# REx86: A Local Large Language Model for Assisting in x86 Assembly Reverse Engineering

> The paper fine-tunes eight local models from CodeLlama, Qwen2.5-Coder, and CodeGemma on 5,981 x86 assembly examples and evaluates their help with binary reverse engineering.

- Authors: Darrin Lea; James Ghawaly; Golden Richard; Aisha Ali-Gombe; Andrew Case
- Venue: 2025 IEEE Annual Computer Security Applications Conference (ACSAC)
- Status: Conference paper
- Publication / posting date: December 8, 2025
- Date source: Published date in the Crossref record for the DOI listed on arXiv.
- First arXiv submission: October 23, 2025
- arXiv: 2510.20975
- Reviewed arXiv version: v1
- DOI: 10.1109/acsac67867.2025.00024
- Sources reviewed: 2026-11-06
- Added to the catalog: 2026-11-06
- Original paper: <https://doi.org/10.1109/ACSAC67867.2025.00024>
- PDF: <https://arxiv.org/pdf/2510.20975>
- Code: <https://github.com/dlea8/REx86>
- BibTeX: <https://awesomerea.org/papers/citations/paper-rex86.bib>
- Catalog page: <https://awesomerea.org/papers/paper-rex86/>
- Record JSON: <https://awesomerea.org/papers/paper-rex86/record.json>
- Chinese version: [简体中文](https://awesomerea.org/zh/papers/paper-rex86/index.md)

## Scope and limitations

Evaluation covers a curated x86 assembly dataset and a 43-person user case study of line-level understanding and problem solving.

## Why it fits this collection

It studies local language-model assistance for understanding and commenting on x86 disassembly used in binary reverse engineering.

## Publication and review notes

The DOI comes from the arXiv record, and the venue and date from Crossref.

## Primary sources

1. <https://arxiv.org/abs/2510.20975>
2. <https://api.crossref.org/works/10.1109/ACSAC67867.2025.00024>

## About this entry

Reviewed against the paper and its primary sources. Cite the original authors using the linked paper or BibTeX.
Original editorial content: MIT. Linked projects, papers and assets retain their own rights and licenses.