3 papers
cs.LG2026
Anchoring Bias: A Persistent Fairness Backdoor Attack against MLLMs under Continual Learning
Yuyang Luo, Kai Shu
Multimodal Large Language Models (MLLMs) are increasingly deployed in high-stakes domains where fairness is a critical safety requirement. In practice, these models are continually…
cs.AI2026
Query-Only Backdoor Attacks on Self-Evolving Skills via Trajectory Poisoning
Yuyang Luo, Haoran Wang, Kai Shu
Agentic skills improve large language model (LLM) agents by encoding reusable procedures for complex tasks. However, manually authored skills often adapt poorly to long-horizon tas…
cs.MA2026
Scaling Teams or Scaling Time? Memory Enabled Lifelong Learning in LLM Multi-Agent Systems
Shanglin Wu, Yuyang Luo, Yueqing Liang +4
Large language model (LLM) multi-agent systems can scale along two distinct dimensions: by increasing the number of agents and by improving through accumulated experience over time…