# RAILS: Retrieval-Augmented Intelligence for Learning Software Development

arXiv: https://arxiv.org/abs/2506.22742 · HTML: https://mlsanity.com/paper/2506.22742/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RAG for code, one of 15 directions in Retrieval-augmented generation.
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 28 Jun 2025.

## Placed in

- Retrieval-augmented generation / [RAG for code](https://mlsanity.com/rag/rag-for-code/)

## Builds on (most cited first, 9 of 9)

- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [CodeSearchNet Challenge: Evaluating the State of Semantic Code Search](https://mlsanity.com/paper/1909.09436/) (2019)
- [DocPrompting: Generating Code by Retrieving the Docs](https://mlsanity.com/paper/2207.05987/) (2022)
- [LLM Inference Unveiled: Survey and Roofline Model Insights](https://mlsanity.com/paper/2402.16363/) (2024)
- [Retrieval-Augmented Reinforcement Learning](https://mlsanity.com/paper/2202.08417/) (2022)
- [Analyzing and Supporting Adaptation of Online Code Examples](https://mlsanity.com/paper/1905.12111/) (2019)
- [ZS4C: Zero-Shot Synthesis of Compilable Code for Incomplete Code Snippets using LLMs](https://mlsanity.com/paper/2401.14279/) (2024)

## Abstract (arXiv)

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.