SEJun 30

FeatX: Editing Software by Editing Features for Repository-Level Code Evolution

arXiv:2606.312068.0Has Code
Predicted impact top 56% in SE · last 90 daysOriginality Incremental advance
AI Analysis

For developers using LLMs for software evolution, FeatX provides a more intuitive feature-based interaction paradigm that reduces manual context management.

FeatX introduces a feature-oriented tool for repository-level code evolution that reduces cognitive load and improves usability over vanilla ChatGPT, achieving a 42.6% relative improvement in function-level modification localization F1 at a cost of $0.07.

Large language models (LLMs) are increasingly used for software evolution, yet most interaction paradigms remain code-centric and require manual context management and prompt iteration. We present FeatX, a feature-oriented tool for editing software by editing features. Given an existing repository, FeatX extracts a hierarchical epic-feature structure with explicit feature-to-code mappings, then invokes a three-stage Evolution Agent to translate feature edits into code patches. The workflow is exposed through four coordinated panels. Across a controlled user study and replay experiments on 38 real-world feature-editing commits, FeatX significantly reduces cognitive load and improves usability compared with vanilla ChatGPT. It also achieves a 42.6\% relative improvement in function-level modification localization F1 over strong LLM baselines, at substantially lower cost (\$0.07 in total). The tool and collected dataset are available at https://github.com/a496263365/FeatX/tree/demo, with a demonstration video at https://youtu.be/OZqKZ4Ii-yM.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes