REFINE is a tool-agnostic, evidence-aware multi-agent approach that generates Java file-level refactoring candidates by combining static analysis, smell-informed planning, LLM-based transformation, and automated re-analysis. In experiments on 450 Java files from 15 open-source systems, REFINE reduced detected code smells by 68–73% across three LLM configurations, achieving higher median reductions with smaller edits compared to a direct-prompt baseline. However, the tool’s outputs still pose risks such as assert/fail-call changes and public-method removal, requiring compilation, testing, dependency analysis, and human review before deployment.
By Muhammad Waseem, Aakash Ahmad, Pekka Abrahamsson
arXiv:2507. 11687v5 Announce Type: replace-cross Abstract: Large language models excel at code generation but struggle with code linting, particularly in generalizing to unseen or evolving best practices beyond those observed during training.
By Atharva Naik, Lawanya Baghel, Dhakshin Govindarajan, Darsh Agrawal, Yiqing Xie, Daniel Fried, Carolyn Rose
RefactorPlatform is an open‑source harness that standardizes the evaluation of repository‑scale refactoring agents by fixing the environment and systematically varying design choices such as model backbone, execution regime, and prompt specificity. Each run operates in an isolated workspace, logs detailed telemetry, and verifies changes with AST‑based checks. Experiments on 100 RefactorBench tasks show that AST‑aware chunking improves performance by 25‑30%, a lean retrieval‑augmented single agent outperforms a sub‑agent configuration, and retrieval’s accuracy gains offset its token overhead, keeping cost per successful refactoring unchanged.
By Aziz Ben Amor, Drish Mali, Mann Acharya, Vijayasri Iyer, S\'ebastien Brati\`eres
arXiv:2603. 17893v2 Announce Type: replace-cross Abstract: Methodology bugs in scientific Python code produce plausible but incorrect results that traditional linters and static analysis tools cannot detect.
By Sergey V. Samsonau
arXiv:2603. 04177v2 Announce Type: replace-cross Abstract: LLM coding agents can generate working code, but their solutions often accumulate complexity, duplication, and architectural debt.
By Alex Thillen, Niels M\"undler, Veselin Raychev, Martin Vechev
arXiv:2606. 08840v1 Announce Type: new Abstract: Code generation models are typically compared using compact execution benchmarks and aggregate pass rates, but such summaries obscure how performance varies across programming languages, problem families, and failure modes.
By Sayed Erfan Arefin
arXiv:2605.22976v2 Announce Type: replace-cross
Abstract: Large Language Models (LLMs) are increasingly integrated into software systems for diverse purposes, due to their versatility, flexibility, a...
By Zacharie Chenail-Larcher, Brahim Mahmoudi, Naouel Moha, Quentin Sti\'evenart, Florent Avellaneda
arXiv:2501. 11086v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have shown tremendous promise in automated software engineering.
By Jing Liu, Seongmin Lee, Eleonora Losiouk, Marcel B\"ohme
The paper introduces MCR-Bench, a benchmark for realistic multi‑round code review that includes 2,269 real‑world tasks across five programming languages, each annotated with fine‑grained defect information and dynamic state labels. Experiments with mainstream large language models show limited overall performance, especially as interaction rounds increase, and reveal that model accuracy varies by defect type and severity. Error analysis identifies key failure mechanisms such as cross‑round temporal misalignment and insufficient long‑range memory.
By Dewu Zheng, Yanlin Wang, Xiwen Wang, Kefeng Duan, Hongyu Zhang, Xilin Liu, Yuchi Ma, Zibin Zheng
arXiv:2607. 27146v1 Announce Type: cross Abstract: Coding agents have made substantial progress on software engineering tasks that modify existing codebases, including bug fixing and feature implementation.
By Yihao Chen, Shi Chang, Khaled Chawa, Feng Lin, Boyuan Chen, Shaowei Wang, Ahmed E. Hassan
arXiv:2607. 18642v1 Announce Type: new Abstract: Mined code corpora are abundant but uncontrolled: a snippet's semantics, surface "messiness," and difficulty are whatever the wild contained; there is no known-optimal reference to grade against; and any public sample may already sit in a model's training set.
By Yuxiang Ji
arXiv:2606. 03852v1 Announce Type: cross Abstract: Large language models often generate code with bugs.
By Yinsheng Yao, Hongxiang Zhang, Weixi Tong, Tianyi Zhang