Next Edit Prediction: Learning to Predict Code Edits from Context and Interaction History

2025-08-13

AI Summary

Existing AI coding assistants exhibit a functional dichotomy: code completion models support only low-latency, cursor-local predictions, while chat-based editing requires manual intent specification and induces disruptive context switching. Neither paradigm actively models developers’ sequential editing behavior. Method: We introduce the novel task of “next-edit prediction,” which jointly forecasts both the location and content of the upcoming code modification. We propose the first interaction-history-aware editing sequence modeling framework, release a high-quality fine-tuning dataset and a dedicated evaluation benchmark, and employ large language models fine-tuned under supervision that jointly encodes code context and user interaction history. Contribution/Results: Experiments demonstrate substantial improvements in predicting continuous editing actions. Our approach advances programming assistants from passive response toward proactive collaboration, establishing a new paradigm for intelligent, behavior-aware programming assistance.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational 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: Large Language Models (LLM) for user modeling and recommendation

Abstract

The rapid advancement of large language models (LLMs) has led to the widespread adoption of AI-powered coding assistants integrated into a development environment. On one hand, low-latency code completion offers completion suggestions but is fundamentally constrained to the cursor's current position. On the other hand, chat-based editing can perform complex modifications, yet forces developers to stop their work, describe the intent in natural language, which causes a context-switch away from the code. This creates a suboptimal user experience, as neither paradigm proactively predicts the developer's next edit in a sequence of related edits. To bridge this gap and provide the seamless code edit suggestion, we introduce the task of Next Edit Prediction, a novel task designed to infer developer intent from recent interaction history to predict both the location and content of the subsequent edit. Specifically, we curate a high-quality supervised fine-tuning dataset and an evaluation benchmark for the Next Edit Prediction task. Then, we conduct supervised fine-tuning on a series of models and performed a comprehensive evaluation of both the fine-tuned models and other baseline models, yielding several novel findings. This work lays the foundation for a new interaction paradigm that proactively collaborate with developers by anticipating their following action, rather than merely reacting to explicit instructions.

Problem

• Predicts next code edit from context and history
• Bridges gap between low-latency and chat-based editing
• Infers developer intent for seamless edit suggestions

Innovation

• Predicts next code edit using interaction history
• Uses supervised fine-tuning for model training
• Proactively anticipates developer edits location and content