Architecture-Aware Multi-Design Generation for Repository-Level Feature Addition

TL;DR

RAIM is an architecture-aware, multi-design framework for repository-level feature addition that improves success rates by accurately pinpointing modification targets and generating diverse implementation options, reducing regressions.

Contribution

This paper introduces RAIM, a novel multi-design, architecture-aware framework that enhances feature addition in large codebases by multi-round exploration and impact-aware selection, surpassing existing methods.

Findings

Achieves a 39.47% success rate on NoCode-bench dataset.

Outperforms baseline systems with a 36.34% relative improvement.

Demonstrates robustness across various foundation models.

Abstract

Implementing new features across an entire codebase presents a formidable challenge for Large Language Models (LLMs). This proactive task requires a deep understanding of the global system architecture to prevent unintended disruptions to legacy functionalities. Conventional pipeline and agentic frameworks often fall short in this area because they suffer from architectural blindness and rely on greedy single-path code generation. To overcome these limitations, we propose RAIM, a multi-design and architecture-aware framework for repository-level feature addition. This framework introduces a localization mechanism that conducts multi-round explorations over a repository-scale code graph to accurately pinpoint dispersed cross-file modification targets. Crucially, RAIM shifts away from linear patching by generating multiple diverse implementation designs. The system then employs a rigorous impact-aware selection process based on static and dynamic analysis to choose the most architecturally sound patch and avoid system regressions. Comprehensive experiments on the NoCode-bench Verified dataset demonstrate that RAIM establishes a new state-of-the-art performance with a 39.47% success rate, achieving a 36.34% relative improvement over the strongest baseline. Furthermore, the approach exhibits robust generalization across various foundation models and empowers open-weight models like DeepSeek-v3.2 to surpass baseline systems powered by leading proprietary models. Detailed ablation studies confirm that the multi-design generation and impact validation modules are critical to effectively managing complex dependencies and reducing code errors. These findings highlight the vital role of structural awareness in automated software evolution.