Lingxi Zhang
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1ML×1Multiagent×1
Frequent co-authors
Research Timeline
2026
When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems
This paper analyzes the failure of current embedding-based defenses in multi-agent LLM systems and proposes using token-level confidence scores (logits) for improved robustness.
Highlighted terms show continued research focus across papers