Cover Image

What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gu, Wenchao, Chen, Juntao, Wang, Yanlin, Jiang, Tianyue, Li, Xingzhe, Liu, Mingwei, Liu, Xilin, Ma, Yuchi, Zheng, Zibin
Format:	Preprint
Published:	2025
Subjects:	Software Engineering
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DRAINCODE: Stealthy Energy Consumption Attacks on Retrieval-Augmented Code Generation via Context Poisoning
by: Wang, Yanlin, et al.
Published: (2026)

Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models
by: Wang, Yanlin, et al.
Published: (2024)

AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion
by: Jiang, Tianyue, et al.
Published: (2026)

EffiReasonTrans: RL-Optimized Reasoning for Code Translation
by: Wang, Yanlin, et al.
Published: (2025)

Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark
by: Zheng, Dewu, et al.
Published: (2024)

A Preliminary Study on the Robustness of Code Generation by Large Language Models
by: Li, Zike, et al.
Published: (2025)

An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunities
by: Yang, Zezhou, et al.
Published: (2025)

An Empirical Study of Agent Developer Practices in AI Agent Frameworks
by: Wang, Yanlin, et al.
Published: (2025)

HumanEvo: An Evolution-aware Benchmark for More Realistic Evaluation of Repository-level Code Generation
by: Zheng, Dewu, et al.
Published: (2024)

RustRepoTrans: Repository-level Code Translation Benchmark Targeting Rust
by: Ou, Guangsheng, et al.
Published: (2024)

A Hierarchical and Evolvable Benchmark for Fine-Grained Code Instruction Following with Multi-Turn Feedback
by: Duan, Guoliang, et al.
Published: (2025)

Improving Retrieval-Augmented Code Comment Generation by Retrieving for Generation
by: Lu, Hanzhen, et al.
Published: (2024)

KTester: Leveraging Domain and Testing Knowledge for More Effective LLM-based Test Generation
by: Li, Anji, et al.
Published: (2025)

Architecture-Aware Multi-Design Generation for Repository-Level Feature Addition
by: Liu, Mingwei, et al.
Published: (2026)

RLCoder: Reinforcement Learning for Repository-Level Code Completion
by: Wang, Yanlin, et al.
Published: (2024)

OmniGIRL: A Multilingual and Multimodal Benchmark for GitHub Issue Resolution
by: Guo, Lianghong, et al.
Published: (2025)

ShortCoder: Knowledge-Augmented Syntax Optimization for Token-Efficient Code Generation
by: Liu, Sicong, et al.
Published: (2026)

SPENCER: Self-Adaptive Model Distillation for Efficient Code Retrieval
by: Gu, Wenchao, et al.
Published: (2025)

When to Stop? Towards Efficient Code Generation in LLMs with Excess Token Prevention
by: Guo, Lianghong, et al.
Published: (2024)

Dynamic analysis enhances issue resolution
by: Liu, Mingwei, et al.
Published: (2026)

SECRET: Towards Scalable and Efficient Code Retrieval via Segmented Deep Hashing
by: Gu, Wenchao, et al.
Published: (2024)

An Empirical Study on Low-Code Programming using Traditional vs Large Language Model Support
by: Liu, Yongkun, et al.
Published: (2024)

Are Decoder-Only Large Language Models the Silver Bullet for Code Search?
by: Chen, Yuxuan, et al.
Published: (2024)

SimpleDevQA: Benchmarking Large Language Models on Development Knowledge QA
by: Zhang, Jing, et al.
Published: (2025)

RustEvo^2: An Evolving Benchmark for API Evolution in LLM-based Rust Code Generation
by: Liang, Linxi, et al.
Published: (2025)

RealSec-bench: A Benchmark for Evaluating Secure Code Generation in Real-World Repositories
by: Wang, Yanlin, et al.
Published: (2026)

Evolving Triple Knowledge-Augmented LLMs for Code Translation in Repository Context
by: Ou, Guangsheng, et al.
Published: (2025)

LAURA: Enhancing Code Review Generation with Context-Enriched Retrieval-Augmented LLM
by: Zhang, Yuxin, et al.
Published: (2025)

Knowledge-Graph-Driven Data Synthesis for Low-Resource Software Development: A HarmonyOS Case Study
by: Liu, Mingwei, et al.
Published: (2025)

Towards an Understanding of Context Utilization in Code Intelligence
by: Wang, Yanlin, et al.
Published: (2025)

When More Retrieval Hurts: Retrieval-Augmented Code Review Generation
by: Meng, Qianru, et al.
Published: (2025)

RepoTransBench: A Real-World Multilingual Benchmark for Repository-Level Code Translation
by: Wang, Yanli, et al.
Published: (2024)

How Does Chunking Affect Retrieval-Augmented Code Completion? A Controlled Empirical Study
by: Wu, Xinjian, et al.
Published: (2026)

An Empirical Study of ChatGPT-Related Projects and Their Issues on GitHub
by: Lin, Zheng, et al.
Published: (2024)

Retrieval-Augmented Code Review Comment Generation
by: Hong, Hyunsun, et al.
Published: (2025)

Build-Aware Incremental C-to-Rust Migration via Skeleton-First Translation and Historical Knowledge Reuse
by: Wang, Shengbo, et al.
Published: (2026)

AnomalyGen: Enhancing Log-Based Anomaly Detection with Code-Guided Data Augmentation
by: Li, Xinyu, et al.
Published: (2026)

AdaDec: A Uncertainty-Guided Lookahead Decoding Framework for LLM-Based Code Generation
by: He, Kaifeng, et al.
Published: (2025)

Comment Traps: How Defective Commented-out Code Augment Defects in AI-Assisted Code Generation
by: Huang, Yuan, et al.
Published: (2025)

Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code
by: He, Kaifeng, et al.
Published: (2026)