CoRoVA: Compressed Representations for Vector-Augmented Code Completion

arXiv:2510.19644v2 Announce Type: replace Abstract: Retrieval-augmented generation has emerged as one of the most effective approaches for code completion enhancement, especially when repository-level context is important. However, adding this extra retrieved context significantly increases sequence length, raises prefill cost, and degrades time-to-first-token (TTFT), which slows down inference -- a critical limitation for interactive settings such as IDEs. In this work, we introduce CoRoVA, a framework that compresses context into compact, semantically rich representations that remain interpretable to code LLMs. This improves generation quality while reducing prompt augmentation to only a few compressed single-token vectors. Our approach requires training only a small projector module and introduces negligible additional latency, yet it significantly improves the prediction quality of code LLMs. Our experiments show that CoRoVA enables a 20-38% reduction in TTFT on completion tasks compared to uncompressed RAG.

Related

• Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation
• Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation
• Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS
• Rag Performance Prediction for Question Answering
• Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrieval

Source: arXiv cs.CL | 2026-04-15