{"ID":2862468,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.25716","arxiv_id":"2509.25716","title":"DeepCodeSeek: Real-Time API Retrieval for Context-Aware Code Generation","abstract":"Current search techniques are limited to standard RAG query-document applications. In this paper, we propose a novel technique to expand the code and index for predicting the required APIs, directly enabling high-quality, end-to-end code generation for auto-completion and agentic AI applications. We address the problem of API leaks in current code-to-code benchmark datasets by introducing a new dataset built from real-world ServiceNow Script Includes that capture the challenge of unclear API usage intent in the code. Our evaluation metrics show that this method achieves 87.86% top-40 retrieval accuracy, allowing the critical context with APIs needed for successful downstream code generation. To enable real-time predictions, we develop a comprehensive post-training pipeline that optimizes a compact 0.6B reranker through synthetic dataset generation, supervised fine-tuning, and reinforcement learning. This approach enables our compact reranker to outperform a much larger 8B model while maintaining 2.5x reduced latency, effectively addressing the nuances of enterprise-specific code without the computational overhead of larger models.","short_abstract":"Current search techniques are limited to standard RAG query-document applications. In this paper, we propose a novel technique to expand the code and index for predicting the required APIs, directly enabling high-quality, end-to-end code generation for auto-completion and agentic AI applications. We address the problem...","url_abs":"https://arxiv.org/abs/2509.25716","url_pdf":"https://arxiv.org/pdf/2509.25716v1","authors":"[\"Esakkivel Esakkiraja\",\"Denis Akhiyarov\",\"Aditya Shanmugham\",\"Chitra Ganapathy\"]","published":"2025-09-30T03:23:27Z","proceeding":"cs.SE","tasks":"[\"cs.SE\",\"cs.AI\",\"cs.IR\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}