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

arXiv: https://arxiv.org/abs/2604.12913 · HTML: https://mlsanity.com/paper/2604.12913/

## Key facts

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

## Builds on (most cited first, 21 of 21)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [Textbooks Are All You Need](https://mlsanity.com/paper/2306.11644/) (2023)
- [CodeT: Code Generation with Generated Tests](https://mlsanity.com/paper/2207.10397/) (2022)
- [Landmark Attention: Random-Access Infinite Context Length for Transformers](https://mlsanity.com/paper/2305.16300/) (2023)
- [Refining Decompiled C Code with Large Language Models](https://mlsanity.com/paper/2310.06530/) (2023)
- [Investigating Mysteries of CoT-Augmented Distillation](https://mlsanity.com/paper/2406.14511/) (2024)
- [Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learning](https://mlsanity.com/paper/2311.13721/) (2023)
- [SK2Decompile: LLM-based Two-Phase Binary Decompilation from Skeleton to Skin](https://mlsanity.com/paper/2509.22114/) (2025)
- [D-LiFT: Improving LLM-based Decompiler Backend via Code Quality-driven Fine-tuning](https://mlsanity.com/paper/2506.10125/) (2025)
- [ALT4Decompile: Inferring C-aligned Abstract Loop Tree for LLM-Based Binary Decompilation](https://mlsanity.com/paper/2509.14646/) (2025)
- [ReF Decompile: Relabeling and Function Call Enhanced Decompile](https://mlsanity.com/paper/2502.12221/) (2025)
- [The CodeInverter Suite: Structure- and Data-Aware Binary Decompilation with Efficient LLMs](https://mlsanity.com/paper/2503.07215/) (2025)

## Built on by (most cited first, 1 of 1)

- [SoK: AI-Augmented Binary Reversing](https://mlsanity.com/paper/2606.17398/) (2026)

## 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.