# HELIOS: Hierarchical Graph Abstraction for Structure-Aware LLM Decompilation

arXiv: https://arxiv.org/abs/2601.14598 · HTML: https://mlsanity.com/paper/2601.14598/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 39 references that are in the map.
- First posted on arXiv 21 Jan 2026.

## Builds on (most cited first, 15 of 15)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [GPT4Graph: Can Large Language Models Understand Graph Structured Data ? An Empirical Evaluation and Benchmarking](https://mlsanity.com/paper/2305.15066/) (2023)
- [Talk like a Graph: Encoding Graphs for Large Language Models](https://mlsanity.com/paper/2310.04560/) (2023)
- [GraphText: Graph Reasoning in Text Space](https://mlsanity.com/paper/2310.01089/) (2023)
- [Neural Network-based Graph Embedding for Cross-Platform Binary Code Similarity Detection](https://mlsanity.com/paper/1708.06525/) (2017)
- [LLM4Decompile: Decompiling Binary Code with Large Language Models](https://mlsanity.com/paper/2403.05286/) (2024)
- [Trex: Learning Execution Semantics from Micro-Traces for Binary Similarity](https://mlsanity.com/paper/2012.08680/) (2020)
- [SLaDe: A Portable Small Language Model Decompiler for Optimized Assembly](https://mlsanity.com/paper/2305.12520/) (2023)
- [Refining Decompiled C Code with Large Language Models](https://mlsanity.com/paper/2310.06530/) (2023)
- [An Observational Investigation of Reverse Engineers' Processes](https://mlsanity.com/paper/1912.00317/) (2019)
- [Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learning](https://mlsanity.com/paper/2311.13721/) (2023)
- [CFG2VEC: Hierarchical Graph Neural Network for Cross-Architectural Software Reverse Engineering](https://mlsanity.com/paper/2301.02723/) (2023)
- [Self-Constructed Context Decompilation with Fined-grained Alignment Enhancement](https://mlsanity.com/paper/2406.17233/) (2024)
- [ReF Decompile: Relabeling and Function Call Enhanced Decompile](https://mlsanity.com/paper/2502.12221/) (2025)
- [AGNOMIN -- Architecture Agnostic Multi-Label Function Name Prediction](https://mlsanity.com/paper/2509.25514/) (2025)

## Built on by (most cited first, 3 of 3)

- [Evaluating Neural Decompilation of Dart AOT Binaries: Fine-Tuning, Metric Validity, Specification Leakage, and Reliability](https://mlsanity.com/paper/2607.06125/) (2026)
- [Structure for Reading, Prose for Writing: Asymmetric Structural Conditioning in Multi-Agent Document Authoring](https://mlsanity.com/paper/2608.20786/) (2026)
- [Echo: Learning-based Matching Decompilation using Trusted Back Translation](https://mlsanity.com/paper/2609.18706/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have recently been applied to binary decompilation, yet they still treat code as plain text and ignore the graphs that govern program control flow. This limitation often yields syntactically fragile and logically inconsistent output, especially for optimized binaries. This paper presents textscHELIOS, a framework that reframes LLM-based decompilation as a structured reasoning task. textscHELIOS summarizes a binary's control flow and function calls into a hierarchical text representation that spells out basic blocks, their successors, and high-level patterns such as loops and conditionals. This representation is supplied to a general-purpose LLM, along with raw decompiler output, optionally combined with a compiler-in-the-loop that returns error messages when the generated code fails to build. On HumanEval-Decompile for textttx8664, textscHELIOS raises average object file compilability from 45.0% to 85.2% for Gemini~2.0 and from 71.4% to 89.6% for GPT-4.1~Mini. With compiler feedback, compilability exceeds 94% and functional correctness improves by up to 5.6 percentage points over text-only prompting. Across six architectures drawn from x86, ARM, and MIPS, textscHELIOS reduces the spread in functional correctness while keeping syntactic correctness consistently high, all without fine-tuning. These properties make textscHELIOS a practical building block for reverse engineering workflows in security settings where analysts need recompilable, semantically faithful code across diverse hardware targets.