---
title: "BUSTA: Teaching Small Language Models to Reason About Binary Execution"
url: https://awesomerea.org/papers/paper-busta/
updated: 2026-11-10
type: paper
---

# BUSTA: Teaching Small Language Models to Reason About Binary Execution

> BUSTA trains small language models to infer input register values from an x86-64 basic block and desired output register state. It evaluates knowable-register prediction accuracy against base and frontier models.

- Authors: Ritika Poddar; Aidan Fennelly; Deirdre Murphy; Eric Wolos; Corre L. Steele; Michael Doyle
- Venue: arXiv
- Status: Preprint
- Publication / posting date: October 26, 2026
- Date source: First arXiv submission date.
- First arXiv submission: October 26, 2026
- arXiv: 2610.36288
- Read in a terminal: `hf papers read 2610.36288`
- Reviewed arXiv version: v1
- Sources reviewed: 2026-11-09
- Added to the catalog: 2026-11-10
- Original paper: <https://arxiv.org/abs/2610.36288>
- PDF: <https://arxiv.org/pdf/2610.36288>
- BibTeX: <https://awesomerea.org/papers/citations/paper-busta.bib>
- Catalog page: <https://awesomerea.org/papers/paper-busta/>
- Record JSON: <https://awesomerea.org/papers/paper-busta/record.json>
- Chinese version: [简体中文](https://awesomerea.org/zh/papers/paper-busta/index.md)

## Scope and limitations

The evaluation focuses on inverse execution of x86-64 basic blocks and register values.

## Why it fits this collection

Inferring the inputs that produce a binary block’s output is reasoning about existing binary code behavior.

## Publication and review notes

The date and venue come from the arXiv record.

## BibTeX

```bibtex
@misc{paper-busta,
  title = {{BUSTA: Teaching Small Language Models to Reason About Binary Execution}},
  author = {{Ritika Poddar} and {Aidan Fennelly} and {Deirdre Murphy} and {Eric Wolos} and {Corre L. Steele} and {Michael Doyle}},
  year = {2026},
  url = {https://arxiv.org/abs/2610.36288},
  howpublished = {arXiv:2610.36288},
  note = {Preprint},
  eprint = {2610.36288},
  archivePrefix = {arXiv},
  month = oct
}
```

## Primary sources

1. <https://arxiv.org/abs/2610.36288>

## 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.
