Back to Arena

Voyager

by NVIDIA / Caltech / UT Austin / Stanford / ASU / UW (Wang et al.)

System Card

OrganizationNVIDIA / Caltech / UT Austin / Stanford / ASU / UW (Wang et al.)
Released2023-05
Architectureagentic-workflow / Ever-growing code skill library + curriculum
DetailsLifelong Minecraft agent with three components: automatic curriculum, ever-growing skill library of executable code, and iterative prompting with environment feedback. Skills are retrieved by embedding similarity and compounded without catastrophic forgetting.
Parameters—
Domainagent-memorylifelong-learning
Open SourceYes
PaperView Paper
WebsiteVisit
CodeRepository
minecraftskill-libraryembodiedcurriculumcode

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
83.695pEstimated
MemoryBank
75.753pEstimated
Cross-Session Memory
1/1
LongMemEval
87.198pEstimated
Multi-Hop QA
2/3
BABILong
78.481pEstimated
MultiHop-RAG
no data
HotpotQA
81.598pEstimated
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