2026· International Workshop on Computer Modeling and Intelligent Systems· pp. 212-226· 0 citations· 34 references
Computer Science
TL;DR
The experimental results demonstrate that the LoRA expert achieves a 35% average speedup in code generation while simultaneously improving correctness from 84% to 96%, surpassing the base model by 12 percentage points.
LACE is presented, an LLM-aided multi-agent workflow that translates natural-language ISAX intents into a compact two-level IR, performs retrieval-guided localized RTL edits over large repositories, and closes the loop with a compiler-agnostic riscv-formal checking flow.
Pingqing Zheng, Jiayin Qin, Fuqi Zhang et al.· 0 citations
Natural-language requirements for program synthesis are often incomplete or ambiguous, yet large language models are commonly expected to generate code in a single pass. Prior clarification-based methods address this issue by asking follow-up questions when sampled candidate programs disagree, but fixed clarify-on-disa...
Muhammad Ahmed, Edwar Tiu, Niyati Nikunj Kapadia et al.· Annual International Compute...· 0 citations
Experimental results show that MRCoder improves code generation accuracy over strong baselines while reducing token consumption by 30 to 50% and inference time by up to 52%.
Peiding Wang, Li Zhang, Fang Liu· arXiv.org· 0 citations
The results indicate that functional correctness in code generation can be meaningfully improved without modifying the backbone architecture, by jointly optimizing how tasks are prompted, how the model is adapted, and how final outputs are selected.
The results show that metainfer organizes generation constraints, validation feedback, and knowledge consolidation into a continuous closed loop, enabling runnable customized inference solutions to be generated from explicit knowledge.
Zhenwen Miao, Honglin Wang, Mingheng Mi et al.· arXiv.org· 0 citations
Large Language Models (LLMs) are now widely used for code generation, yet even syntactically correct output may contain logical and semantic errors that remain invisible until runtime, particularly in framework-driven applications, where correctness depends on dependency injection, framework conventions, configuration,...
Muhammed Suphi Şeyhkuruş, Tolga Ovatman· Annual International Compute...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
