Retrieval-Augmented Code Generation

Latest papers

14 papers1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

FeatLens: Feature-Guided Dynamic Code Graph Construction and Retrieval for Repository-Level Code Generation
Sep 22, 2026Xutian Li, Bo Xiong, Yifeng Zhu +6Graph Retrieval-Augmented Generation Repository-Level Code Generation
Peking University
CodePoisonRAG: Knowledge Poisoning Attacks on Retrieval-Augmented Code Generation
Sep 2, 2026Varun Gadey, Ziad Marey, Alexandra DmitrienkoRetrieval-Augmented Code Generation Data Poisoning Attacks
University of Duisburg-Essen, Germany
Beyond "What to Retrieve": Uncertainty in Retrieval-Augmented Code Generation
Jul 27, 2026Chandan Kumar Sah, Li Zhang, Xiaoli LianRetrieval-Augmented Generation LLM Uncertainty Estimation
Beihang University, Beijing, China
Tool-Guided Retrieval-Augmented Repair for Securing LLM-Generated C Code
Jul 21, 2026Vidyut Sriram, Saatvik Pradhan, Suman SahaAutomated Program Repair Code Generation
The Pennsylvania State University
Understanding Agent-Based Patching of Compiler Missed Optimizations
Jul 2, 2026Batu Guan, Zirui Wang, Shaohua LiCode Generation AI Coding Agents
The Chinese University of Hong Kong · Hong Kong SAR
PennySynth: RAG-Driven Data Synthesis for Automated Quantum Code Generation
May 25, 2026Minghao Shao, Nouhaila Innan, Hariharan Janardhanan +3Code Generation LLM-Based Program Synthesis
1eBRAIN Lab, Division of Engineering, New York University Abu Dhabi (NYUAD), Abu Dhabi, UAE · Center for Quantum and Topological Systems (CQTS), NYUAD Research Institute, NYUAD, Abu Dhabi, UAE · Department of Computer Science and Engineering, NYU Tandon School of Engineering, New York, USA
Improving BM25 Code Retrieval Under Fixed Generic Tokenization: Adaptive q-Log Odds as a Drop-In BM25 Fix
May 18, 2026Santosh Kumar Radha, Oktay GoktasInformation Retrieval Retrieval-Augmented Code Generation
AgentField
When Retrieval Hurts Code Completion: A Diagnostic Study of Stale Repository Context
May 14, 2026Haojun Weng, Qianqian Yang, Hao Fu +2Retrieval-Augmented Generation Retrieval Robustness
Independent Researcher, California, USA · Independent Researcher, Beijing, China
BlenderRAG: High-Fidelity 3D Object Generation via Retrieval-Augmented Code Synthesis
May 1, 2026Massimo Rondelli, Francesco Pivi, Maurizio GabbrielliRetrieval-Augmented Generation 3D Asset Generation
University of Bologna, Bologna, Italy · Ferrari S.p.A., Maranello, Italy
Context-Augmented Code Generation: How Product Context Improves AI Coding Agent Decision Compliance by 49%
Apr 27, 2026Drew Dillon, Kasyap VaranasiRetrieval-Augmented Generation AI Coding Agents
Brief
On Accelerating Grounded Code Development for Research
Apr 21, 2026Santosh GanjiCoding Agents Code Generation
AstraAI: LLMs, Retrieval, and AST-Guided Assistance for HPC Codebases
Mar 28, 2026Mahesh Natarajan, Xiaoye Li, Weiqun ZhangRetrieval-Augmented Code Generation Code Generation
Applied Mathematics and Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA
BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?
Mar 3, 2026Guoxin Chen, Fanzhe Meng, Jiale Zhao +12Retrieval-Augmented Code Generation Software Engineering Benchmarks
VeriGRAG: Enhancing LLM-Based Verilog Code Generation with Structure-Aware Soft Prompts
Sep 27, 2025Jiayu Zhao, Zehua Pei, Zetao Guo +2RTL Code Generation LLM Code Generation
University of Science and Technology of China

Sep 22, 2026J/K move · Enter open · S save

FeatLens: Feature-Guided Dynamic Code Graph Construction and Retrieval for Repository-Level Code Generation

Xutian Li, Bo Xiong, Yifeng Zhu, Kunze Li+5

Peking University

Graph Retrieval-Augmented Generation Repository-Level Code Generation LLM Code Generation Retrieval-Augmented Code Generation

Open paper AskPDF arXiv

Recent code generation research has moved from isolated function completion toward repository-level generation in existing codebases. To implement a target function correctly, an LLM must identify reusable repository dependencies such as existing functions, APIs, and cross-file definitions. Existing retrieval methods provide such context through code similarity search, persistent whole-repository graphs, or LLM-driven graph exploration, but often incur high graph construction, reasoning, and token costs. Feature-oriented methods offer a natural view of software functionality, yet they mainly support requirement decomposition, planning, or feature editing rather than code dependency retrieval. This paper presents FeatLens, a feature-guided dynamic code graph construction and retrieval approach for repository-level code generation. FeatLens builds a feature index that links natural-language feature descriptions to function-level code entities. Given a generation task, it dynamically constructs a task-specific seed graph from the feature index and applies semantic-structural graph reasoning with personalized PageRank to select a compact reasoning graph. This design replaces persistent whole-repository graph maintenance and LLM exploration with deterministic and lightweight dependency retrieval. Experiments on DevEval and EvoCodeBench show that FeatLens achieves the best DR@15 among sparse, dense, and graph-based baselines (0.501 and 0.460). On DevEval generation, it obtains the highest DIR@1, reaching 52.91% with DeepSeek-V3.2 and 53.58% with GPT-5-mini, while maintaining competitive Pass@1 and producing shorter code. Compared with the strongest graph-based baseline, FeatLens reduces graph nodes by 61.0%, edges by 86.2%, and total token overhead by 45.9%, with no LLM tokens used during retrieval.