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

• URL: http://arxiv.org/abs/2604.12913v1
• Date: Tue, 14 Apr 2026 15:58:38 GMT
• Title: CoDe-R: Refining Decompiler Output with LLMs via Rationale Guidance and Adaptive Inference
• Abstract summary: Binary decompilation is a critical reverse engineering task aimed at reconstructing high-level source code from stripped executables.<n>Large Language Models (LLMs) have recently shown promise, but they often suffer from "logical hallucinations" and "semantic misalignment"<n>We propose Cognitive Decompiler Refinement with Robustness (CoDe-R), a lightweight two-stage code refinement framework.
• Score: 10.71961188176124
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Decoupling is a Necessity: Transformation-Agnostic Decompiled Code Recovery under Optimization and Obfuscation [17.25489608715255]
  We present ReSource, the first multi-phase LLM framework for source recovery.<n>It conceptualizes the binary-to-source discrepancies into three tiers, namely lexical, syntactic, and semantic.<n>It achieves an 83% Top-5 source retrieval accuracy and an average similarity score of 0.66.
  arXiv  Detail & Related papers  (2026-08-28T03:52:54Z)
• UniCoder: Unified Visual-to-Code Generation via Symbolic Rewards and Reference-Guided Code Optimization [22.627858794105066]
  We introduce UniCoder, a unified RL framework that integrates two novel mechanisms.<n>First, we propose textbfSymbolic Attribute Alignment, which employs a lightweight auxiliary LLM to parse generated code into discrete visual attributes.<n>Second, to escape local optima, we devise textbfReference-Guided Code Optimization, a strategy that dynamically injects ground-truth trajectories into low-performing rollout groups.
  arXiv  Detail & Related papers  (2026-06-30T14:29:48Z)
• Binary Decompilation LLM with Feedback-Driven Multi-Turn Refinement [39.339662640253785]
  This paper presents AutoDecompiler, a decompilation-specialized LLM trained with reinforcement learning for feedback-driven multi-turn binary decompilation.<n>We design decompilation-specific rewards that capture code validity, recompilability, execution consistency, and semantic fidelity.<n>We train the AutoDecompiler family and evaluate it across different input settings, model scales, and benchmarks.
  arXiv  Detail & Related papers  (2026-06-15T03:25:05Z)
• Structured Semantic Cloaking for Jailbreak Attacks on Large Language Models [28.741175254258422]
  We propose Structured Semantic Cloaking (S2C), a novel multi-dimensional jailbreak attack framework.<n>S2C strategically distributes and reshapes semantic cues such that full intent consolidation requires multi-step inference.<n>We evaluate S2C across multiple open-source and proprietary LLMs using HarmBench and JBB-Behaviors.
  arXiv  Detail & Related papers  (2026-03-17T07:20:48Z)
• Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models [96.0074341403456]
  Inference-time compute has re-emerged as a practical way to improve LLM reasoning.<n>Most test-time scaling (TTS) algorithms rely on autoregressive decoding.<n>We propose Prism, an efficient TTS framework for dLLMs.
  arXiv  Detail & Related papers  (2026-02-02T09:14:51Z)
• Context-Guided Decompilation: A Step Towards Re-executability [50.71992919223209]
  Binary decompilation plays an important role in software security analysis, reverse engineering and malware understanding.<n>Recent advances in large language models (LLMs) have enabled neural decompilation, but the generated code is typically only semantically plausible.<n>We propose ICL4Decomp, a hybrid decompilation framework that leverages in-context learning (ICL) to guide LLMs toward generating re-executable source code.
  arXiv  Detail & Related papers  (2025-11-03T17:21:39Z)
• When Retriever Meets Generator: A Joint Model for Code Comment Generation [3.6781644685120924]
  RAGSum is built on top offuse retrieval and generation using a single CodeT5 backbone.<n>A contrastive pre-training phase shapes code embeddings for nearest-neighbor search.<n>A lightweight self-refinement loop is deployed to polish the final output.
  arXiv  Detail & Related papers  (2025-07-16T18:12:27Z)
• DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation [68.19756761027351]
  Diffusion large language models (dLLMs) are compelling alternatives to autoregressive (AR) models.<n>We investigate their denoising processes and reinforcement learning methods.<n>Our work provides deeper insight into the machinery of dLLM generation and offers an effective, diffusion-native RL training framework.
  arXiv  Detail & Related papers  (2025-06-25T17:35:47Z)
• ReF Decompile: Relabeling and Function Call Enhanced Decompile [50.86228893636785]
  The goal of decompilation is to convert compiled low-level code (e.g., assembly code) back into high-level programming languages.<n>This task supports various reverse engineering applications, such as vulnerability identification, malware analysis, and legacy software migration.
  arXiv  Detail & Related papers  (2025-02-17T12:38:57Z)
• Progressive Binarization with Semi-Structured Pruning for LLMs [36.91249209658632]
  We propose Progressive Binarization with Semi-Structured Pruning (PBS$2$P), a novel post-training framework that seamlessly integrates binarization and semi-structured pruning.<n>We show that PBS$2$P consistently outperforms state-of-the-art (SOTA) binary post-training quantization methods in both perplexity and downstream accuracy.
  arXiv  Detail & Related papers  (2025-02-03T13:30:29Z)
• Reward-Guided Speculative Decoding for Efficient LLM Reasoning [80.55186052123196]
  We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs)<n>RSD incorporates a controlled bias to prioritize high-reward outputs, in contrast to existing speculative decoding methods that enforce strict unbiasedness.<n>RSD delivers significant efficiency gains against decoding with the target model only, while achieving significant better accuracy than parallel decoding method on average.
  arXiv  Detail & Related papers  (2025-01-31T17:19:57Z)
• COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement [80.18490952057125]
  Iterative refinement has emerged as an effective paradigm for enhancing the capabilities of large language models (LLMs) on complex tasks. We propose Context-Wise Order-Agnostic Language Modeling (COrAL) to overcome these challenges. Our approach models multiple token dependencies within manageable context windows, enabling the model to perform iterative refinement internally.
  arXiv  Detail & Related papers  (2024-10-12T23:56:19Z)
• UniASM: Binary Code Similarity Detection without Fine-tuning [2.2329530239800035]
  We propose a novel rich-semantic function representation technique to ensure the model captures the intricate nuances of binary code.<n>We introduce the first UniLM-based binary code embedding model, named UniASM, which includes two newly designed training tasks.<n>The experimental results show that UniASM outperforms the state-of-the-art (SOTA) approaches on the evaluation datasets.
  arXiv  Detail & Related papers  (2022-10-28T14:04:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.