Reusing code snippets from online programming Q&A communities has become a common development practice, in which developers often need to adapt code snippets to their code contexts to satisfy their own programming needs. However, how developers make these code adaptations based on contexts is still unclear. To bridge this gap, we first conduct a semi-structured interview of 21 developers to investigate their adaptation practices and perceived challenges during this process. The result suggests that code snippet adaptation is a challenging and exhausting task for developers, as they should tailor the snippets to guarantee their correctness and quality with laborious work. We also note that developers all resort to their intra-file context to complete adaptations, which motivates us to further study how developers performed context-based adaptations (CAs) in real scenarios. To this end, we conduct a quantitative study on an adaptation dataset comprising 300 code snippet reuse cases with 1,384 adaptations from Stack Overflow to GitHub. For each adaptation, we manually annotate its intention and relationship with the context. Based on our annotated data, we employ frequent itemset mining to obtain four CA patterns from our dataset, including Fortification , Code Wiring , Attribute-ization and Parameterization . Our main findings reveal that: (1) more than half of the code snippet reuse cases include CAs and 23.3% of the adaptations are CAs; (2) more than half of the CAs are corrective adaptations and variable is the primary adapted language construct; (3) attribute is the most frequently utilized context and 88% of the local contexts are within the nearest 10 LOCs; and (4) CAs towards different intentions are repetitive, which are useful for automatic adaptation. Overall, our study provides valuable insights into code snippet adaptation and has important implications for research, practice, and tool design.

Robot software development can be considered as a component-driven process, and existing ROS components, such as an ROS node, can be reused to construct robot applications. By reusing the ROS node, the development process of robot software can be significantly accelerated. However, the challenges in reusing ROS nodes primarily lie in the scattered organization of ROS node information. To address this challenge, this paper proposes a method to construct an ROS node knowledge graph (RNKG) based on high-quality open-source robot projects. In order to build a high-quality knowledge graph of ROS nodes, we first constructed a high-quality dataset of open-source robot projects. Since ROS node knowledge can exist in both text and code formats, we initially separated the data in the dataset into code data and text data, and then applied different knowledge extraction methods to extract corresponding entities. Finally, we integrated a series of ROS node knowledge and organized it into a knowledge graph. To validate the effectiveness of the constructed ROS node knowledge graph, we first verified the completeness of the entities and the accuracy of relationships in the knowledge graph. Next, we evaluated the performance of the ROS node knowledge graph in assisting developers with the downstream task of finding ROS nodes. These findings suggest that our proposed method for constructing an ROS node knowledge graph is feasible and demonstrate that the ROS node knowledge graph helps search ROS nodes.

Code snippet adaptation is a fundamental activity in the software development process. Unlike code generation, code snippet adaptation is not a "free creation", which requires developers to tailor a given code snippet in order to fit specific requirements and the code context. Recently, large language models (LLMs) have confirmed their effectiveness in the code generation task with promising results. However, their performance on adaptation, a reuse-oriented and context-dependent code change prediction task, is still unclear. To bridge this gap, we conduct an empirical study to investigate the performance and issues of LLMs on the adaptation task. We first evaluate the adaptation performances of three popular LLMs and compare them to the code generation task. Our result indicates that their adaptation ability is weaker than generation, with a nearly 15% decrease on pass@1 and more context-related errors. By manually inspecting 200 cases, we further investigate the causes of LLMs' sub-optimal performance, which can be classified into three categories, i.e., Unclear Requirement, Requirement Misalignment and Context Misapplication. Based on the above empirical research, we propose an interactive prompting approach to eliciting LLMs' adaptation ability. Experimental result reveals that our approach greatly improve LLMs' adaptation performance. The best-performing Human-LLM interaction successfully solves 159 out of the 202 identified defects and improves the pass@1 and pass@5 by over 40% compared to the initial instruction-based prompt. Considering human efforts, we suggest multi-agent interaction as a trade-off, which can achieve comparable performance with excellent generalization ability. We deem that our approach could provide methodological assistance for autonomous code snippet reuse and adaptation with LLMs.

Code adaptation is a fundamental but challenging task in software development, requiring developers to modify existing code for new contexts. A key challenge is to resolve Context Adaptation Bugs (CtxBugs), which occurs when code correct in its original context violates constraints in the target environment. Unlike isolated bugs, CtxBugs cannot be resolved through local fixes and require cross-context reasoning to identify semantic mismatches. Overlooking them may lead to critical failures in adaptation. Although Large Language Models (LLMs) show great potential in automating code-related tasks, their ability to resolve CtxBugs remains a significant and unexplored obstacle to their practical use in code adaptation. To bridge this gap, we propose CtxBugGen, a novel framework for generating CtxBugs to evaluate LLMs. Its core idea is to leverage LLMs' tendency to generate plausible but context-free code when contextual constraints are absent. The framework generates CtxBugs through a four-step process to ensure their relevance and validity: (1) Adaptation Task Selection, (2) Task-specific Perturbation,(3) LLM-based Variant Generation and (4) CtxBugs Identification. Based on the benchmark constructed by CtxBugGen, we conduct an empirical study with four state-of-the-art LLMs. Our results reveal their unsatisfactory performance in CtxBug resolution. The best performing LLM, Kimi-K2, achieves 55.93% on Pass@1 and resolves just 52.47% of CtxBugs. The presence of CtxBugs degrades LLMs' adaptation performance by up to 30%. Failure analysis indicates that LLMs often overlook CtxBugs and replicate them in their outputs. Our study highlights a critical weakness in LLMs' cross-context reasoning and emphasize the need for new methods to enhance their context awareness for reliable code adaptation.

Code adaptation is a fundamental but challenging task in software development, requiring developers to modify existing code for new contexts. A key challenge is to resolve Context Adaptation Bugs (CtxBugs) , which occurs when code correct in its original context violates constraints in the target environment. Unlike isolated bugs, CtxBugs cannot be resolved through local fixes and require cross-context reasoning to identify semantic mismatches. Overlooking them may lead to critical failures in adaptation. Although Large Language Models (LLMs) show great potential in automating code-related tasks, their ability to resolve CtxBugs remains a significant and unexplored obstacle to their practical use in code adaptation. To bridge this gap, we propose CtxBugGen , a novel framework for generating CtxBugs to evaluate LLMs. Its core idea is to leverage LLMs’ tendency to generate plausible but context-free code when contextual constraints are absent. The framework generates CtxBugs through a four-step process to ensure their relevance and validity: (1) Selection of four established context-aware adaptation tasks from the literature, (2) Perturbation via task-specific rules to induce CtxBugs from LLMs while ensuring their plausibility, (3) Generation of candidate variants by prompting LLMs without any context constraints and (4) Identification of valid CtxBugs through syntactic differencing and test execution in the target context. Based on the benchmark constructed by CtxBugGen , we conduct an empirical study with four state-of-the-art LLMs. Our results reveal their unsatisfactory performance in CtxBug resolution. The best performing LLM, Kimi-K2, achieves 55.93% on Pass@1 and resolves just 52.47% of CtxBugs . The presence of CtxBugs degrades LLMs’ adaptation performance by up to 30%. Failure analysis indicates that LLMs often overlook CtxBugs and replicate them in their outputs. This suggests that LLMs overly focus on the local code correctness of the reused code while ignoring its compatibility in the target context. Our study highlights a critical weakness in LLMs’ cross-context reasoning and emphasize the need for new methods to enhance their context awareness for reliable code adaptation. The replication package for this paper is at https://github.com/ztwater/CtxBugGen.