LLM Based Code Generation and Code Integration with Multi-Agent Systems Büyük Dil Modeli Tabanli Kod Üretimi ve Çoklu Ajan Sistemleri ile Kod Entegrasyonu
34th Signal Processing and Communications Applications Conference, SIU 2026, İstanbul, Türkiye, 7 - 10 Temmuz 2026, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Doi Numarası: 10.1109/siu71813.2026.11636409
- Basıldığı Şehir: İstanbul
- Basıldığı Ülke: Türkiye
- Anahtar Kelimeler: abstract syntax tree, code generation, code integration, large language model, multi-agent systems
- İstanbul Medipol Üniversitesi Adresli: Evet
Özet
Contemporary large language models can generate syntactically correct code from natural language specifications. However, integrating the generated code into existing software projects remains a largely manual, error-prone process that severely limits practical utility. This paper proposes a novel four-agent multi-agent system architecture to bridge the gap between code generation and code integration. The system comprises a Context Retrieval Agent, Code Generation Agent, Code Integration Agent, and Orchestration Agent. Evaluated through 270 experiments across three software projects of varying complexity, six language models, and three code generation styles, the AST-based integration architecture achieved a 100% success rate. Syntax validity averaged 69.2%, and the best model configuration reached a normalized score of 0.795.