Diffs vs. Whole Files: An Empirical Comparison of Iterative Edit-Based and Direct Generation for Flutter/Dart Code Models
Large language models used for code editing can be trained and deployed in at least two output regimes: direct generation, where the model emits the entire modified file in one shot, and iterative diff-based generation ("steps"), where the model emits a sequence of localized search/replace edits applied one at a time until it signals completion or a step budget is exhausted. The diff-based regime is attractive because it mirrors how developers edit code and should require far fewer generated tokens per turn. We train two code models - a 100M-parameter model trained from scratch (Rainbow-Pony-100M) and a fine-tuned Qwen2.5-Coder-0.5B - in both regimes on a shared Flutter/Dart dataset, and ...
| Authors | Andrej Andrejev |
|---|---|
| Primary category | cs.SE |
| Published | 5 September 2026 |
| Last updated at source | 5 September 2026 |
Connected in the knowledge graph
- bbidpa/flutter-diff-steps-v1Dataset · cited by
- bbidpa/Qwen2.5-Coder-0.5B-Flutter-directModel · cited by
- bbidpa/Rainbow-Pony-100m-Flutter-stepsModel · cited by
- bbidpa/Qwen2.5-Coder-0.5B-Flutter-stepsModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.