{"ID":2846471,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.01183","arxiv_id":"2511.01183","title":"QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code","abstract":"Compilers, while essential, are notoriously complex systems that demand prohibitively expensive human expertise to develop and maintain. The recent advancements in Large Language Models (LLMs) offer a compelling new paradigm: Neural Compilation, which could potentially simplify compiler development for new architectures and facilitate the discovery of innovative optimization techniques. However, several critical obstacles impede its practical adoption. Firstly, a significant lack of dedicated benchmarks and robust evaluation methodologies hinders objective assessment and tracking of progress in the field. Secondly, systematically enhancing the reliability and performance of LLM-generated assembly remains a critical challenge. Addressing these challenges, this paper introduces NeuComBack, a novel benchmark dataset specifically designed for IR-to-assembly compilation. Leveraging this dataset, we first define a foundational Neural Compilation workflow and conduct a comprehensive evaluation of the capabilities of recent frontier LLMs on Neural Compilation, establishing new performance baselines. We further propose a self-evolving prompt optimization method that enables LLMs to iteratively evolve their internal prompt strategies by extracting insights from prior self-debugging traces, thereby enhancing their neural compilation capabilities. Experiments demonstrate that our method significantly improves both the functional correctness and the performance of LLM-generated assembly code. Compared to baseline prompts, the functional correctness rates improved from 44% to 64% on x86_64 and from 36% to 58% on aarch64, respectively. More significantly, among the 16 correctly generated x86_64 programs using our method, 14 (87.5%) surpassed clang-O3 performance.","short_abstract":"Compilers, while essential, are notoriously complex systems that demand prohibitively expensive human expertise to develop and maintain. The recent advancements in Large Language Models (LLMs) offer a compelling new paradigm: Neural Compilation, which could potentially simplify compiler development for new architecture...","url_abs":"https://arxiv.org/abs/2511.01183","url_pdf":"https://arxiv.org/pdf/2511.01183v1","authors":"[\"Hainan Fang\",\"Yuanbo Wen\",\"Jun Bi\",\"Yihan Wang\",\"Tonghui He\",\"Yanlin Tang\",\"Di Huang\",\"Jiaming Guo\",\"Rui Zhang\",\"Qi Guo\",\"Yunji Chen\"]","published":"2025-11-03T03:20:26Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.PL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}