AgenticTyper: Automated Typing of Legacy Software Projects Using Agentic AI
Clemens Pohle
TL;DR
AgenticTyper leverages an LLM-based agentic system to automate the addition of types in legacy JavaScript projects, significantly reducing manual effort and improving maintenance safety.
Contribution
This work introduces AgenticTyper, a novel LLM-driven system that automates type addition, error correction, and behavioral verification at scale for legacy JavaScript codebases.
Findings
Resolved all initial type errors in 20 minutes
Reduced manual effort from one day to 20 minutes
Effective at repository scale with 81K LOC
Abstract
Legacy JavaScript systems lack type safety, making maintenance risky. While TypeScript can help, manually adding types is expensive. Previous automated typing research focuses on type inference but rarely addresses type checking setup, definition generation, bug identification, or behavioral correctness at repository scale. We present AgenticTyper, a Large Language Model (LLM)-based agentic system that addresses these gaps through iterative error correction and behavior preservation via transpilation comparison. Evaluation on two proprietary repositories (81K LOC) shows that AgenticTyper resolves all 633 initial type errors in 20 minutes, reducing manual effort from one working day.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSoftware Engineering Research · Software Testing and Debugging Techniques · Scientific Computing and Data Management