Back to Arena

AutoGen Studio

by Microsoft Research

System Card

OrganizationMicrosoft Research
Released2023-01
Architectureagentic-workflow / conversational multi-agent framework with no-code UI
DetailsAutoGen is Microsoft's open-source multi-agent framework for conversational agent collaboration. AutoGen Studio adds a no-code web UI for prototyping multi-agent workflows without code. In v0.4 (2024), the framework was redesigned with OpenTelemetry observability, cross-language support (Python and .NET), and merged with Semantic Kernel into Microsoft Agent Framework (1.0 GA targeted 2026).
Parameters—
Domainagent-memory
Open SourceYes
WebsiteVisit
Microsoftmulti-agentno-code-UIOpenTelemetrySemantic-Kernel

Capability Profile

Benchmark Scores

5 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
1/2
LoCoMo
79.684p
MemoryBank
no data
Cross-Session Memory
1/1
LongMemEval
75.550p
Multi-Hop QA
2/3
BABILong
no data
MultiHop-RAG
74.169p
HotpotQA
76.781p
Agent Task Memory
1/1
AgentBench-Mem
7226p
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
0/1
RAGAS
no data
Sources:AutoGen Studio vendor documentation; evaluated on AgentBench Memory Track (Tsinghua KEG, 2308)AutoGen Studio vendor documentation; evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)AutoGen Studio vendor documentation; evaluated on LoCoMo: Long-Term Conversational Memory Benchmark (Snap Research, 2402)AutoGen Studio vendor documentation; evaluated on LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (Salesforce AI Research, 2410)AutoGen Studio vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)