mlsanityData to 7 Oct 2026

SpareCodeSearch: Searching for Code Context When You Have No Spare GPU

arXiv 2510.12948 ↗First posted 14 Oct 2025cs.SE cs.AIcited by 0

On the map: Retrieval-augmented generation → RAG for code

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) frameworks aim to enhance Code Language Models (CLMs) by including another module for retrieving relevant context to construct the input prompt. However, these retrieval modules commonly use semantic search, requiring substantial computational resources for training and hosting these embedded models, making them infeasible to integrate into lightweight applications such as in-IDE AI-based code completion. In this solution paper, we prove that using keyword-search is sufficient to retrieve relevant and useful code context inside large codebases, without the need for extensive GPU resources. The usefulness of code contexts found by our solution is demonstrated through their completion results on the Code Context Competition's benchmark, reaching 0.748 and 0.725 chRF scores on Kotlin and Python tracks, respectively.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in RAG for code, one of 15 directions in Retrieval-augmented generation. Builds on 3 of its 13 references that are in the map. First posted on arXiv 14 Oct 2025.

Builds on

3 of 13 references.

References · 3

  1. 2022On the Transferability of Pre-trained Language Models for Low-Resource Programming Languagescited by 30
  2. 2023The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generationcited by 20
  3. 2025Fixing 7,400 Bugs for 1: Cheap Crash-Site Program Repaircited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Retrieval-augmented code completion for local projects using large language models
  2. 2024Context-Augmented Code Generation Using Programming Knowledge Graphs
  3. 2024CodeRAG-Bench: Can Retrieval Augment Code Generation?
  4. 2024Prompt-based Code Completion via Multi-Retrieval Augmented Generation
  5. 2025What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond
  6. 2025A Deep Dive into Retrieval-Augmented Generation for Code Completion: Experience on WeChat
  7. 2025An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunities
  8. 2024Repoformer: Selective Retrieval for Repository-Level Code Completion