mlsanityData to 14 Oct 2026

FLARE: Fine-Grained Diagnostic Feedback for LLM Code Refinement

arXiv 2606.03852 ↗First posted 2 Jun 2026cs.SE cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 23 of its 34 references that are in the map. First posted on arXiv 2 Jun 2026.

Builds on

23 of 34 references.

References · 23

  1. 2017Attention Is All You Needcited by 60,361
  2. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  3. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
  4. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  5. 2026DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligencecited by 1,040
  6. 2023Teaching Large Language Models to Self-Debugcited by 988
  7. 2024A Survey on Large Language Models for Code Generationcited by 658
  8. 2020GraphCodeBERT: Pre-training Code Representations with Data Flowcited by 609
  9. 2026GLM-5: from Vibe Coding to Agentic Engineeringcited by 587
  10. 2024BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructionscited by 546
  11. 2022Generating Sequences by Learning to Self-Correctcited by 277
  12. 2024OpenCodeInterpreter: Integrating Code Generation with Execution and Refinementcited by 247
11 more
  1. 2018Correcting Length Bias in Neural Machine Translationcited by 120
  2. 2023Self-Edit: Fault-Aware Code Editor for Code Generationcited by 111
  3. 2025S*: Test Time Scaling for Code Generationcited by 98
  4. 2023Large Language Models for Test-Free Fault Localizationcited by 67
  5. 2024Calibration and Correctness of Language Models for Codecited by 49
  6. 2024AgentFL: Scaling LLM-based Fault Localization to Project-Level Contextcited by 47
  7. 2023Large Language Models and Simple, Stupid Bugscited by 45
  8. 2024CYCLE: Learning to Self-Refine the Code Generationcited by 42
  9. 2024Collu-Bench: A Benchmark for Predicting Language Model Hallucinations in Codecited by 13
  10. 2025NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debuggingcited by 4
  11. 2025Where's the Bug? Attention Probing for Scalable Fault Localizationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loopscited by 35