Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2507.18130 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908492603850752 |
|---|---|
| author | Deng, Le Jiang, Zhonghao Cao, Jialun Pradel, Michael Liu, Zhongxin |
| author_facet | Deng, Le Jiang, Zhonghao Cao, Jialun Pradel, Michael Liu, Zhongxin |
| contents | Natural language-driven no-code development allows users to specify software functionality using natural language (NL) instead of editing source code, promising increased productivity and democratized development. Large language models (LLMs) show potential in enabling this paradigm. In this context, software documentation acts as an NL specification for functionality. This work introduces NoCode-bench, a benchmark designed to evaluate LLMs on real-world NL-driven feature addition tasks, consisting of 634 tasks across 10 projects and 114k code changes. Each task pairs documentation updates with corresponding code implementations, validated by developer-written test cases. A subset of 114 high-quality, human-verified instances, NoCode-bench Verified, ensures reliable evaluation. Our experiments reveal that, despite high token usage, the best LLMs achieve a task success rate of only 28.07%, highlighting challenges in cross-file editing, codebase understanding, and tool calling. These findings indicate that LLMs are not yet ready for fully NL-driven no-code development. NoCode-bench lays the foundation for future advances in this area. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_18130 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | NoCode-bench: A Benchmark for Evaluating Natural Language-Driven Feature Addition Deng, Le Jiang, Zhonghao Cao, Jialun Pradel, Michael Liu, Zhongxin Software Engineering Natural language-driven no-code development allows users to specify software functionality using natural language (NL) instead of editing source code, promising increased productivity and democratized development. Large language models (LLMs) show potential in enabling this paradigm. In this context, software documentation acts as an NL specification for functionality. This work introduces NoCode-bench, a benchmark designed to evaluate LLMs on real-world NL-driven feature addition tasks, consisting of 634 tasks across 10 projects and 114k code changes. Each task pairs documentation updates with corresponding code implementations, validated by developer-written test cases. A subset of 114 high-quality, human-verified instances, NoCode-bench Verified, ensures reliable evaluation. Our experiments reveal that, despite high token usage, the best LLMs achieve a task success rate of only 28.07%, highlighting challenges in cross-file editing, codebase understanding, and tool calling. These findings indicate that LLMs are not yet ready for fully NL-driven no-code development. NoCode-bench lays the foundation for future advances in this area. |
| title | NoCode-bench: A Benchmark for Evaluating Natural Language-Driven Feature Addition |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2507.18130 |