Metraipolis › archive › dc_9f6ea73e01a4

STILL: Recovering Lowered STL Semantics for LLM-assisted C++ Decompilation — arXiv:2608.26408

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.26408
License (as archived)
CC0-1.0
Archived
2026-10-17T16:16:07.191Z
SHA-256 of the archived text
44e2584f312e606a0b36fc1e08b8daf2897a8bf0e5622767065e2bde6b5df3fc
Stable URL of this page
https://metraipolis.com/documento/dc_9f6ea73e01a4

How to cite

STILL: Recovering Lowered STL Semantics for LLM-assisted C++ Decompilation — arXiv:2608.26408 — arXiv (en), https://arxiv.org/abs/2608.26408 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9f6ea73e01a4 (Metraipolis archive dc_9f6ea73e01a4, sha256 44e2584f312e606a0b36fc1e08b8daf2897a8bf0e5622767065e2bde6b5df3fc)
BibTeX
@misc{dc9f6ea73e01a4,
  title = {STILL: Recovering Lowered STL Semantics for LLM-assisted C++ Decompilation — arXiv:2608.26408},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26408},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9f6ea73e01a4; sha256 44e2584f312e606a0b36fc1e08b8daf2897a8bf0e5622767065e2bde6b5df3fc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26408. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM-assisted decompilation improves readability and re-executability, but still underperforms on stripped C++ functions that use the Standard Template Library (STL). Compilation, optimization, and symbol stripping remove or obscure source-level semantics such as container types and library-call structure, while traditional decompiler output often fails to recover them. We present STILL, a structured semantic interface that predicts function-level STL container semantics from stripped control-flow graphs and renders them as compact hints for LLM refinement. On StlBench, STILL predicts common container-level STL semantics, with the strongest cross-dataset results for stable string and vector slices. On stripped HumanEval decompilation, these hints enable DeepSeek-chat refinement to reach 28.4% executability, compared with 17.4% for no-hint refinement and 8.9% for raw Ghidra decompilation; hint utility is downstream-backbone-dependent, with decompilation-specialized models requiring lightweight adaptation to benefit from the same interface.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-28 in cs.SE).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2608.26408 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T15:36:41.155Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).