Back to Arena

Agent Workflow Memory

by CMU (Wang, Mao, Fried, Neubig)

System Card

OrganizationCMU (Wang, Mao, Fried, Neubig)
Released2024-09
Architectureagentic-workflow / Induced-workflow (routine) memory
DetailsInduces commonly reused routines (workflows) from training examples or on-the-fly from test queries, then selectively injects them to guide subsequent generations. Workflows are context-abstracted sub-routines.
Parameters—
Domainagent-memorylifelong-learning
Open SourceYes
PaperView Paper
CodeRepository
web-agentworkflowsroutinesmind2webwebarena

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
8191p
MemoryBank
77.965p
Cross-Session Memory
1/1
LongMemEval
78.768p
Multi-Hop QA
2/3
BABILong
7658p
MultiHop-RAG
no data
HotpotQA
73.663p
Agent Task Memory
1/1
AgentBench-Mem
7226p
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
0/1
RAGAS
no data
Sources:Agent Workflow Memory paper (arXiv:2409.07429); evaluated on LoCoMo: Long-Term Conversational Memory Benchmark (Snap Research, 2402)Agent Workflow Memory paper (arXiv:2409.07429); evaluated on LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (Salesforce AI Research, 2410)Agent Workflow Memory paper (arXiv:2409.07429); evaluated on AgentBench Memory Track (Tsinghua KEG, 2308)Agent Workflow Memory paper (arXiv:2409.07429); evaluated on BABILong: Testing the Limits of LLMs with Long-Context Reasoning-in-a-Haystack (AIRI, 2406)Agent Workflow Memory paper (arXiv:2409.07429); evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)Agent Workflow Memory paper (arXiv:2409.07429); evaluated on MemoryBank: Enhancing LLMs with Long-Term Memory (Sun Yat-sen University, 2305)