From the 2 of 11 linked papers with an AI index.
11 papers
MADE: Belief-Driven Dual-Agent Coordination for Autonomous Model Deployment
Yicheng Liu, Bolin Zhang, Weiran Liu +4
LLM-based agents now have strong general capabilities. However, they still struggle with domain-specific tasks, motivating the integration of external tools to broaden their capabi…
TraceDev: A Traceability-Driven Multi-agent Framework for Requirement-to-Code Development
Mingyu Chen, Yakun Zhang, Zihao Xie +5
In modern software development, the rapid advancement of Large Language Models (LLMs) has made the end-to-end transformation of Natural Language Requirements (NLRs) into executable…
An Empirical Study for Android-to-OpenHarmony GUI Test Migration
Yakun Zhang, Xinjia Chen, Yiyun Chen +6
The paper empirically evaluates how existing Android GUI test migration tools perform on OpenHarmony, builds a benchmark of real apps, and proposes an improved method (ITeM‑HM) tha…
LogiDroid: Individual Functional Test Generation via Business Logic Extraction and Adaptation
Yakun Zhang, Zihan Wang, Xinzhi Peng +6
LogiDroid is a two‑stage system that uses large language model agents to extract structured business logic from requirements and adapt it to a mobile app's GUI, automatically gener…
Contextualized Code Pretraining for Code Generation
Chen Liu, Qingyuan Liang, Hanwen Zhang +3
As code generation becomes increasingly central to improving software development efficiency, modern code models are largely trained and evaluated on code with natural-language des…
Persistent Cross-Attempt State Optimization for Repository-Level Code Generation
Ruwei Pan, Jiangshuai Wang, Qisheng Zhang +6
Large language models (LLMs) have achieved substantial progress in repository-level code generation. However, solving the same repository-level task often requires multiple attempt…