Back to Arena

MoT

by Fudan (Li, Qiu)

System Card

OrganizationFudan (Li, Qiu)
Released2023-05
Architectureepisodic-buffer / Pre-thought high-confidence thoughts as memory
DetailsTwo-stage self-improvement: pre-thinks on unlabeled data, stores high-confidence chains-of-thought as memory, then recalls them at test time to guide reasoning. No parameter updates, no labeled data.
Parameters—
Domainagent-memoryepisodic-session
Open SourceYes
PaperView Paper
CodeRepository
emnlp-2023self-improvementcotunlabeled

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
73.538pEstimated
MemoryBank
74.741pEstimated
Cross-Session Memory
1/1
LongMemEval
74.441pEstimated
Multi-Hop QA
2/3
BABILong
no data
MultiHop-RAG
72.354pEstimated
HotpotQA
71.350pEstimated
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