RAILS: Retrieval-Augmented Intelligence for Learning Software Development
This addresses software developers' need for more accurate code assistance, though it is incremental as it builds on existing retrieval-augmented methods.
The paper tackles the problem of LLMs producing incomplete code or incorrect imports in software development by introducing RAILS, a framework that augments LLM prompts with retrieved context and uses compiler feedback for validation, resulting in outperforming baseline prompting on 78 real-world Java import error cases.
Large Language Models (LLMs) like GPT-3.5-Turbo are increasingly used to assist software development, yet they often produce incomplete code or incorrect imports, especially when lacking access to external or project-specific documentation. We introduce RAILS (Retrieval-Augmented Intelligence for Learning Software Development), a framework that augments LLM prompts with semantically retrieved context from curated Java resources using FAISS and OpenAI embeddings. RAILS incorporates an iterative validation loop guided by compiler feedback to refine suggestions. We evaluated RAILS on 78 real-world Java import error cases spanning standard libraries, GUI APIs, external tools, and custom utilities. Despite using the same LLM, RAILS outperforms baseline prompting by preserving intent, avoiding hallucinations, and surfacing correct imports even when libraries are unavailable locally. Future work will integrate symbolic filtering via PostgreSQL and extend support to other languages and IDEs.