Xiaoao Zhu, Ni Zhang, Jie Ren, Zhiqiang Li, Jie Zheng, Zhanyong Tang, Zheng Wang · 2026 · arXiv
DOI: 10.48550/arXiv.2610.30877 · open-access PDF
Mengangkat binari yang terlepas, sangat dioptimalkan ke kanonik, pre-optimization LLVM intermediate representation (IR) sangat penting untuk analisis keamanan downstream dan migrasi perangkat lunak warisan ketika kode sumber tidak tersedia. Namun, optimisasi kompilator agresif menulis ulang kontrol dan aliran data, menghapus metadata struktural, dan memperkenalkan idiom tingkat rendah yang dihapus tipe, menyebabkan lifters saat ini menghasilkan IR yang tidak berbentuk atau berbeda secara semantik. Kami menyajikan ATLAS, kerangka kerja multi-agen yang dirancang untuk merekonstruksi secara resmi valid dan kanonik LLVM IR dari disassembly yang dioptimalkan.
Machine translation (Meta M2M100); the English original follows.
Lifting stripped, heavily optimized binaries to a canonical, pre-optimization LLVM intermediate representation (IR) is essential for downstream security analysis and legacy software migration when source code is unavailable. However, aggressive compiler optimizations rewrite control and data flow, remove structural metadata, and introduce type-erased low-level idioms, causing current lifters to produce malformed or semantically divergent IR. We present ATLAS, a multi-agent framework designed to reconstruct formally valid and canonical LLVM IR from optimized disassembly.ATLAS combines (i) Struc
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.30877, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange