LANTERN: Layered Archival and Temporal Episodic Retrieval Network for Long-Context LLM Conversations

LANTERN is a lightweight memory layer for LLMs that archives conversation turns and restores relevant details after context compaction via hybrid retrieval. It recovers 78.3% of verifiable facts lost to compaction, outperforming LLM-driven approaches with significantly lower inference cost and zero LLM calls.