EASE 2025
Tue 17 - Fri 20 June 2025 Istanbul, Turkey
Thu 19 Jun 2025 13:55 - 14:10 at Senate Hall - LLMs for SE (Test) Chair(s): Ayse Tosun

Mutation testing is a widely recognized technique for assessing and enhancing the effectiveness of software test suites by introducing deliberate code mutations. However, its application often results in overly large test suites, as developers generate numerous tests to kill specific mutants, increasing computational overhead. This paper introduces PRIMG (Prioritization and Refinement Integrated Mutation-driven Generation), a novel framework for incremental and adaptive test case generation for Solidity smart contracts. PRIMG integrates two core components: a mutation prioritization module, which employs a machine learning model trained on mutant subsumption graphs to predict the usefulness of surviving mutants, and a test case generation module, which utilizes Large Language Models (LLMs) to generate and iteratively refine test cases to achieve syntactic and behavioral correctness.

We evaluated PRIMG on real-world Solidity projects from Code4Arena to assess its effectiveness in improving mutation scores and generating high-quality test cases. The experimental results demonstrate that PRIMG significantly reduces test suite size while maintaining high mutation coverage. The prioritization module consistently outperformed random mutant selection, enabling the generation of high-impact tests with reduced computational effort. Furthermore, the refining process enhanced the correctness and utility of LLM-generated tests, addressing their inherent limitations in handling edge cases and complex program logic.

Thu 19 Jun

Displayed time zone: Athens change

13:30 - 15:00
LLMs for SE (Test)Research Papers / Short Papers, Emerging Results / Industry Papers / AI Models / Data at Senate Hall
Chair(s): Ayse Tosun Istanbul Technical University
13:30
15m
Talk
Can We Enhance Bug Report Quality Using LLMs?: An Empirical Study of LLM-Based Bug Report Generation
AI Models / Data
Jagrit Acharya University of Calgary, Gouri Ginde (Deshpande) University of Calgary
13:45
10m
Talk
LELANTE: LEveraging LLM for Automated ANdroid TEsting
Short Papers, Emerging Results
Shamit Fatin Bangladesh University of Engineering and Technology (BUET), Mehbubul Hasan Al-Quvi Bangladesh University of Engineering and Technology (BUET), Haz Sameen Shahgir University of California, Riverside, Sukarna Barua Bangladesh University of Engineering and Technology (BUET), Anindya Iqbal Bangladesh University of Engineering and Technology Dhaka, Bangladesh, Sadia Sharmin Bangladesh University of Engineering and Technology (BUET), Md. Mostofa Akbar Bangladesh University of Engineering and Technology (BUET), Kallol Kumar Pal Samsung R&D Institute Bangladesh (SRBD), A. Asif Al Rashid Samsung R&D Institute Bangladesh (SRBD)
Pre-print
13:55
15m
Talk
PRIMG : Efficient LLM-driven Test Generation Using Mutant Prioritization
AI Models / Data
Mohamed Salah Bouafif Polytechnique Montréal, Mohammad Hamdaqa Polytechnique Montreal, Edward Zulkoski Quantstamp
Pre-print
14:10
15m
Talk
Quality Assessment of Python Tests Generated by Large Language Models
Research Papers
Victor Alves Federal University of Ceará (UFC), Carla Bezerra Federal University of Ceará (UFC), Ivan Machado Federal University of Bahia - UFBA, Larissa Rocha University of the State of Bahia (UNEB), Tássio Virgínio Federal University of Bahia (UFBA), Publio Silva Federal University of Ceará (UFC)
14:25
10m
Talk
Test Code Generation at Ericsson using Program Analysis Augmented Fine Tuned LLMs
Industry Papers
Sai Krishna Bala Ericsson, Balvinder Singh Ericsson, Sujoy Roychowdhury Ericsson, Giriprasad Sridhara Ericsson, Sourav Mazumdar Ericsson, Magnus Sandelin Ericsson, Dimitris Rentas Ericsson, Maciej Nalepa Ericsson, Karol Sawicki Ericsson, Jakub Gajda Ericsson
14:35
15m
Talk
Tracking the Moving Target: A Framework for Continuous Evaluation of LLM Test Generation in Industry
Research Papers
Maider Azanza University of the Basque Country (UPV/EHU), Beatriz Pérez Lamancha LKS Next, Eneko Pizarro University of the Basque Country (UPV/EHU)
Pre-print
14:50
10m
Talk
Leveraging LLMs for Automated Translation of Legacy Code: A Case Study on PL/SQL to Java Transformation
Industry Papers
Lola Solovyeva University of Twente, Eduardo Carneiro Oliveira Utrecht University, Shiyu Fan Eindhoven University of Technology, Alper Tuncay Leiden University, Shamil Gareev Eötvös Loránd University, Andrea Capiluppi University of Groningen
:
:
:
: