Meng Shuai

API Recommendation for Novice Programmers: From Clear Expressions to Effective Results

IEEE Transactions on Reliability - Accepted - Second author and corresponding author

This work proposes IOCAPI, an intent-oriented and context-aware API recommendation method. It uses I/O examples to model user intent and connects LLM generation with task-semantic recovery, turning implicit user needs into structured constraints for explainable API recommendation.

Paper link

API Recommendation based on Consensus Learning for Novice Programmers

IEEE Transactions on Services Computing - Revise and Resubmit - First author

This work proposes CoLAR, a consensus-learning framework that integrates external semantic retrieval with the internal knowledge of large language models. It builds multiple reasoning paths, votes over candidate APIs, and improves robustness for short or incomplete novice queries.

Journal link

API Recommendation for Novice Programmers with Consensus Learning using Heterogeneous Information

Automated Software Engineering - Under Review - Second author and corresponding author

This work proposes CoHAPI, a Java API recommendation framework that learns complementary recommendation branches from Stack Overflow Q&A data and GitHub code comments. It uses rank-fusion consensus and semantic verification to improve stability under incomplete natural-language queries.

Journal link

AI Alumni Time Machine

Research-driven product prototype - 2026 - Present

Served as project lead, responsible for product planning, system architecture, core feature development, and team coordination from idea validation to prototype delivery.

Project website

Warehouse MES Management System

Industry internship project - May 2025 - Nov 2025

Participated as a core developer, designing and implementing key business modules on both backend microservices and frontend visualization pages.