How Should Diffusion Language Models Edit Code?
Quick summary
arXiv:2609.38257v1 Announce Type: cross Abstract: Code editing requires a model to decide where to make changes, generate the new content, and preserve everything else. We study how masked diffusion language models divide these responsibilities across four editing interfaces: whole-file rewriting, search-and-replace, locate-then-infill, and token-level editing. Experiments on CanItEdit reveal a composition gap: diffusion models can generate coordinated changes when the correct edit locations are supplied, but much of this capability is lost when those locations must be predicted. Access to the
Key takeaways
- arXiv:2609.38257v1 Announce Type: cross Abstract: Code editing requires a model to decide where to make changes, generate the new content, and preserve everything else.
- We study how masked diffusion language models divide these responsibilities across four editing interfaces: whole-file rewriting, search-and-replace, locate-then-infill, and token-level editing.
- Experiments on CanItEdit reveal a composition gap: diffusion models can generate coordinated changes when the correct edit locations are supplied, but much of this capability is lost when those locations must be predicted.
Why it matters
The value of this work lies as much in how it was tested as in the claim itself. Sample design, baselines, uncertainty and replication help separate a laboratory result from real-world impact.
Member comments