Diffs vs. Whole Files: An Empirical Comparison of Iterative Edit-Based and Direct Generation for Flutter/Dart Code Models
- 类型：arxiv
- 标识：2609.05779
- 链接：https://arxiv.org/abs/2609.05779
- 主分类：engineering
- 形态：application
- TLDR：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-1
- 待LLM分类：是
- 来源文件：
- /inbox/tom/_candidates/2026-09-10-agent-rag-longcontext-candidates.json