Metraipolis › archive › dc_a2da4afc1789
T-LLM Compiler: Trusted LLM-based Code Optimization and Verification Framework — arXiv:2608.14953
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.14953
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T17:08:15.309Z
- SHA-256 of the archived text
f12e35f509f0d0fbe1338d81090f966800a011b67d4000064e649ed89ea036f6- Stable URL of this page
https://metraipolis.com/documento/dc_a2da4afc1789
How to cite
T-LLM Compiler: Trusted LLM-based Code Optimization and Verification Framework — arXiv:2608.14953 — arXiv (en), https://arxiv.org/abs/2608.14953 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a2da4afc1789 (Metraipolis archive dc_a2da4afc1789, sha256 f12e35f509f0d0fbe1338d81090f966800a011b67d4000064e649ed89ea036f6)
BibTeX
@misc{dca2da4afc1789,
title = {T-LLM Compiler: Trusted LLM-based Code Optimization and Verification Framework — arXiv:2608.14953},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.14953},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a2da4afc1789; sha256 f12e35f509f0d0fbe1338d81090f966800a011b67d4000064e649ed89ea036f6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14953. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent advances in Large Language Models (LLMs) have opened opportunities to apply high-level code transformations to the field of code optimization, and it has since emerged as one of the most fundamental tasks for LLMs to perform; however, at present, LLMs struggle to apply wide-ranging code optimization tasks due to both the complexity of the code and the inability to independently verify the correctness of the transformations. In this paper, we present the Trusted LLM (T-LLM) Compiler, which proposes an advancement in compiler technology through a collaborative effort involving high-level LLM code transformations, traditional compilers, and verification tools. Experimental results reveal that it can significantly improve code correctness when tested on a set of PolyBench/C benchmarks. Our approach facilitates iterative code optimization efforts with verification strategies that enable corrective actions. Through this approach, T-LLM Compiler achieves code optimization accuracy of up to 83.3% and a speedup of up to 16.1\% on the PolyBench/C benchmarks, with the transformed code reaching an average of 26.7% speedup wrt standard baselines. Additionally, we release the project's source code to the open-source community. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Machine Learning (cs.LG); Performance (cs.PF); Programming Languages (cs.PL). Pagina del lavoro: https://arxiv.org/abs/2608.14953 — 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 2026-10-18T16:29:13.752Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).