{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Adnan M"],"funding":["ACT Government, Future Jobs Fund - Open Source Institute (OpenSI) and NetApp Technology Alliance Agreement with OpenSI","Australian Government through the Department of Education's National Industry PhD Program"],"pagination":["44120"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12715212"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["15(1)"],"pubmed_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 self-debugging and provides the first systematic metric to gauge LLM-based code generation."],"journal":["Scientific reports"],"pubmed_title":["Measuring and mitigating debugging effectiveness decay in code language models."],"pmcid":["PMC12715212"],"funding_grant_id":["R01553, R01657","project 36337"],"pubmed_authors":["Adnan M","Kuhn CCN"],"additional_accession":[]},"is_claimable":false,"name":"Measuring and mitigating debugging effectiveness decay in code language models.","description":"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 self-debugging and provides the first systematic metric to gauge LLM-based code generation.","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Dec","modification":"2026-06-09T04:51:57.813Z","creation":"2026-06-09T03:07:54.369Z"},"accession":"S-EPMC12715212","cross_references":{"pubmed":["41413142"],"doi":["10.1038/s41598-025-27846-5"]}}