mlsanityData to 14 Oct 2026

Unlocking LLM Code Correction with Iterative Feedback Loops

arXiv 2606.17514 ↗First posted 16 Jun 2026cs.SE cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Large Language Models have shown remarkable capabilities in code generation. However, most existing evaluations focus only on single-attempt accuracy and overlook the iterative refinement process that is central to real-world programming. This study presents a systematic investigation of LLMs' ability to rectify their own code through execution feedback. Using real-world programming problems across four models and two major programming languages, this study evaluates performance using iterative refinement framework where LLMs receive compiler error messages and testcase feedback after each attempt. This study introduces metrics to evaluate code failures, analyze rectification patterns, and compare the effectiveness of reasoning and non-reasoning models, offering actionable insights into both the understanding and practical application of feedback loops in LLM-driven code generation systems. Results show that reasoning models consistently improve over iterations, substantially outperforming non-reasoning models in leveraging feedback, while syntactic and runtime errors are far more tractable than logical or algorithmic failures.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 24 of its 33 references that are in the map. First posted on arXiv 16 Jun 2026.

Builds on

24 of 33 references.

References · 24

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  2. 2021Program Synthesis with Large Language Modelscited by 3,637
  3. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  4. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 885
  5. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  6. 2024A Survey on Large Language Models for Code Generationcited by 658
  7. 2025Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Modelscited by 138
  8. 2024Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-stepcited by 127
  9. 2025Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problemscited by 87
  10. 2024Are Your LLMs Capable of Stable Reasoning?cited by 65
  11. 2024A Performance Study of LLM-Generated Code on Leetcodecited by 49
  12. 2023SelfEvolve: A Code Evolution Framework via Large Language Modelscited by 43
12 more
  1. 2024CodeIt: Self-Improving Language Models with Prioritized Hindsight Replaycited by 23
  2. 2025GPU Kernel Scientist: An LLM-Driven Framework for Iterative Kernel Optimizationcited by 22
  3. 2024On Evaluating the Efficiency of Source Code Generated by LLMscited by 21
  4. 2024Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generationcited by 21
  5. 2025Proving the Coding Interview: A Benchmark for Formally Verified Code Generationcited by 19
  6. 2022Piloting Copilot, Codex, and StarCoder2: Hot Temperature, Cold Prompts, or Black Magic?cited by 14
  7. 2023GPT-Fathom: Benchmarking Large Language Models to Decipher the Evolutionary Path towards GPT-4 and Beyondcited by 14
  8. 2023ChatCoder: Chat-based Refine Requirement Improves LLMs' Code Generationcited by 13
  9. 2025VeriMind: Agentic LLM for Automated Verilog Generation with a Novel Evaluation Metriccited by 12
  10. 2025Security Degradation in Iterative AI Code Generation -- A Systematic Analysis of the Paradoxcited by 10
  11. 2025Analyzing Prominent LLMs: An Empirical Study of Performance and Complexity in Solving LeetCode Problemscited by 4
  12. 2016Gradual Typing in an Open Worldcited by 1

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

Similar, not cited

Close in wording, no citation either way

  1. 2024Code Repair with LLMs gives an Exploration-Exploitation Tradeoff
  2. 2025Demystifying Errors in LLM Reasoning Traces: An Empirical Study of Code Execution Simulation
  3. 2025FeedbackEval: A Benchmark for Evaluating Large Language Models in Feedback-Driven Code Repair Tasks
  4. 2026CodeContests-O: Powering LLMs via Feedback-Driven Iterative Test Case Generation
  5. 2024Reasoning Runtime Behavior of a Program with LLM: How Far Are We?
  6. 2025Refining Critical Thinking in LLM Code Generation: A Faulty Premise-based Evaluation Framework
  7. 2024Planning-Driven Programming: A Large Language Model Programming Workflow
  8. 2024CodeMind: Evaluating Large Language Models for Code Reasoning