arXiv:2606. 14948v1 Announce Type: cross Abstract: LLMs have substantially improved software engineering yet real-world development requires architectural understanding.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2608. 04783v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into software engineering has shifted the focus from function-level generation to repository-scale assistance.
arXiv:2606. 29520v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used as assistants across the software development lifecycle, yet their ability to reason about software architecture remains largely unmeasured.
E2E-SWE is a benchmark that tests large language models’ ability to create complete, functional software repositories from scratch. It includes 186 tasks across 11 programming languages, each requiring an agent to build an installable project based solely on a natural‑language specification and an empty workspace, while passing a hidden test suite. The benchmark was crafted by software engineers and LLMs, then refined through iterative verification by autonomous agents to ensure clarity and solvability.
arXiv:2606. 01385v1 Announce Type: cross Abstract: Software architecture design is a critical yet inherently complex and knowledge-intensive phase that requires balancing competing quality attributes and adapting to evolving requirements.
arXiv:2507. 11059v3 Announce Type: replace-cross Abstract: The rapid advancement of Large Language Models (LLMs) in software engineering has revealed critical limitations in existing benchmarks, particularly the widely used SWE-bench dataset.
The study investigates whether large language models can extract Architectural Design Decisions (ADDs) from source code commits. Using four LLMs (Gemini 3 Pro, DeepSeek R1, Kimi K2, Qwen3) with zero‑shot and few‑shot prompting on 30 developer‑written ADDs, the authors evaluate outputs with ROUGE‑L, BLEU, METEOR, and BERTScore. Results show all models achieve a BERT‑F1 above 0.81, with few‑shot prompting slightly improving alignment, but the generated ADDs tend to be overly long, implementation‑focused, and lack the rationale behind the decisions.