List your company

Temporal Reasoning on Time-Dialog Out-of-Domain (test)

40.2F1 ScoreMemAgent
28.7631.7334.737.67Dec 23, 2025

Evaluation results

MethodLinks
MemAgentParams=7B, Setting=Non-RAG2025.1240.2
Memory-T1Params=3B, Setting=Non-RAG2025.1237.7
MemAgentParams=7B, Setting=RAG2025.1237.6
Memory-T1Params=3B, Setting=RAG2025.1236.7
Time-R1Params=3B, Setting=RAG2025.1231.4
Time-R1Params=3B, Setting=Non-RAG2025.1229.2