mlsanityData to 7 Oct 2026

CoDe-R: Refining Decompiler Output with LLMs via Rationale Guidance and Adaptive Inference

arXiv 2604.12913 ↗First posted 14 Apr 2026cs.SE cs.AI cs.CRcited by 1

Not on the map. Why?

Abstract (arXiv)

Binary decompilation is a critical reverse engineering task aimed at reconstructing high-level source code from stripped executables. Although Large Language Models (LLMs) have recently shown promise, they often suffer from "logical hallucinations" and "semantic misalignment" due to the irreversible semantic loss during compilation, resulting in generated code that fails to re-execute. In this study, we propose Cognitive Decompiler Refinement with Robustness (CoDe-R), a lightweight two-stage code refinement framework. The first stage introduces Semantic Cognitive Enhancement (SCE), a Rationale-Guided Semantic Injection strategy that trains the model to recover high-level algorithmic intent alongside code. The second stage introduces a Dynamic Dual-Path Fallback (DDPF) mechanism during inference, which adaptively balances semantic recovery and syntactic stability via a hybrid verification strategy. Evaluation on the HumanEval-Decompile benchmark demonstrates that CoDe-R (using a 1.3B backbone) establishes a new State-of-the-Art (SOTA) in the lightweight regime. Notably, it is the first 1.3B model to exceed an Average Re-executability Rate of 50.00%, significantly outperforming the baseline and effectively bridging the gap between efficient models and expert-level performance. Our code is available at https://github.com/Theaoi/CoDe-R.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 21 of its 35 references that are in the map. First posted on arXiv 14 Apr 2026.

Builds on

21 of 35 references.

References · 21

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2025Qwen3 Technical Reportcited by 8,195
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  5. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  6. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  7. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,928
  8. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
  9. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 871
  10. 2023Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizescited by 710
  11. 2023Textbooks Are All You Needcited by 561
  12. 2022CodeT: Code Generation with Generated Testscited by 369
9 more
  1. 2023Landmark Attention: Random-Access Infinite Context Length for Transformerscited by 206
  2. 2023Refining Decompiled C Code with Large Language Modelscited by 24
  3. 2024Investigating Mysteries of CoT-Augmented Distillationcited by 15
  4. 2023Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learningcited by 12
  5. 2025SK2Decompile: LLM-based Two-Phase Binary Decompilation from Skeleton to Skincited by 7
  6. 2025D-LiFT: Improving LLM-based Decompiler Backend via Code Quality-driven Fine-tuningcited by 5
  7. 2025ALT4Decompile: Inferring C-aligned Abstract Loop Tree for LLM-Based Binary Decompilationcited by 4
  8. 2025ReF Decompile: Relabeling and Function Call Enhanced Decompilecited by 3
  9. 2025The CodeInverter Suite: Structure- and Data-Aware Binary Decompilation with Efficient LLMscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026SoK: AI-Augmented Binary Reversingcited by 0