Signals 4 · free daily AI digest

When LLM Decompilers Recompile More and Preserve Less

Paper recorded by Signals 4 on 2026-09-04 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-04 on arXiv · recorded by Signals 4 on 2026-09-07

Category: cs.AI · 人工智能 · first seen 2026-09-07

Abstract

Decompilation recovers high-level source from compiled machine code and serves as a foundation for security tasks such as vulnerability detection and malware analysis. Traditional decompilers like Ghidra and Hex-Rays expose whatever they cannot resolve as visible placeholders and often emit pseudocode that will not compile or execute; LLM-based decompilers produce clean, idiomatic C and are now ju

Read on arXiv →

#170 most recent of 300 cs.AI papers we have recorded · ↑ newer: CUA-Universe: A Scalable and Dynamic Environment for Hybrid GUI+CLI Ag · ↓ older: Design Docs Are All You Need: An AI-native Machine-Learning Performanc
Cite this page: When LLM Decompilers Recompile More and Preserve Less: the #170 most recent of 300 cs.AI papers we have recorded (as of 2026-09-04). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/when-llm-decompilers-recompile-more-and-preserve-less.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.AI papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions