Zijie Xu
Biographic Data
| ID | 8197291 |
|---|---|
| NAME | Zijie Xu |
| GIVEN NAMES | Zijie |
| FAMILY NAME | Xu |
| SIGNATURE | XU Z |
| AFFILIATIONS | Minzu University of, Beijing, China |
| ORCID | 0009-0003-1670-8134 |
| VERIFIED | Yes |
| TOTAL WORKS | 2 |
| TOTAL CITATIONS | 0 |
| WORKS AS AUTHOR | 2 |
| WORKS AS EDITOR | 0 |
| FIRST PUBLICATION YEAR | 2024 |
| LATEST PUBLICATION YEAR | 2026 |
| H-INDEX | 0 |
The Trust Paradox in LLM-Based Multi-Agent Systems
Multi-agent systems powered by large language models (LLMs) are advancing rapidly, yet the security implications of trust-mediated collaboration remain insufficiently understood. We introduce and empirically validate thetrust–vulnerability paradox (TVP): increasing inter-agent trust to improve coordination can simultaneously amplify risks of over-exposure and authorization drift (AD). To study this phenomenon under controlled and reproducible con…
An ERP study on novel word learning in an immersive virtual reality context
In this behavioral and electrophysiological study, we compare novel word learning, particularly lexical form acquisition, in an immersive virtual reality (VR) context with a picture-word (PW) association context. We also test whether inhibitory control and age of second language acquisition (L2 AoA) have modulating effects. Chinese speakers of L2 English learned two sets of German words, one set in each of the contexts. Behavioral performance fro…
No prominent works on this page.
An ERP study on novel word learning in an immersive virtual reality context
In this behavioral and electrophysiological study, we compare novel word learning, particularly lexical form acquisition, in an immersive virtual reality (VR) context with a picture-word (PW) association context. We also test whether inhibitory control and age of second language acquisition (L2 AoA) have modulating effects. Chinese speakers of L2 English learned two sets of German words, one set in each of the contexts. Behavioral performance fro…
The Trust Paradox in LLM-Based Multi-Agent Systems
Multi-agent systems powered by large language models (LLMs) are advancing rapidly, yet the security implications of trust-mediated collaboration remain insufficiently understood. We introduce and empirically validate thetrust–vulnerability paradox (TVP): increasing inter-agent trust to improve coordination can simultaneously amplify risks of over-exposure and authorization drift (AD). To study this phenomenon under controlled and reproducible con…
Access Control and Trust (1 work) · Authorization (1 work) · Categorization, perception, and language (1 work) · Computer Science (1 work) · Explainable Artificial Intelligence (XAI (1 work) · Human–computer interaction (1 work) · Information security (1 work) · Language, Metaphor, and Cognition (1 work) · Neurobiology of Language and Bilingualism (1 work) · Psychology (1 work)