6 papers
Analyzing and Mitigating Cost-Inefficient Behaviors in Coding Agents
Yiran Hu, Nan Jiang, Shanchao Liang +3
Although effective, coding agents often incur substantial monetary costs. Their recurring cost-inefficient behaviors remain underexplored. We conduct the first study of behavioral…
TENET: One Step Toward Test-Driven Development for Repository-Level Code Generation
Yiran Hu, Shanchao Liang, Nan Jiang +2
Test-Driven Development (TDD) is a widely adopted practice that requires developers to create and execute tests alongside implementation. With recent advances in Large Language Mod…
Unified Software Engineering Agent as AI Software Engineer
Leonhard Applis, Yuntong Zhang, Shanchao Liang +3
The growth of Large Language Model (LLM) technology has raised expectations for automated coding. However, software engineering is more than coding and is concerned with activities…
Can Language Models Replace Programmers for Coding? REPOCOD Says 'Not Yet'
Shanchao Liang, Yiran Hu, Nan Jiang +1
Recently, a number of repository-level code generation benchmarks-such as CoderEval, DevEval, RepoEval, RepoBench, and LongCodeArena-have emerged to evaluate the capabilities of la…
CaBaGe: Data-Free Model Extraction using ClAss BAlanced Generator Ensemble
Jonathan Rosenthal, Shanchao Liang, Kevin Zhang +1
Machine Learning as a Service (MLaaS) is often provided as a pay-per-query, black-box system to clients. Such a black-box approach not only hinders open replication, validation, an…
LATTE: Improving Latex Recognition for Tables and Formulae with Iterative Refinement
Nan Jiang, Shanchao Liang, Chengxiao Wang +2
Portable Document Format (PDF) files are dominantly used for storing and disseminating scientific research, legal documents, and tax information. LaTeX is a popular application for…