Author

Hanjun Wei

Observed name: Wei, Hanjun

Institution: University of Chinese Academy of Sciences

Observed institution: University of Chinese Academy of Sciences

OpenAlex ID: A5141000130

Why Generate a Click? Plug-in Decision Heads for Web Agents

2026 · Gan, Chengguang, Liang, Yunhao, et al. · arXiv (Cornell University)

LLM-Based Test Generation: Information Sources, Generation Strategies, and Quality Evidence

2026 · Liang, Yunhao, Gan, Chengguang, et al. · arXiv (Cornell University)

Test-Driven Approaches to Software Engineering with Large Language Models: A Survey of Phases, Tasks, and Agent Skills

2026 · Liang, Yunhao, Gan, Chengguang, et al. · arXiv (Cornell University)

Correct Tests Are Not Enough: Measuring and Training Oracle Conversion in Specification-Based Test Generation

2026 · Liang, Yunhao, Gan, Chengguang, et al. · arXiv (Cornell University)

How Output Format Confounds Data Quality and Capability in Instruction Tuning

2026 · Gan, Chengguang, Wei, Hanjun, et al. · arXiv (Cornell University)

Joint Training Is Not Enough: Conditioned Cross-Granularity Training for Multimodal Document Understanding

2026 · Gan, Chengguang, Liang, Yunhao, et al. · arXiv (Cornell University)

Auditing and Decomposing Feedback-Driven Evolution in LLM Test Generation under the Oracle Problem

2026 · Liang, Yunhao, Gan, Chengguang, et al. · arXiv (Cornell University)

Security Tests as Executable Specifications for LLM Code Generation: Benefits, Trade-offs, and Coverage Limits

2026 · Liang, Yunhao, Gan, Chengguang, et al. · arXiv (Cornell University)

Do Code Language Models Follow Tests? Paired Interventions on Program Behavior

2026 · Liang, Yunhao, Gan, Chengguang, et al. · arXiv (Cornell University)

A Learning-Rate-Gated Failure of GRPO in a Small Language and Vision-Language Model Web Agent: A Controlled Null and Its Mechanism

2026 · Gan, Chengguang, Cai, Zhixi, et al. · arXiv (Cornell University)

MAG: A Web-Agent Benchmark and Harness for Multimodal Action and Guide Generation

2026 · Gan, Chengguang, Wei, Hanjun, et al. · arXiv (Cornell University)

A Multilingual Dataset and Empirical Validation for the Mutual Reinforcement Effect in Information Extraction

2026 · Association for Computational Linguistics 2026, Gan, Chengguang, et al. · Underline Science Inc.

Works count: 12

Citation count:

H-index:

I10-index: