activity
20242026
most citedCoSQA+: Pioneering the Multi-Choice Code Search Benchmark with Test-Driven Agents

2 citations · 10 across the 31 of their papers we have counts for

collaborators
Showing cs.SEShow all

31 papers · 1 filter

cs.SE2026

SWE-Gate: Passing Functional Tests Is Not Enough for Software Engineering Agents

Xin He, Yanlin Wang, Mingwei Liu +3

Repository-level software engineering benchmarks have significantly advanced the evaluation of coding agents, but existing benchmarks primarily measure whether generated patches pa…

cs.SE2026

Efficient SWE Agent Benchmarking via Trajectory-Aware Evaluation

Kefeng Duan, Dewu Zheng, Yanlin Wang +7

Evaluating software engineering agents on realistic benchmarks is costly, since each task may require multi-step code exploration, modification, and test execution. Existing effici…

cs.SE2026

Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation

Kefeng Duan, Dewu Zheng, Yanlin Wang +8

The repository-level code generation task requires synthesizing code that satisfies task requirements while remaining consistent with the target repository context. Since real-worl…

cs.SE2026

WebDesignIter: Co-Evolving Design Knowledge for Repository-Level Front-End Code Generation

Zheng Pei, Mingwei Liu, Zhenxi Chen +2

Front-end development accumulates change after change at the repository level, weaving complex cross-file dependencies that current LLM coding agents tuned for single-shot tasks ca…

cs.SE2026

Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code

Kaifeng He, Xiaojun Zhang, Peiliang Cai +7

Large language models (LLMs) frequently generate defective outputs in code generation tasks, ranging from logical bugs to security vulnerabilities. While these generation failures…

cs.SE2026

RepoDoc: A Knowledge Graph-Based Framework to Automatic Documentation Generation and Incremental Updates

Dong Xu, Mingwei Liu, Xiwen Wang +2

Maintaining up-to-date, comprehensive documentation for large codebases is a persistent challenge. Recent progress in automated documentation has moved from template-based rules to…