# REPOFUSE: Repository-Level Code Completion with Fused Dual Context

arXiv: https://arxiv.org/abs/2402.14323 · HTML: https://mlsanity.com/paper/2402.14323/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 22 Feb 2024.

## Builds on (most cited first, 18 of 18)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [InCoder: A Generative Model for Code Infilling and Synthesis](https://mlsanity.com/paper/2204.05999/) (2022)
- [UniXcoder: Unified Cross-Modal Pre-training for Code Representation](https://mlsanity.com/paper/2203.03850/) (2022)
- [CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X](https://mlsanity.com/paper/2303.17568/) (2023)
- [Efficient Training of Language Models to Fill in the Middle](https://mlsanity.com/paper/2207.14255/) (2022)
- [Grounded Copilot: How Programmers Interact with Code-Generating Models](https://mlsanity.com/paper/2206.15000/) (2022)
- [CodePlan: Repository-level Coding using LLMs and Planning](https://mlsanity.com/paper/2309.12499/) (2023)
- [CodeGen2: Lessons for Training LLMs on Programming and Natural Languages](https://mlsanity.com/paper/2305.02309/) (2023)
- [ReACC: A Retrieval-Augmented Code Completion Framework](https://mlsanity.com/paper/2203.07722/) (2022)
- [Repository-Level Prompt Generation for Large Language Models of Code](https://mlsanity.com/paper/2206.12839/) (2022)
- [CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context](https://mlsanity.com/paper/2212.10007/) (2022)
- [Big Code != Big Vocabulary: Open-Vocabulary Models for Source Code](https://mlsanity.com/paper/2003.07914/) (2020)
- [PanGu-Coder: Program Synthesis with Function-Level Language Modeling](https://mlsanity.com/paper/2207.11280/) (2022)
- [RepoFusion: Training Code Models to Understand Your Repository](https://mlsanity.com/paper/2306.10998/) (2023)
- [GrACE: Generation using Associated Code Edits](https://mlsanity.com/paper/2305.14129/) (2023)
- [Better Context Makes Better Code Language Models: A Case Study on Function Call Argument Completion](https://mlsanity.com/paper/2306.00381/) (2023)
- [Practitioners' Expectations on Code Completion](https://mlsanity.com/paper/2301.03846/) (2023)

## Built on by (most cited first, 30 of 32)

- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph](https://mlsanity.com/paper/2410.14684/) (2024)
- [Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks](https://mlsanity.com/paper/2505.16901/) (2025)
- [Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches](https://mlsanity.com/paper/2510.04905/) (2025)
- [What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond](https://mlsanity.com/paper/2503.20589/) (2025)
- [Improving Code Localization with Repository Memory](https://mlsanity.com/paper/2510.01003/) (2025)
- [In Line with Context: Repository-Level Code Generation via Context Inlining](https://mlsanity.com/paper/2601.00376/) (2026)
- [GraphCodeAgent: Dual Graph-Guided LLM Agent for Retrieval-Augmented Repo-Level Code Generation](https://mlsanity.com/paper/2504.10046/) (2025)
- [LLM/Agent-as-Data-Analyst: A Survey](https://mlsanity.com/paper/2509.23988/) (2025)
- [Hierarchical Context Pruning: Optimizing Real-World Code Completion with Repository-Level Pretrained Code LLMs](https://mlsanity.com/paper/2406.18294/) (2024)
- [CodeRAG: Finding Relevant and Necessary Knowledge for Retrieval-Augmented Repository-Level Code Completion](https://mlsanity.com/paper/2509.16112/) (2025)
- [Preference-Guided Refactored Tuning for Retrieval Augmented Code Generation](https://mlsanity.com/paper/2409.15895/) (2024)
- [Towards an Understanding of Context Utilization in Code Intelligence](https://mlsanity.com/paper/2504.08734/) (2025)
- [RANGER -- Repository-Level Agent for Graph-Enhanced Retrieval](https://mlsanity.com/paper/2509.25257/) (2025)
- [AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion](https://mlsanity.com/paper/2601.19697/) (2026)
- [Knowledge Augmented Complex Problem Solving with Large Language Models: A Survey](https://mlsanity.com/paper/2505.03418/) (2025)
- [A Deep Dive into Retrieval-Augmented Generation for Code Completion: Experience on WeChat](https://mlsanity.com/paper/2507.18515/) (2025)
- [Enhancing Project-Specific Code Completion by Inferring Internal API Information](https://mlsanity.com/paper/2507.20888/) (2025)
- [SPENCER: Self-Adaptive Model Distillation for Efficient Code Retrieval](https://mlsanity.com/paper/2508.00546/) (2025)
- [Impact-driven Context Filtering For Cross-file Code Completion](https://mlsanity.com/paper/2508.05970/) (2025)
- [RepoReasoner: Evaluating Repository-Level Code Reasoning Ability of Long-Context Language Models](https://mlsanity.com/paper/2607.25996/) (2026)
- [Repository Structure-Aware Training Makes SLMs Better Issue Resolver](https://mlsanity.com/paper/2412.19031/) (2024)
- [Repository-Level Graph Representation Learning for Enhanced Security Patch Detection](https://mlsanity.com/paper/2412.08068/) (2024)
- [SpecAgent: A Speculative Retrieval and Forecasting Agent for Code Completion](https://mlsanity.com/paper/2510.17925/) (2025)
- [DRAINCODE: Stealthy Energy Consumption Attacks on Retrieval-Augmented Code Generation via Context Poisoning](https://mlsanity.com/paper/2601.20615/) (2026)
- [FastCoder: Accelerating Repository-level Code Generation via Efficient Retrieval and Verification](https://mlsanity.com/paper/2502.17139/) (2025)
- [NES: An Instruction-Free, Low-Latency Next Edit Suggestion Framework Powered by Learned Historical Editing Trajectories](https://mlsanity.com/paper/2508.02473/) (2025)
- [TENET: One Step Toward Test-Driven Development for Repository-Level Code Generation](https://mlsanity.com/paper/2509.24148/) (2025)
- [MHRC-Bench: A Multilingual Hardware Repository-Level Code Completion benchmark](https://mlsanity.com/paper/2601.03708/) (2026)
- [A Lightweight Framework for Adaptive Retrieval In Code Completion With Critique Model](https://mlsanity.com/paper/2406.10263/) (2024)

## Abstract (arXiv)

The success of language models in code assistance has spurred the proposal of repository-level code completion as a means to enhance prediction accuracy, utilizing the context from the entire codebase. However, this amplified context can inadvertently increase inference latency, potentially undermining the developer experience and deterring tool adoption - a challenge we termed the Context-Latency Conundrum. This paper introduces REPOFUSE, a pioneering solution designed to enhance repository-level code completion without the latency trade-off. REPOFUSE uniquely fuses two types of context: the analogy context, rooted in code analogies, and the rationale context, which encompasses in-depth semantic relationships. We propose a novel rank truncated generation (RTG) technique that efficiently condenses these contexts into prompts with restricted size. This enables REPOFUSE to deliver precise code completions while maintaining inference efficiency. Through testing with the CrossCodeEval suite, REPOFUSE has demonstrated a significant leap over existing models, achieving a 40.90% to 59.75% increase in exact match (EM) accuracy for code completions and a 26.8% enhancement in inference speed. Beyond experimental validation, REPOFUSE has been integrated into the workflow of a large enterprise, where it actively supports various coding tasks.