FeatLens cuts code graph size to speed up repo level code generation
FeatLens: Feature-Guided Dynamic Code Graph Construction and Retrieval for Repository-Level Code Generation
Software EngineeringArtificial Intelligence
Summary
Generating new code inside a large software project requires understanding which existing code parts can be reused. The authors present FeatLens, a method that uses natural language descriptions of features to quickly find the most relevant code pieces and their connections. This avoids building huge, slow-to-handle graphs of the entire project and helps code generation models focus on a smaller set of important code units. Their experiments show that FeatLens improves the retrieval of needed code dependencies and reduces overhead compared to previous approaches.
What this means in practice
- •For software engineering teams: Improve automated function implementation in large codebases by efficiently retrieving relevant code dependencies, reducing generation time and resource use.
- •For software tool developers: Develop lightweight code generation tools that dynamically construct task-specific code graphs rather than maintaining large persistent graphs.
Authors
Xutian Li, Bo Xiong, Yifeng Zhu, Kunze Li, Xianlin Zhao, Runbang Yan, Yanzhen Zou, Lu Zhang, Bing Xie
Abstract
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 \textbf{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.