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
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
77.570p
MemoryBank
73.733p
Cross-Session Memory
1/1
LongMemEval
79.677p
Multi-Hop QA
2/3
BABILong
77.272p
MultiHop-RAG
no data
HotpotQA
79.795p
Agent Task Memory
1/1
AgentBench-Mem
7226p
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
0/1
RAGAS
no data
Sources:Generative Agents paper (arXiv:2304.03442); evaluated on LoCoMo: Long-Term Conversational Memory Benchmark (Snap Research, 2402)Generative Agents paper (arXiv:2304.03442); evaluated on LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (Salesforce AI Research, 2410)Generative Agents paper (arXiv:2304.03442); evaluated on AgentBench Memory Track (Tsinghua KEG, 2308)Generative Agents paper (arXiv:2304.03442); evaluated on MemoryBank: Enhancing LLMs with Long-Term Memory (Sun Yat-sen University, 2305)Generative Agents paper (arXiv:2304.03442); evaluated on BABILong: Testing the Limits of LLMs with Long-Context Reasoning-in-a-Haystack (AIRI, 2406)Generative Agents paper (arXiv:2304.03442); evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)