Context-Aware Code Wiring Recommendation with LLM-based Agent

2025-07-01

AI Summary

In software development, developers frequently reuse external code snippets but must manually perform “code wiring”—i.e., resolving unresolved variables in pasted code by substituting them with contextually appropriate local variables. Existing approaches rely heavily on heuristic rules or historical templates, failing to adequately model contextual dependencies; empirical analysis shows over 50% of wiring scenarios require explicit context awareness. This paper introduces WIRL, a retrieval-augmented intelligent agent powered by large language models (LLMs), which formalizes code wiring as a context-aware RAG-based fill-in-the-blank task. WIRL innovatively integrates a state-machine-driven hybrid decision mechanism—combining rule-guided inference with LLM-driven exploration—to achieve precise, context-sensitive variable mapping. Evaluated on a real-world dataset, WIRL achieves 91.7% precision and 90.0% recall, outperforming state-of-the-art LLMs and IntelliJ IDEA by +22.6 and +54.3 percentage points, respectively, significantly advancing automation of context-sensitive code reuse.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Planning, Routing, and Scheduling: Planning with Language Models
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Copy-paste-modify is a widespread and pragmatic practice in software development, where developers adapt reused code snippets, sourced from platforms such as Stack Overflow, GitHub, or LLM outputs, into their local codebase. A critical yet underexplored aspect of this adaptation is code wiring, which involves substituting unresolved variables in the pasted code with suitable ones from the surrounding context. Existing solutions either rely on heuristic rules or historical templates, often failing to effectively utilize contextual information, despite studies showing that over half of adaptation cases are context-dependent. In this paper, we introduce WIRL, an LLM-based agent for code wiring framed as a Retrieval-Augmented Generation (RAG) infilling task. WIRL combines an LLM, a customized toolkit, and an orchestration module to identify unresolved variables, retrieve context, and perform context-aware substitutions. To balance efficiency and autonomy, the agent adopts a mixed strategy: deterministic rule-based steps for common patterns, and a state-machine-guided decision process for intelligent exploration. We evaluate WIRL on a carefully curated, high-quality dataset consisting of real-world code adaptation scenarios. Our approach achieves an exact match precision of 91.7% and a recall of 90.0%, outperforming advanced LLMs by 22.6 and 13.7 percentage points in precision and recall, respectively, and surpassing IntelliJ IDEA by 54.3 and 49.9 percentage points. These results underscore its practical utility, particularly in contexts with complex variable dependencies or multiple unresolved variables. We believe WIRL paves the way for more intelligent and context-aware developer assistance in modern IDEs.

Problem

• Automating context-aware code variable substitution
• Improving accuracy in reused code adaptation
• Enhancing IDE support for complex dependencies

Innovation

• LLM-based agent for code wiring
• Retrieval-Augmented Generation infilling task
• Mixed strategy for efficiency and autonomy