activity
20242026
collaborators

9 papers

cs.AI2026

Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction

Mingzhe Du, Luu Anh Tuan, Tianyi Wu +4

Repository-level vulnerability reproduction is a demanding software engineering (SE) task: an agent must inspect a codebase, infer the input grammar that reaches a vulnerable path,…

cs.LG2026

CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models

Xiao Zhu, Xinyu Zhou, Boyu Zhu +5

Reinforcement Learning from Verifiable Rewards (RLVR) has driven recent progress in code large language models by leveraging execution-based feedback from unit tests, but its scala…

cs.SE2025

Nexus: Execution-Grounded Multi-Agent Test Oracle Synthesis

Dong Huang, Mingzhe Du, Jie M. Zhang +4

Test oracle generation in non-regression testing is a longstanding challenge in software engineering, where the goal is to produce oracles that can accurately determine whether a f…

cs.SE2025

Benchmarking LLMs for Unit Test Generation from Real-World Functions

Dong Huang, Jie M. Zhang, Mark Harman +3

Recently, large language models (LLMs) have shown great promise in automating unit test generation, significantly reducing the manual effort required by developers. To effectively…

cs.CL2025

AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge

Xiaobao Wu, Liangming Pan, Yuxi Xie +7

Data contamination hinders fair LLM evaluation by introducing test data into newer models' training sets. Existing studies solve this challenge by updating benchmarks with newly co…

cs.CL2025

EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code

Yuhao Qing, Boyu Zhu, Mingzhe Du +9

Existing code generation benchmarks primarily evaluate functional correctness, with limited focus on code efficiency and often restricted to a single language like Python. To addre…