Back to Arena

Generative Agents

by Stanford / Google

System Card

OrganizationStanford / Google
Released2023-04
Architecturehierarchical-summary / Memory stream + reflection tree + planning
DetailsExtends an LLM with a complete natural-language record of agent experiences (memory stream), synthesizes them over time into hierarchical reflections (non-leaf nodes of a reflection tree), and retrieves them dynamically by recency, importance, and relevance to plan behavior.
Parameters—
Domainagent-memoryepisodic-sessionlifelong-learning
Open SourceYes
PaperView Paper
CodeRepository
uist-2023reflectionsmallvillememory-streamsimulation

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
7232pEstimated
MemoryBank
65.416pEstimated
Cross-Session Memory
1/1
LongMemEval
71.125pEstimated
Multi-Hop QA
2/3
BABILong
71.515pEstimated
MultiHop-RAG
no data
HotpotQA
7255pEstimated
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