Back to Arena

HEMA

by independent (Ahn et al.)

System Card

Organizationindependent (Ahn et al.)
Released2025-04
Architecturehierarchical-summary / Dual Compact + Vector memory
DetailsCombines Compact Memory (a one-sentence narrative summary continuously updated) with Vector Memory (episodic chunk embeddings queried by cosine similarity). On a 6B transformer, maintains dialogues beyond 300 turns under 3,500 tokens prompt length.
Parameters—
Domainepisodic-sessionlong-contextagent-memory
Open SourceNo
PaperView Paper
hippocampusdual-memorycompact-summaryconversational

Capability Profile

Benchmark Scores

6 of 14 benchmarks
Data Transparency:6 estimated
Long-Context Retrieval
1/5
RULER
no data
NIAH
no data
LooGLE
no data
LongBench
no data
∞Bench
77.231pEstimated
Multi-Turn Recall
1/2
LoCoMo
76.766pEstimated
MemoryBank
no data
Cross-Session Memory
1/1
LongMemEval
66.821pEstimated
Multi-Hop QA
2/3
BABILong
72.926pEstimated
MultiHop-RAG
no data
HotpotQA
66.735pEstimated
Agent Task Memory
1/1
AgentBench-Mem
6816pEstimated
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
0/1
RAGAS
no data
Sources:Arena estimate — derived from capability profile, not independently verified