paper-with-me

Papers

The Debugging Decay Index: Rethinking Debugging Strategies for Code LLMs

2025-06-23 · Muntasir Adnan, Carlos C. N. Kuhn

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.

📄 PDF Abstract BibTeX arXiv:2506.18403

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Methods 이 논문이 사용한 방법론

Exponential Decay Exponential Decay is a learning rate schedule where we decay the learning rate with more iterations using an exponential function: $$ \text{lr} =…

Similar Papers 제목 키워드 기반

Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?

2026-04-19 · Wang Bill Zhu, Miaosen Chai, Shangshang Wang, Yejia Liu 외 arxiv

Unlike code completion, debugging requires localizing faults and applying targeted edits. We observe that frontier LLMs often regenerate correct but over-edited solutions during debugging. To evaluate how far LLMs are fr…

Code Completion

Interactive Debugging and Steering of Multi-Agent AI Systems

2025-03-03 · Will Epperson, Gagan Bansal, Victor Dibia, Adam Fourney 외

Fully autonomous teams of LLM-powered AI agents are emerging that collaborate to perform complex tasks for users. What challenges do developers face when trying to build and debug these AI agent teams? In formative inter…

AI Agent

Toward a Unified Framework for Debugging Concept-based Models

2021-09-23 · Andrea Bontempelli, Fausto Giunchiglia, Andrea Passerini, Stefano Teso

In this paper, we tackle interactive debugging of "gray-box" concept-based models (CBMs). These models learn task-relevant concepts appearing in the inputs and then compute a prediction by aggregating the concept activat…

NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging

2025-05-21 · Weiming Zhang, Qingyao Li, Xinyi Dai, Jizheng Chen 외

Debugging is a critical aspect of LLM's coding ability. Early debugging efforts primarily focused on code-level analysis, which often falls short when addressing complex programming errors that require a deeper understan…

MLDebugging: Towards Benchmarking Code Debugging Across Multi-Library Scenarios

2025-06-15 · Jinyang Huang, Xiachong Feng, Qiguang Chen, Hanjie Zhao 외

Code debugging is a crucial task in software engineering, which attracts increasing attention. While remarkable success has been made in the era of large language models (LLMs), current research still focuses on the simp…

Benchmarking