LW
Longtian Wang
cs.AIcs.CRcs.SEcs.CLcs.CVcs.IRcs.LG
On Valency
published · living versionsW_g5gbs324·v1 · currentpublished
AgenTest: Mining Business Rules to Test LLM Agents for Business Logic Bugs
with Lili Quan, Yuelin Wang, Mingfei Cheng, Chao Shen +2
1 version
W_3ykek3zb·v1published
Preprints & journals
9 papers in the corpus · 2024–2026AgenTest: Mining Business Rules to Test LLM Agents for Business Logic Bugs2610.28116v1 · Lili Quan, Longtian Wang, Yuelin Wang et al.2026 · 0 citationsarXivon Valency
When Code Becomes an LLM Call: An Empirical Study of Call-Site Contracts in Agentic Systems2610.24545v1 · Shihao Weng, Longtian Wang, Yang Feng et al.2026 · 0 citationsarXivon Valency
Detecting Backdoors in Object Detection via Pre-NMS Prediction Distribution Shift2608.19088v1 · Longtian Wang, Zhengyu Zhao, Chenhao Lin et al.2026 · 0 citationsarXiv
Selection-Based Vulnerabilities: Clean-Label Backdoor Attacks in Active Learning2508.05681v1 · Yuhan Zhi, Longtian Wang, Xiaofei Xie et al.2025 · 0 citationsarXiv
Benchmarking and Revisiting Code Generation Assessment: A Mutation-Based Approach2505.06880v1 · Longtian Wang, Tianlin Li, Xiaofei Xie et al.2025 · 0 citationsarXiv
TokenProber: Jailbreaking Text-to-image Models via Fine-grained Word Impact Analysis2505.08804v1 · Longtian Wang, Xiaofei Xie, Tianlin Li et al.2025 · 0 citationsarXiv
Revisiting Training-Inference Trigger Intensity in Backdoor Attacks2503.12058v1 · Chenhao Lin, Chenyang Zhao, Shiwei Wang et al.2025 · 0 citationsarXiv
Exposing Product Bias in LLM Investment Recommendation2503.08750v1 · Yuhan Zhi, Xiaoyu Zhang, Longtian Wang et al.2025 · 0 citationsarXiv
StablePT: Towards Stable Prompting for Few-shot Learning via Input Separation2404.19335v2 · Xiaoming Liu, Chen Liu, Zhaohan Zhang et al.2024 · 2 citationsarXiv
Career total: 18 works. 9 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.