RippleMem: From Isolated Retrieval to Associative Recollection for Long-Term Agent Memory
Ranking
Overall
77
Content
95
Popularity
34
Observed public metrics from 1 member.
Merged summary
TL;DR - RippleMem is a long-term agent memory system that retrieves initial “anchor” memories, then follows semantic and structural associations to reconstruct distributed evidence. It improves benchmark accuracy while cutting memory-graph construction cost by roughly 30×.
- Stores interactions as cue-rich episodic units in an event-centric memory graph.
- Uses hybrid cues for anchor retrieval, followed by adaptive associative expansion.
- Improves LLM-as-a-Judge accuracy by 3.95% on LoCoMo and up to 11.87% on LongMemEval-S.
- Addresses incomplete flat retrieval without relying on noisy full-context searches or costly graph construction.
Sources (1)
RippleMem: From Isolated Retrieval to Associative Recollection for Long-Term Agent Memory
Public signals
Semantic Scholar citations 0 · Semantic Scholar influential citations 0
TL;DR - RippleMem is a long-term agent memory system that retrieves initial “anchor” memories, then follows semantic and structural associations to reconstruct distributed evidence. It improves benchmark accuracy while cutting memory-graph construction cost by roughly 30×.
- Stores interactions as cue-rich episodic units in an event-centric memory graph.
- Uses hybrid cues for anchor retrieval, followed by adaptive associative expansion.
- Improves LLM-as-a-Judge accuracy by 3.95% on LoCoMo and up to 11.87% on LongMemEval-S.
- Addresses incomplete flat retrieval without relying on noisy full-context searches or costly graph construction.