works

• 

  How Generation Architecture Shapes Code Complexity in Multi-Agent LLM Systems: A Paired Study on HumanEval

  Nazmus Ashrafi

  Preprint, 2026

  arXivCode

  Python·LangChain·LangGraph·radon·SciPy·statsmodels·OpenAI API

  • Summary: How Generation Architecture Shapes Code Complexity in Multi-Agent LLM Systems
• 

  LEOPARD: A Structured LLM Orchestration Framework for Precision-Centric Grammatical Error Correction

  N. Ashrafi, M. Mediani, S. Bouktif

  IEEE Intl. Conf. on Frontiers of Engineering and Emerging Technologies (FET), Bahrain, 2026

  DOIPDFCodeVideo

  Python·LangChain·LangGraph·spaCy·OpenAI API

  • LEOPARD: A Multi-Agent LLM Framework for Precision-Centric Grammatical Error Correction
• 

  Enhancing LLM Code Generation: Multi-Agent Collaboration and Runtime Debugging

  N. Ashrafi, S. Bouktif, M. Mediani

  IEEE Intl. Conf. on AI and Communication Technologies (AICT), 2025

  DOIarXivCode

  Python·LangChain·LangGraph·OpenAI API·Anthropic API·Hugging Face·Google Vertex·SciPy·Pandas

  • Enhancing LLM Code Generation: Multi-Agent Collaboration and Runtime Debugging