The Debugging Decay Index: Rethinking Debugging Strategies for Code LLMs
This addresses a critical limitation in iterative code generation for AI systems, providing a quantitative framework to optimize debugging strategies.
The paper tackles the problem of AI debugging effectiveness decaying exponentially, with models losing 60-80% of capability within 2-3 attempts, by introducing the Debugging Decay Index (DDI) to quantify and predict intervention points, showing that strategic fresh starts can rescue debugging effectiveness.
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.