activity
20242026
most citedAcTracer: Active Testing of Large Language Model via Multi-Stage Sampling

1 citations · 1 across the 12 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

DynaTrust: Defending Multi-Agent Systems Against Sleeper Agents via Dynamic Trust Graphs

Yu Li, Qiang Hu, Yao Zhang +3

Large Language Model-based Multi-Agent Systems (MAS) have demonstrated remarkable collaborative reasoning capabilities but introduce new attack surfaces, such as the sleeper agent,…