{"ID":3004706,"CreatedAt":"2026-06-03T03:09:48.883664427Z","UpdatedAt":"2026-06-05T11:43:53.432517148Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.03852","arxiv_id":"2606.03852","title":"FLARE: Fine-Grained Diagnostic Feedback for LLM Code Refinement","abstract":"Large language models often generate code with bugs. Existing methods rely on feedback signals such as test failures and self-critiques to iteratively refine the generated code. Such signals are either too coarse-grained or too high-level, which is not sufficient to inform the model where to fix the bug. In this work, we present Flare, an iterative framework with a lightweight diagnostic model that predicts line-level suspiciousness signals for bug localization and code refinement. Given the inherent uncertainty of diagnostic predictions, Flare searches over the top-k suspicious regions and selects the best candidate according to execution outcomes. Experiments on LiveCodeBench and BigCodeBench with five base LLMs show that, even without candidate search (k=1), Flare outperforms the strongest baseline with an absolute improvement from 1.72% to 7.42%. Furthermore, searching over 10 candidates yields an average improvement of 8.50% compared with no candidate search. When evaluated in isolation, our lightweight diagnostic model achieves the best performance compared with recent fault localization methods, demonstrating that it can provide reliable fine-grained guidance for code refinement.","short_abstract":"Large language models often generate code with bugs. Existing methods rely on feedback signals such as test failures and self-critiques to iteratively refine the generated code. Such signals are either too coarse-grained or too high-level, which is not sufficient to inform the model where to fix the bug. In this work,...","url_abs":"https://arxiv.org/abs/2606.03852","url_pdf":"https://arxiv.org/pdf/2606.03852v1","authors":"[\"Yinsheng Yao\",\"Hongxiang Zhang\",\"Weixi Tong\",\"Tianyi Zhang\"]","published":"2026-06-02T16:29:17Z","proceeding":"cs.SE","tasks":"[\"cs.SE\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}