6 papers
LLM-as-a-Judge Version Shift: The Instrument Changed, Not the Standard
Guijia Zhang, Harry Yang
Automated research pipelines increasingly rely on fixed LLM judges to rank, filter, and revise proposals, yet these judges are routinely replaced by newer versions. We study whethe…
Aborted but Not Forgotten: KV-Cache Retention Breaks Rollback Consistency in Language Agents
Guijia Zhang, Harry Yang
Stateful language agents assume a rejected branch can be taken back by clearing it from the application transcript. We show this breaks when the serving session retains key/value (…
Do GUI Agents Believe Their Eyes? Diagnosing State-Belief Reliance on Pixels versus Structure
Guijia Zhang, Yuxun Chen, Yuheng Qi +1
Multimodal GUI agents read an interface through two redundant channels: the rendered pixels of a screenshot and a serialized structure such as a document object model or accessibil…
Hallucination as Exploit: Evidence-Carrying Multimodal Agents
Guijia Zhang, Hao Zheng, Harry Yang
Multimodal agents increasingly choose tool calls from screenshots, documents, and webpages, where a false perceptual claim can turn hallucination from an answer-quality error into…
STARS: Skill-Triggered Audit for Request-Conditioned Invocation Safety in Agent Systems
Guijia Zhang, Shu Yang, Xilin Gong +1
Autonomous language-model agents increasingly rely on installable skills and tools to complete user tasks. Static skill auditing can expose capability surface before deployment, bu…
SCP: Spatial Causal Prediction in Video
Yanguang Zhao, Jie Yang, Shengqiong Wu +9
Spatial reasoning, the ability to understand spatial relations, causality, and dynamic evolution, is central to human intelligence and essential for real-world applications such as…