研究人员正在探索新的方法来提高大型语言模型（LLM）生成代码的可靠性和效率。一项研究侧重于迭代反馈循环，利用编译器错误消息和测试用例结果来帮助LLM改进其代码，其中推理模型比非推理模型显示出显著的改进。另一篇论文介绍了一个名为SwiftTrans的框架，旨在提高LLM翻译代码的功能正确性和运行时效率，解决了LLM生成的程序可能比人类编写的程序慢的问题。第三种方法通过选择性地生成代码并使用自动生成的单元测试来评估和控制正确性来解决代码幻觉问题。
AI
arXiv:2606.20373v1 Announce Type: cross Abstract: Large Language Models (LLMs) show promise for code compilation tasks, but applying them to runtime performance tuning is difficult due to complex microarchitectural effects and noisy runtime measurements. We present AutoPass, a mu…
Large Language Models (LLMs) show promise for code compilation tasks, but applying them to runtime performance tuning is difficult due to complex microarchitectural effects and noisy runtime measurements. We present AutoPass, a multi-agent framework for compiler performance tunin…
arXiv:2606.17683v1 Announce Type: new Abstract: While large language models (LLMs) have greatly advanced the functional correctness of automated code translation systems, the runtime efficiency of translated programs has received comparatively little attention. With the waning of…
arXiv:2606.17514v1 Announce Type: cross Abstract: Large Language Models have shown remarkable capabilities in code generation. However, most existing evaluations focus only on single-attempt accuracy and overlook the iterative refinement process that is central to real-world prog…
While large language models (LLMs) have greatly advanced the functional correctness of automated code translation systems, the runtime efficiency of translated programs has received comparatively little attention. With the waning of Moore's law, runtime efficiency has become incr…
arXiv cs.LG
TIER_1English(EN)·Jaewoo Jeong, Taesoo Kim, Sangdon Park·
arXiv:2505.13553v3 Announce Type: replace-cross Abstract: The hallucination of code generation models hinders their applicability to systems requiring higher safety standards. One critical bottleneck in addressing code hallucination is the difficulty of identifying the functional…
Research addresses code generation challenges for no-resource programming languages by developing benchmarks and proposing a method that combines further pre-training with weight difference transfer to create specialized instruction-following models at reduced computational cost.
