# STALL+: Boosting LLM-based Repository-level Code Completion with Static Analysis

arXiv: https://arxiv.org/abs/2406.10018 · HTML: https://mlsanity.com/paper/2406.10018/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2024.

## Built on by (most cited first, 21 of 21)

- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models](https://mlsanity.com/paper/2409.16191/) (2024)
- [Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches](https://mlsanity.com/paper/2510.04905/) (2025)
- [An LLM Agent for Automatic Geospatial Data Analysis](https://mlsanity.com/paper/2410.18792/) (2024)
- [In Line with Context: Repository-Level Code Generation via Context Inlining](https://mlsanity.com/paper/2601.00376/) (2026)
- [Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models](https://mlsanity.com/paper/2407.00456/) (2024)
- [An Empirical Study of Agent Developer Practices in AI Agent Frameworks](https://mlsanity.com/paper/2512.01939/) (2025)
- [Towards an Understanding of Context Utilization in Code Intelligence](https://mlsanity.com/paper/2504.08734/) (2025)
- [Statically Contextualizing Large Language Models with Typed Holes](https://mlsanity.com/paper/2409.00921/) (2024)
- [AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion](https://mlsanity.com/paper/2601.19697/) (2026)
- [Combining Large Language Models with Static Analyzers for Code Review Generation](https://mlsanity.com/paper/2502.06633/) (2025)
- [A Deep Dive into Retrieval-Augmented Generation for Code Completion: Experience on WeChat](https://mlsanity.com/paper/2507.18515/) (2025)
- [EffiReasonTrans: RL-Optimized Reasoning for Code Translation](https://mlsanity.com/paper/2510.18863/) (2025)
- [Exploring the Challenges and Opportunities of AI-assisted Codebase Generation](https://mlsanity.com/paper/2508.07966/) (2025)
- [AppForge: From Assistant to Independent Developer -- Are GPTs Ready for Software Development?](https://mlsanity.com/paper/2510.07740/) (2025)
- [Timing Analysis Agent: Autonomous Multi-Corner Multi-Mode (MCMM) Timing Debugging with Timing Debug Relation Graph](https://mlsanity.com/paper/2504.11502/) (2025)
- [CodeSSM: Towards State Space Models for Code Understanding](https://mlsanity.com/paper/2505.01475/) (2025)
- [ShortCoder: Knowledge-Augmented Syntax Optimization for Token-Efficient Code Generation](https://mlsanity.com/paper/2601.09703/) (2026)
- [Towards Iterative End-to-End Software Development: A Feature-Driven Multi-Agent Framework](https://mlsanity.com/paper/2511.02399/) (2025)
- [How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring](https://mlsanity.com/paper/2606.26979/) (2026)
- [Structure-Aware Corpus Construction and User-Perception-Aligned Metrics for Large-Language-Model Code Completion](https://mlsanity.com/paper/2505.13073/) (2025)

## Abstract (arXiv)

Repository-level code completion is challenging as it involves complicated contexts from multiple files in the repository. To date, researchers have proposed two technical categories to enhance LLM-based repository-level code completion, i.e., retrieval-augmented generation (RAG) and static analysis integration. This work performs the first study on the static analysis integration in LLM-based repository-level code completion by investigating both the effectiveness and efficiency of static analysis integration strategies across different phases of code completion. We first implement a framework STALL+, which supports an extendable and customizable integration of multiple static analysis strategies into the complete pipeline of LLM-based repository-level code completion; and based on STALL+, we perform extensive experiments by including different code LLMs on the latest repository-level code completion benchmark CrossCodeEval. Our findings show that integrating file-level dependencies in prompting phase performs the best while the integration in post-processing phase performs the worse. Additionally, we observe different improvements from static analysis between dynamic languages and static languages, i.e., the best combination is prompting-phase with decoding-phase integration for Java while the best combination is prompting-phase with post-processing-phase integration for Python given the limitations of statically analyzing dynamic languages. Additionally, we find the complementarity between RAG and static analysis integration as well as their cost-effectiveness after combination.