1.58 across all benchmarks. Moreover, TSGP produces more compact solutions than SLIM_GSGP, despite its higher accuracy. In addition, the target semantic distance is able to effectively adjust the step size in the semantic space: small values enable consistent improvement in fitness but often lead to larger programs, while larger values promote faster convergence and compactness. Thus, the target semantic distance provides an effective mechanism for balancing exploration and exploitation.

cs.LG↗

arXiv2025

LLM-Guided Genetic Improvement: Envisioning Semantic Aware Automated Software Evolution

Genetic Improvement (GI) of software automatically creates alternative software versions that are improved according to certain properties of interests (e.g., running-time). Search-based GI excels at navigating large program spaces, but operates primarily at the syntactic level. In contrast, Large Language Models (LLMs) offer semantic-aware edits, yet lack goal-directed feedback and control (which is instead a strength of GI). As such, we propose the investigation of a new research line on AI-powered GI aimed at incorporating semantic aware search. We take a first step at it by augmenting GI with the use of automated clustering of LLM edits. We provide initial empirical evidence that our proposal, dubbed PatchCat, allows us to automatically and effectively categorize LLM-suggested patches. PatchCat identified 18 different types of software patches and categorized newly suggested patches with high accuracy. It also enabled detecting NoOp edits in advance and, prospectively, to skip test suite execution to save resources in many cases. These results, coupled with the fact that PatchCat works with small, local LLMs, are a promising step toward interpretable, efficient, and green GI. We outline a rich agenda of future work and call for the community to join our vision of building a principled understanding of LLM-driven mutations, guiding the GI search process with semantic signals.

cs.SE↗

arXiv2025

A Performance Analysis of Lexicase-Based and Traditional Selection Methods in GP for Symbolic Regression

In recent years, several new lexicase-based selection variants have emerged due to the success of standard lexicase selection in various application domains. For symbolic regression problems, variants that use an epsilon-threshold or batches of training cases, among others, have led to performance improvements. Lately, especially variants that combine lexicase selection and down-sampling strategies have received a lot of attention. This paper evaluates the most relevant lexicase-based selection methods as well as traditional selection methods in combination with different down-sampling strategies on a wide range of symbolic regression problems. In contrast to most work, we not only compare the methods over a given evaluation budget, but also over a given time budget as time is usually limited in practice. We find that for a given evaluation budget, epsilon-lexicase selection in combination with a down-sampling strategy outperforms all other methods. If the given running time is very short, lexicase variants using batches of training cases perform best. Further, we find that the combination of tournament selection with informed down-sampling performs well in all studied settings.

cs.NE↗

arXiv2025

Was Tournament Selection All We Ever Needed? A Critical Reflection on Lexicase Selection

The success of lexicase selection has led to various extensions, including its combination with down-sampling, which further increased performance. However, recent work found that down-sampling also leads to significant improvements in the performance of tournament selection. This raises the question of whether tournament selection combined with down-sampling is the better choice, given its faster running times. To address this question, we run a set of experiments comparing epsilon-lexicase and tournament selection with different down-sampling techniques on synthetic problems of varying noise levels and problem sizes as well as real-world symbolic regression problems. Overall, we find that down-sampling improves generalization and performance even when compared over the same number of generations. This means that down-sampling is beneficial even with way fewer fitness evaluations. Additionally, down-sampling successfully reduces code growth. We observe that population diversity increases for tournament selection when combined with down-sampling. Further, we find that tournament selection and epsilon-lexicase selection with down-sampling perform similar, while tournament selection is significantly faster. We conclude that tournament selection should be further analyzed and improved in future work instead of only focusing on the improvement of lexicase variants.

cs.NE↗

arXiv2025

Transformer Semantic Genetic Programming for Symbolic Regression

In standard genetic programming (stdGP), solutions are varied by modifying their syntax, with uncertain effects on their semantics. Geometric-semantic genetic programming (GSGP), a popular variant of GP, effectively searches the semantic solution space using variation operations based on linear combinations, although it results in significantly larger solutions. This paper presents Transformer Semantic Genetic Programming (TSGP), a novel and flexible semantic approach that uses a generative transformer model as search operator. The transformer is trained on synthetic test problems and learns semantic similarities between solutions. Once the model is trained, it can be used to create offspring solutions with high semantic similarity also for unseen and unknown problems. Experiments on several symbolic regression problems show that TSGP generates solutions with comparable or even significantly better prediction quality than stdGP, SLIM_GSGP, DSR, and DAE-GP. Like SLIM_GSGP, TSGP is able to create new solutions that are semantically similar without creating solutions of large size. An analysis of the search dynamic reveals that the solutions generated by TSGP are semantically more similar than the solutions generated by the benchmark approaches allowing a better exploration of the semantic solution space.

cs.NE↗

arXiv2024

ComfyGI: Automatic Improvement of Image Generation Workflows

Automatic image generation is no longer just of interest to researchers, but also to practitioners. However, current models are sensitive to the settings used and automatic optimization methods often require human involvement. To bridge this gap, we introduce ComfyGI, a novel approach to automatically improve workflows for image generation without the need for human intervention driven by techniques from genetic improvement. This enables image generation with significantly higher quality in terms of the alignment with the given description and the perceived aesthetics. On the performance side, we find that overall, the images generated with an optimized workflow are about 50% better compared to the initial workflow in terms of the median ImageReward score. These already good results are even surpassed in our human evaluation, as the participants preferred the images improved by ComfyGI in around 90% of the cases.

cs.CV↗

arXiv2024

Untangling the Effects of Down-Sampling and Selection in Genetic Programming

Genetic programming systems often use large training sets to evaluate the quality of candidate solutions for selection, which is often computationally expensive. Down-sampling training sets has long been used to decrease the computational cost of evaluation in a wide range of application domains. More specifically, recent studies have shown that both random and informed down-sampling can substantially improve problem-solving success for GP systems that use the lexicase parent selection algorithm. We test whether these down-sampling techniques can also improve problem-solving success in the context of three other commonly used selection methods, fitness-proportionate, tournament, implicit fitness sharing plus tournament selection, across six program synthesis GP problems. We verified that down-sampling can significantly improve the problem-solving success for all three of these other selection schemes, demonstrating its general efficacy. We discern that the selection pressure imposed by the selection scheme does not interact with the down-sampling method. However, we find that informed down-sampling can improve problem solving success significantly over random down-sampling when the selection scheme has a mechanism for diversity maintenance like lexicase or implicit fitness sharing. Overall, our results suggest that down-sampling should be considered more often when solving test-based problems, regardless of the selection scheme in use.

cs.NE↗

arXiv2024

Large Language Models Suffer From Their Own Output: An Analysis of the Self-Consuming Training Loop

Large Language Models (LLM) are already widely used to generate content for a variety of online platforms. As we are not able to safely distinguish LLM-generated content from human-produced content, LLM-generated content is used to train the next generation of LLMs, giving rise to a self-consuming training loop. From the image generation domain we know that such a self-consuming training loop reduces both quality and diversity of images finally ending in a model collapse. However, it is unclear whether this alarming effect can also be observed for LLMs. Therefore, we present the first study investigating the self-consuming training loop for LLMs. Further, we propose a novel method based on logic expressions that allows us to unambiguously verify the correctness of LLM-generated content, which is difficult for natural language text. We find that the self-consuming training loop produces correct outputs, however, the output declines in its diversity depending on the proportion of the used generated data. Fresh data can slow down this decline, but not stop it. Given these concerning results, we encourage researchers to study methods to negate this process.

cs.LG↗

arXiv2024

Informed Down-Sampled Lexicase Selection: Identifying productive training cases for efficient problem solving

Genetic Programming (GP) often uses large training sets and requires all individuals to be evaluated on all training cases during selection. Random down-sampled lexicase selection evaluates individuals on only a random subset of the training cases allowing for more individuals to be explored with the same amount of program executions. However, creating a down-sample randomly might exclude important cases from the current down-sample for a number of generations, while cases that measure the same behavior (synonymous cases) may be overused despite their redundancy. In this work, we introduce Informed Down-Sampled Lexicase Selection. This method leverages population statistics to build down-samples that contain more distinct and therefore informative training cases. Through an empirical investigation across two different GP systems (PushGP and Grammar-Guided GP), we find that informed down-sampling significantly outperforms random down-sampling on a set of contemporary program synthesis benchmark problems. Through an analysis of the created down-samples, we find that important training cases are included in the down-sample consistently across independent evolutionary runs and systems. We hypothesize that this improvement can be attributed to the ability of Informed Down-Sampled Lexicase Selection to maintain more specialist individuals over the course of evolution, while also benefiting from reduced per-evaluation costs.

cs.NE↗

arXiv2023

Enhancing Genetic Improvement Mutations Using Large Language Models

Large language models (LLMs) have been successfully applied to software engineering tasks, including program repair. However, their application in search-based techniques such as Genetic Improvement (GI) is still largely unexplored. In this paper, we evaluate the use of LLMs as mutation operators for GI to improve the search process. We expand the Gin Java GI toolkit to call OpenAI's API to generate edits for the JCodec tool. We randomly sample the space of edits using 5 different edit types. We find that the number of patches passing unit tests is up to 75% higher with LLM-based edits than with standard Insert edits. Further, we observe that the patches found with LLMs are generally less diverse compared to standard edits. We ran GI with local search to find runtime improvements. Although many improving patches are found by LLM-enhanced GI, the best improving patch was found by standard GI.

cs.SE↗

arXiv2023

Do You Trust ChatGPT? -- Perceived Credibility of Human and AI-Generated Content

This paper examines how individuals perceive the credibility of content originating from human authors versus content generated by large language models, like the GPT language model family that powers ChatGPT, in different user interface versions. Surprisingly, our results demonstrate that regardless of the user interface presentation, participants tend to attribute similar levels of credibility. While participants also do not report any different perceptions of competence and trustworthiness between human and AI-generated content, they rate AI-generated content as being clearer and more engaging. The findings from this study serve as a call for a more discerning approach to evaluating information sources, encouraging users to exercise caution and critical thinking when engaging with content generated by AI systems.

cs.HC↗

arXiv2023

Down-Sampled Epsilon-Lexicase Selection for Real-World Symbolic Regression Problems

Epsilon-lexicase selection is a parent selection method in genetic programming that has been successfully applied to symbolic regression problems. Recently, the combination of random subsampling with lexicase selection significantly improved performance in other genetic programming domains such as program synthesis. However, the influence of subsampling on the solution quality of real-world symbolic regression problems has not yet been studied. In this paper, we propose down-sampled epsilon-lexicase selection which combines epsilon-lexicase selection with random subsampling to improve the performance in the domain of symbolic regression. Therefore, we compare down-sampled epsilon-lexicase with traditional selection methods on common real-world symbolic regression problems and analyze its influence on the properties of the population over a genetic programming run. We find that the diversity is reduced by using down-sampled epsilon-lexicase selection compared to standard epsilon-lexicase selection. This comes along with high hyperselection rates we observe for down-sampled epsilon-lexicase selection. Further, we find that down-sampled epsilon-lexicase selection outperforms the traditional selection methods on all studied problems. Overall, with down-sampled epsilon-lexicase selection we observe an improvement of the solution quality of up to 85% in comparison to standard epsilon-lexicase selection.

cs.NE↗

arXiv2023

An Analysis of the Automatic Bug Fixing Performance of ChatGPT

To support software developers in finding and fixing software bugs, several automated program repair techniques have been introduced. Given a test suite, standard methods usually either synthesize a repair, or navigate a search space of software edits to find test-suite passing variants. Recent program repair methods are based on deep learning approaches. One of these novel methods, which is not primarily intended for automated program repair, but is still suitable for it, is ChatGPT. The bug fixing performance of ChatGPT, however, is so far unclear. Therefore, in this paper we evaluate ChatGPT on the standard bug fixing benchmark set, QuixBugs, and compare the performance with the results of several other approaches reported in the literature. We find that ChatGPT's bug fixing performance is competitive to the common deep learning approaches CoCoNut and Codex and notably better than the results reported for the standard program repair approaches. In contrast to previous approaches, ChatGPT offers a dialogue system through which further information, e.g., the expected output for a certain input or an observed error message, can be entered. By providing such hints to ChatGPT, its success rate can be further increased, fixing 31 out of 40 bugs, outperforming state-of-the-art.

cs.SE↗

arXiv2023

MTGP: Combining Metamorphic Testing and Genetic Programming

Genetic programming is an evolutionary approach known for its performance in program synthesis. However, it is not yet mature enough for a practical use in real-world software development, since usually many training cases are required to generate programs that generalize to unseen test cases. As in practice, the training cases have to be expensively hand-labeled by the user, we need an approach to check the program behavior with a lower number of training cases. Metamorphic testing needs no labeled input/output examples. Instead, the program is executed multiple times, first on a given (randomly generated) input, followed by related inputs to check whether certain user-defined relations between the observed outputs hold. In this work, we suggest MTGP, which combines metamorphic testing and genetic programming and study its performance and the generalizability of the generated programs. Further, we analyze how the generalizability depends on the number of given labeled training cases. We find that using metamorphic testing combined with labeled training cases leads to a higher generalization rate than the use of labeled training cases alone in almost all studied configurations. Consequently, we recommend researchers to use metamorphic testing in their systems if the labeling of the training data is expensive.

cs.SE↗

arXiv2022

The Randomness of Input Data Spaces is an A Priori Predictor for Generalization

Over-parameterized models can perfectly learn various types of data distributions, however, generalization error is usually lower for real data in comparison to artificial data. This suggests that the properties of data distributions have an impact on generalization capability. This work focuses on the search space defined by the input data and assumes that the correlation between labels of neighboring input values influences generalization. If correlation is low, the randomness of the input data space is high leading to high generalization error. We suggest to measure the randomness of an input data space using Maurer's universal. Results for synthetic classification tasks and common image classification benchmarks (MNIST, CIFAR10, and Microsoft's cats vs. dogs data set) find a high correlation between the randomness of input data spaces and the generalization error of deep neural networks for binary classification problems.

cs.LG↗

arXiv2021

Choose Your Programming Copilot: A Comparison of the Program Synthesis Performance of GitHub Copilot and Genetic Programming

GitHub Copilot, an extension for the Visual Studio Code development environment powered by the large-scale language model Codex, makes automatic program synthesis available for software developers. This model has been extensively studied in the field of deep learning, however, a comparison to genetic programming, which is also known for its performance in automatic program synthesis, has not yet been carried out. In this paper, we evaluate GitHub Copilot on standard program synthesis benchmark problems and compare the achieved results with those from the genetic programming literature. In addition, we discuss the performance of both approaches. We find that the performance of the two approaches on the benchmark problems is quite similar, however, in comparison to GitHub Copilot, the program synthesis approaches based on genetic programming are not yet mature enough to support programmers in practical software development. Genetic programming usually needs a huge amount of expensive hand-labeled training cases and takes too much time to generate solutions. Furthermore, source code generated by genetic programming approaches is often bloated and difficult to understand. For future work on program synthesis with genetic programming, we suggest researchers to focus on improving the execution time, readability, and usability.

cs.SE↗