Back to Arena

Generative Agents

by Stanford University / Google Research

System Card

OrganizationStanford University / Google Research
Released2023-04
Architectureagentic-workflow / Memory stream + reflection tree + planning
DetailsThree-component architecture: a Memory Stream stores natural-language experiences, Reflection synthesizes memories into higher-level conclusions in a tree, and Planning translates reasoning into plans. Retrieval scored by recency, importance, and relevance.
Parameters—
Domainagent-memoryepisodic-sessionlifelong-learning
Open SourceYes
PaperView Paper
CodeRepository
memory-streamreflection-treesmallvillesimulacrauist-2023

Capability Profile

Benchmark Scores

6 of 14 benchmarks
Data Transparency:6 estimated
Long-Context Retrieval
0/5
RULER
no data
NIAH
no data
LooGLE
no data
LongBench
no data
∞Bench
no data
Multi-Turn Recall
2/2
LoCoMo
77.571pEstimated
MemoryBank
73.733pEstimated
Cross-Session Memory
1/1
LongMemEval
79.676pEstimated
Multi-Hop QA
2/3
BABILong
77.272pEstimated
MultiHop-RAG
no data
HotpotQA
79.795pEstimated
Agent Task Memory
1/1
AgentBench-Mem
7226pEstimated
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
0/1
RAGAS
no data
Sources:Arena estimate — derived from capability profile, not independently verified