arXiv subjects

Denis Neumüller

Publications and source records attributed to Denis Neumüller.

3 recordsLinked to original sources

arXiv2026

Exploring the Effectiveness of Abstract Syntax Tree Patterns for Algorithm Recognition

The automated recognition of algorithm implementations can support many software maintenance and re-engineering activities by providing knowledge about the concerns present in the code base. Moreover, recognizing inefficient algorithms like Bubble Sort and suggesting superior alternatives from a library can help in assessing and improving the quality of a system. Approaches from related work suffer from usability as well as scalability issues and their accuracy is not evaluated. In this paper, we investigate how well our approach based on the abstract syntax tree of a program performs for automatic algorithm recognition. To this end, we have implemented a prototype consisting of: A domain-specific language designed to capture the key features of an algorithm and used to express a search pattern on the abstract syntax tree, a matching algorithm to find these features, and an initial catalog of "ready to use" patterns. To create our search patterns we performed a web search using the algorithm name and described key features of the found reference implementations with our domain-specific language. We evaluate our prototype on a subset of the BigCloneEval benchmark containing algorithms like Fibonacci, Bubble Sort, and Binary Search. We achieve an average F1-score of 0.74 outperforming the large language model Codellama which attains 0.35. Additionally, we use multiple code clone detection tools as a baseline for comparison, achieving a recall of 0.62 while the best-performing tool reaches 0.20.

cs.SE↗

arXiv2026

Combining Static Code Analysis and Large Language Models Improves Correctness and Performance of Algorithm Recognition

Context: Since it is well-established that developers spend a substantial portion of their time understanding source code, the ability to automatically identify algorithms within source code presents a valuable opportunity. This capability can support program comprehension, facilitate maintenance, and enhance overall software quality. Objective: We empirically evaluate how combining LLMs with static code analysis can improve the automated recognition of algorithms, while also evaluating their standalone performance and dependence on identifier names. Method: We perform multiple experiments evaluating the combination of LLMs with static analysis using different filter patterns. We compare this combined approach against their standalone performance under various prompting strategies and investigate the impact of systematic identifier obfuscation on classification performance and runtime. Results: The combination of LLMs with lightweight static analysis performs surprisingly well, reducing required LLM calls by 72.39-97.50% depending on the filter pattern. This not only lowers runtime significantly but also improves F1-scores by up to 12 percentage points (pp) compared to the baseline. Regarding the different prompting strategies, in-context learning with two examples provides an effective trade-off between classification performance and runtime efficiency, achieving F1-scores of 75-77% with only a modest increase in inference time. Lastly, we find that LLMs are not solely dependent on name-information as they are still able to identify most algorithm implementations when identifiers are obfuscated. Conclusion: By combining LLMs with static analysis, we achieve substantial reductions in runtime while simultaneously improving F1-scores, underscoring the value of a hybrid approach.

cs.SE↗

arXiv2025

Providing Information About Implemented Algorithms Improves Program Comprehension: A Controlled Experiment

Context: Various approaches aim to support program comprehension by automatically detecting algorithms in source code. However, no empirical evaluations of their helpfulness have been performed. Objective: To empirically evaluate how algorithm labels - which include the algorithm's name and additional information - impact program comprehension in terms of correctness and time. Method: We conducted a controlled experiment with 56 participants, where the experimental group received code with labeled algorithms. The groups completed exercises designed to measure program comprehension as well as a post-questionnaire on label helpfulness, use cases for algorithm recognition, and reasons for self-implementation of algorithms in practice. Results: Annotating source code with algorithm labels significantly improves program comprehension (p=0.040), with a median improvement of 6 points (~23%), but does not affect completion times (p=0.991). Qualitative analysis revealed that a majority of participants perceived the labels as helpful, especially for recognizing the codes intent. Participants also proposed use cases such as error detection, optimization, and library replacement. Reasons for self-implementing algorithms included library inadequacies, performance needs and avoiding dependencies or licensing costs. Conclusion: This study shows that algorithm labels improve program comprehension, especially for developers with medium programming experience. Our qualitative analysis also sheds light on how participants benefit from the labels, further use cases for algorithm recognition and motivations behind self-implementing algorithms.

cs.SE↗