Developers frequently write uninformative git commit messages such as "fix" or "update stuff", degrading the value of version-control history for code review, debugging, and onboarding. We present CommitLLM, a three-stage pipeline that generates concise, Conventional Commits-compliant messages from code diffs using a fine-tuned small language model.
arXiv:2607. 17532v1 Announce Type: cross Abstract: Developers frequently write uninformative git commit messages such as "fix" or "update stuff", degrading the value of version-control history for code review, debugging, and onboarding.
arXiv:2608.21074v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in research workflows and software development pipelines, yet their output remains sensitive to in...
arXiv:2604. 01029v2 Announce Type: replace-cross Abstract: Multi-LLM revision pipelines, in which a second model reviews and improves a draft produced by a first, are widely assumed to derive their gains from genuine error correction.
The paper investigates how large language models (LLMs) handle bug fixing versus problem solving in competitive programming. Using a dataset of ~3,000 Codeforces submissions and their human fixes, the authors compare LLM-generated patches to human patches and assess whether LLMs prefer to modify buggy code or generate new solutions. Results show that LLMs often alter more lines than necessary and sometimes produce entirely new solutions, performing better when allowed to generate solutions from scratch rather than patching existing code.
The paper investigates how Large Language Models (LLMs) handle bug fixing compared to human-written patches by analyzing about 3,000 Codeforces submissions. It finds that LLMs often modify more lines than necessary and sometimes produce entirely new solutions, and that they solve more problems correctly when generating solutions from scratch rather than patching existing code. The study highlights implications for AI‑assisted programming tools, suggesting a shift toward incremental problem‑solving strategies.
The paper compares two output regimes for code-editing language models: direct generation, where the model outputs the entire modified file, and iterative diff-based generation, where the model emits a sequence of localized edits. Experiments on Flutter/Dart tasks show that direct generation consistently outperforms diff-based generation across metrics such as compilation success, token efficiency, and quality judgments. However, diff-based generation can be competitive for short, spatially localized edits, particularly in refactoring and error-handling tasks with few edit steps.
arXiv:2608. 02639v1 Announce Type: cross Abstract: Production prompts rarely carry a single instruction.
The paper investigates how large language models can propagate user-specified local changes to all affected parts of artifacts generated through conversational interaction. It introduces a new benchmark for this setting and evaluates nine revision methods—including sequential reflection and parallel sampling variants—using several LLMs. Results show baseline accuracies between 68.3% and 93%, with the most cost‑effective approach achieving a 2.2%–9.7% accuracy improvement by selecting from three parallel samples.
arXiv:2607. 00700v1 Announce Type: cross Abstract: LLVM is a widely used compiler infrastructure whose scale and complexity make issue resolution labor-intensive and challenging.
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.
Compressed short-text generators can fail in two different places: the codec may discard information before generation starts, or the latent generator may produce weak codes. Without separating these failure modes, researchers can spend compute improving the wrong component.
arXiv:2501. 11086v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have shown tremendous promise in automated software engineering.