Advancements in AI-Powered Code Completion and Modification

The field of AI-powered code completion and modification is moving towards more interactive and adaptive approaches. Researchers are exploring ways to improve the quality of code completion by optimizing context collection, developing more effective retrieval strategies, and creating interactive natural language representations of code. The use of large language models and pseudocode is also being investigated to give developers greater control over LLM-assisted code writing. Noteworthy papers include Code4MeV2, which introduces a research-oriented, open-source code completion plugin, and NaturalEdit, which presents a system for code modification through direct interaction with adaptive natural language representation. Smart Paste is also notable for its deployment and positive feedback at Google's enterprise scale.

Sources

Code4MeV2: a Research-oriented Code-completion Platform

Smart Paste: Automatically Fixing Copy/Paste for Google Developers

Challenge on Optimization of Context Collection for Code Completion

NaturalEdit: Code Modification through Direct Interaction with Adaptive Natural Language Representation

Code Semantic Zooming

Beyond More Context: How Granularity and Order Drive Code Completion Quality

Built with on top of