#artificial intelligence
May 2026
MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs
MemQ is introduced, which applies TD ($\lambda$) eligibility traces to memory Q-values, propagating credit backward through a provenance DAG that records which memories were retrieved when each new memory was created.
Junwei Liao, Hao-Ting Shi, Ruiwen Zhou et al.
· arXiv.org · 4 citations