Abstract is missing.
- Continuous Benchmark Generation for Evaluating Enterprise-scale LLM AgentsDivyanshu Saxena, Rishikesh Maurya, Xiaoxuan Ou, Gagan Somashekar, Shachee Mishra Gupta, Arun Iyer, Yu Kang 0006, Chetan Bansal, Aditya Akella, Saravan Rajmohan. 1-5 [doi]
- CP-Agent: Agentic Constraint ProgrammingStefan Szeider. 6-13 [doi]
- An Automated Methodology for Generating Labeled Datasets of Semantic Errors in CodeMahmoud Kassem, Francisco Ribeiro, Sarah Nadi. 14-20 [doi]
- Code vs Serialized AST Inputs for LLM-Based Code Summarization: An Empirical StudyShijia Dong, Haoruo Zhao, Paul Harvey. 21-28 [doi]
- Multi-task Code LLMs: Data Mix or Model Merge?Mingzhi Zhu, Michele Merler, Boris Sobolev, Rahul Krishna, Raju Pavuluri, Stacy Patterson. 29-36 [doi]
- English or Chinese? Investigating the Impact of Prompt Language on Large Language Models for Code SummarizationYijia Tang, Zhiqiu Huang, Jian Xie 0004, Yaoshen Yu, Bowei Xia, Enya Shen, Yukun Cao. 37-41 [doi]
- The Hidden DNA of LLM-Generated JavaScript: Structural Patterns Enable High-Accuracy Authorship AttributionNorbert Tihanyi, Bilel Cherif, Richard A. Dubniczky, Mohamed Amine Ferrag, Lajos Balkanyi, Tamás Bisztray. 42-50 [doi]
- Learning Functional Equivalence via Supervised Contrastive Code-Problem AlignmentSiu Wun Cheung, Harshitha Menon. 51-58 [doi]
- Code Roulette: How Prompt Variability Affects LLM Code GenerationAndrei Paleyes, Diana Robinson, Radzim Sendyka, Christian Cabrera 0001, Neil D. Lawrence. 59-66 [doi]
- Statistical Independence Aware Caching for LLM WorkflowsYihan Dai, Dimitrios Stamatios Bouras, Haoxiang Jia, Sergey Mechtaev. 67-72 [doi]
- An Initial Exploration of Contrastive Prompt Tuning to Generate Energy-Efficient CodeSophie Weidmann, Fernando Castor. 73-81 [doi]
- Do LLMs Dream of Energy-Efficient Code?Antimo Di Bernardo, Gianluca Capozzi, Pasquale De Rosa, Daniele Cono D'Elia, Leonardo Querzoni, Giuseppe Antonio Di Luna, Valerio Schiavoni. 82-89 [doi]
- Achieving Productivity Gains with AI-based IDE features: A Journey at GoogleMaxim Tabachnyk, Xu Shu, Alexander Frömmgen, Pavel Sychev, Vahid Meimand, Ilia Krets, Stanislav Pyatykh, Abner Araujo, Kristof Molnar, Satish Chandra 0001. 90-96 [doi]
- Usage, Effects and Requirements for AI Coding Assistants in the Enterprise: An Empirical StudyMichele Merler, Rangeet Pan, Rahul Krishna, Tin Kam Ho, Raju Pavuluri, Maja Vukovic. 97-104 [doi]
- Benchmarking LLM Commit Message Generation through a Developer-centric Pairwise Preference FrameworkLucas Aguiar, Matheus Freitas, Matheus Paixão, Rafael Carmo. 105-112 [doi]
- RuberDuckBench: A Benchmark for AI Coding AssistantsFerida Mohammed, Fatma Ayad, Petros Maniatis, Satish Chandra 0001, Elizabeth Dinella. 113-120 [doi]
- Towards LLM-guided Semantic Validation of Autonomous Driving Safety PoliciesQingzhao Zhang 0001, Z. Morley Mao. 121-125 [doi]
- Evaluating LLMs-Driven Java Code Refactoring from a Developer's PerspectiveJavel Freitas, Guilherme Pereira, Lara Lima, Caio Rian de Sousa, Edivar Filho, José Cezar de Souza Filho, Paulo Henrique M. Maia, Carla I. M. Bezerra. 126-130 [doi]
- A Spec-Driven Workflow for AI-Assisted Domain-Driven Development: Insights from PracticeJefferson de Barros Santos. 131-134 [doi]
- Towards Improving in-IDE Code Completion for Driver DevelopmentBatuhan Raif Karagöz, Mahesh Jayasankar, Saurabh Bodhe, Subhayan Roy, Lejin Varghese, Yonas Bedasso, Max Kiehn. 135-142 [doi]
- LLM-Driven SQL Remediation: Towards Safe and Explainable Code for Automated Schema RefactoringAntony Seabra de Medeiros, Claudio Cavalcante, Nicolaas Ruberg, Sérgio Lifschitz. 143-150 [doi]
- An Empirical Study of C to Rust Translation using Local Large-Language ModelsNathan Rutherford, Dan O'Keeffe. 151-158 [doi]
- SecRepoBench: Benchmarking Code Agents for Secure Code Completion in Real-World RepositoriesChihao Shen, Connor Dilgren, Purva Chiniya, Luke Griffith, Yu Ding, Yizheng Chen. 159-166 [doi]
- MAsFL: Data-Secure, Efficient and Accurate Fault Localization with Multi-Agent Small Language ModelsDuong Pham Duc, Hiroshi Sato 0001, Masao Kubo. 167-174 [doi]
- Diverse LLMs vs. Vulnerabilities: Who Detects and Fixes Them Better?Arastoo Zibaeirad, Marco Vieira. 175-183 [doi]
- RAG Against the Machine: Zero-Shot Software Vulnerabilities Classification using LLMsEdvin Nordqvist, Changjie Wang, Simone Ferlin, Mariano Scazzariello, Marco Chiesa. 184-191 [doi]
- LLM-Powered On-Demand Test Suites in Self-Graded Student Programming AssignmentsChang Liu. 192-196 [doi]
- Natural Language Summarization Enables Multi-Repository Bug Localization by LLMs in Microservice ArchitecturesAmirkia Rafiei Oskooei, Selcan Yukcu, Mehmet Cevheri Bozoglan, Mehmet S. Aktas. 197-205 [doi]