evidence-distillation

Tag

Cards List
#evidence-distillation

DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA

arXiv cs.CL · 2026-05-22 Cached

DeferMem introduces a long-term memory framework for LLM agents that decouples memory into high-recall candidate retrieval and query-conditioned evidence distillation using reinforcement learning, achieving state-of-the-art QA accuracy with faster runtime.

0 favorites 0 likes
← Back to home

Submit Feedback