Long-term memory enables personalized agents, but its value depends on retrieving the right evidence at the right time. Most memory systems use static top-k retrieval: they issue one query, return a fixed number of memories, and pass them directly to a downstream model. This approach can miss evidence distributed acros...
Cascade is proposed, a hierarchical recoverability control framework that minimizes the internal identifiability of target knowledge and effectively reduces recoverability while maintaining stable model utility.
Qing-Chen Yu, Shi-Ying Duan, Xiao-Dong Li et al.· 0 citations
Designing effective memory mechanisms is crucial for advancing LLM-driven Multi-Agent Systems (MAS), helping agents learn together and perform better over time. While recent work has led to strong cooperation skills, most methods still use flat, unstructured memories, which easily get filled with noise and erase differ...
Cheng-Xin Yu, Zhao-Xin Fan, Fa-Guo Wu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.