Tootfinder

Bridging Developer Instructions and Code Completion Through Instruction-Aware Fill-in-the-Middle Paradigm
Zhensu Sun, Chengran Yang, Chao Peng, Pengfei Gao, Xiaoning Du, Li Li, David Lo
https://arxiv.org/abs/2509.24637

Bridging Developer Instructions and Code Completion Through Instruction-Aware Fill-in-the-Middle Paradigm
Large Language Models (LLMs) have significantly advanced code completion, yet they often fail when the developer's intent is underspecified in the code context. To address this, developers usually add natural language instructions (e.g., comments) into the code context to clarify their intent. However, existing code LLMs applied for code completion systems merely undergo a fill-in-the-middle (FIM) pre-training, which struggles to leverage this information effectively due to the lack of instruct…