Levina Li

Sparsifying communication topologies in LLM multi-agent systems can lead to significant efficiency gains without sacrificing accuracy, challenging conventional design approaches.

Federated learning can outperform centralized models in multi-agent safety without compromising data privacy, achieving a remarkable 43% reduction in attack success rates.

Adaptive memory management can boost LLM task success by over 15 points while slashing token usage by up to 20%.