# When Retrieval Hurts Code Completion: A Diagnostic Study of Stale Repository Context

arXiv: https://arxiv.org/abs/2605.14478 · HTML: https://mlsanity.com/paper/2605.14478/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RAG for code, one of 15 directions in Retrieval-augmented generation.
- Builds on 14 of its 16 references that are in the map.
- First posted on arXiv 14 May 2026.

## Placed in

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

## Builds on (most cited first, 14 of 14)

- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems](https://mlsanity.com/paper/2306.03091/) (2023)
- [CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion](https://mlsanity.com/paper/2310.11248/) (2023)
- [CodePlan: Repository-level Coding using LLMs and Planning](https://mlsanity.com/paper/2309.12499/) (2023)
- [We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs](https://mlsanity.com/paper/2406.10279/) (2024)
- [CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based Verification](https://mlsanity.com/paper/2405.00253/) (2024)
- [SWE-Bench++: A Framework for the Scalable Generation of Software Engineering Benchmarks from Open-Source Repositories](https://mlsanity.com/paper/2512.17419/) (2025)
- [EVOR: Evolving Retrieval for Code Generation](https://mlsanity.com/paper/2402.12317/) (2024)
- [CodeRAG: Finding Relevant and Necessary Knowledge for Retrieval-Augmented Repository-Level Code Completion](https://mlsanity.com/paper/2509.16112/) (2025)
- [RustEvo^2: An Evolving Benchmark for API Evolution in LLM-based Rust Code Generation](https://mlsanity.com/paper/2503.16922/) (2025)
- [Towards Mitigating API Hallucination in Code Generated by LLMs with Hierarchical Dependency Aware](https://mlsanity.com/paper/2505.05057/) (2025)
- [Impact-driven Context Filtering For Cross-file Code Completion](https://mlsanity.com/paper/2508.05970/) (2025)
- [Identifying and Mitigating API Misuse in Large Language Models](https://mlsanity.com/paper/2503.22821/) (2025)
- [When LLMs Lag Behind: Knowledge Conflicts from Evolving APIs in Code Generation](https://mlsanity.com/paper/2604.09515/) (2026)

## Built on by (most cited first, 1 of 1)

- [Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model](https://mlsanity.com/paper/2608.13867/) (2026)

## Abstract (arXiv)

Context: Retrieval-augmented code generation relies on cross-file repository context, but retrieved snippets may come from obsolete project states. Objectives: We study whether temporally stale repository snippets act as harmless noise or actively induce current-state-incompatible code. Methods: We conduct a controlled diagnostic study on a curated 17-sample set of production-helper signature changes from five Python repositories. For each sample, we compare current-only, stale-only, no-retrieval, and mixed current/stale retrieval conditions under prompts that hide commit freshness and expected current signatures. Results: Under neutralized prompts, stale-only retrieval induces stale helper references on 15/17 Qwen2.5-Coder-7B-Instruct samples and 13/17 gpt-4.1-mini samples, corresponding to 88.2 and 76.5 percentage-point increases over current-only retrieval. No retrieval produces zero stale references but only 1/17 passing completions. The two models share 75.0% Jaccard overlap among stale-triggering samples, and mixed conditions show that adding valid current evidence largely rescues stale-only failures. Conclusion: Temporal validity of retrieved repository context is a distinct diagnostic variable for Code RAG robustness: stale context can actively bias models toward obsolete repository state rather than merely removing useful evidence.