1 citations · 1 across the 13 of their papers we have counts for
Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems
Zhongwen Luan, Xiaoyu Zhang, Ming Hu +3
As large language model (LLM)-based multi-agent systems (MASs) are increasingly applied to long-horizon complex tasks, their reliability has emerged as the core bottleneck hinderin…
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,…