SEApr 14

Learning Project-wise Subsequent Code Edits via Interleaving Neural-based Induction and Tool-based Deduction

arXiv:2604.1222063.51 citationsh-index: 8Has Code
Predicted impact top 33% in SE · last 90 daysOriginality Incremental advance
AI Analysis

For developers and AI-assisted coding tools, TRACE addresses the trade-off between editing scope, accuracy, and efficiency in real-world software engineering tasks.

TRACE improves project-wise code editing by interleaving neural-based induction for semantic edits and tool-based deduction for syntactic edits, achieving higher accuracy and efficiency than existing methods like Cursor and CoEdPilot.

In industrial and open-source software engineering tasks, developers often perform project-wise code editing tasks, including feature enhancement, refactoring, and bug fixing, where the leading AI models are expected to support the productivity. Hence, researchers and practitioners have proposed and adopted many LLM-based solutions to facilitate their real-world development. However, they largely suffer from the balance among predicting scope, accuracy, and efficiency. For example, solutions like Cursor achieve high accuracy only in a local editing scope while its performance drops on cross-file edits. In contrast, solutions like CoEdPilot exhibit efficiency limitations when used to predict project-wise edits. In this work, we propose TRACE (Tool-integrated RecommendAtion for Code Editing), a novel subsequent code editing solution to push the boundary of scope, accuracy, and efficiency. Our rationale lies in that code edits are triggered for either semantic or syntactic reasons. Therefore, TRACE predicts subsequent edits by interleaving neural-based induction for semantic edit prediction and tool-based deduction for syntactic edit prediction. The tools can be any IDE facilities, such as refactoring tools (e.g., rename) or linting tools (e.g., use-def), providing decent performance of deducing edit-location and edit-generation. Technically, we address the challenge of (1) when to interleave between neural-based and tool-based prediction and (2) how to further improve the performance of neural-based prediction. As for the former, we learn a neural model to detect when to invoke IDE editing tools. As for the latter, we propose a novel and fine-grained editing representation to further boost the performance of neural editing models. ......

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes