The Debugging Decay Index: Rethinking Debugging Strategies for Code LLMs
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908723994165248 |
|---|---|
| author | Adnan, Muntasir Kuhn, Carlos C. N. |
| author_facet | Adnan, Muntasir Kuhn, Carlos C. N. |
| contents | The effectiveness of AI debugging follows a predictable exponential decay pattern; most models lose 60-80% of their debugging capability within just 2-3 attempts, despite iterative debugging being a critical capability for practical code generation systems. We introduce the Debugging Decay Index (DDI), a mathematical framework that quantifies when debugging becomes ineffective and predicts intervention points. Our strategic fresh start approach shifts from exploitation to exploration at strategic points in the debugging process, demonstrating that well-timed interventions can rescue the effectiveness of debugging. DDI reveals a fundamental limitation in current AI debugging and provides the first quantitative framework for optimising iterative code generation strategies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_18403 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Debugging Decay Index: Rethinking Debugging Strategies for Code LLMs Adnan, Muntasir Kuhn, Carlos C. N. Software Engineering Artificial Intelligence The effectiveness of AI debugging follows a predictable exponential decay pattern; most models lose 60-80% of their debugging capability within just 2-3 attempts, despite iterative debugging being a critical capability for practical code generation systems. We introduce the Debugging Decay Index (DDI), a mathematical framework that quantifies when debugging becomes ineffective and predicts intervention points. Our strategic fresh start approach shifts from exploitation to exploration at strategic points in the debugging process, demonstrating that well-timed interventions can rescue the effectiveness of debugging. DDI reveals a fundamental limitation in current AI debugging and provides the first quantitative framework for optimising iterative code generation strategies. |
| title | The Debugging Decay Index: Rethinking Debugging Strategies for Code LLMs |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2506.18403 |