The Debugging Decay Index: Rethinking Debugging Strategies for Code LLMs

TL;DR

This paper introduces the Debugging Decay Index (DDI), a mathematical framework that quantifies debugging effectiveness decay in AI models, enabling strategic interventions to improve iterative code debugging.

Contribution

The paper presents the DDI as a novel quantitative tool to identify when debugging becomes ineffective and guides strategic interventions for AI code debugging.

Findings

Debugging effectiveness decays exponentially within 2-3 attempts

Strategic interventions can significantly restore debugging performance

DDI provides a fundamental limit and optimization framework for AI debugging

Abstract

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.