Method Drift›Agent / long-term memory
Superseded baseline#41 of 63 most-superseded
Memento
Embodied Agents Meet Personalization: Investigating Challenges and Solutions Through the Lens of Memory UtilizationAgent / long-term memory · first seen May 22, 2025
superseded — cited as a baseline and beaten by newer methods
0 papers critique it · 1 beat it on benchmarks
Beaten on benchmarks
Head-to-head results where a newer method reports beating Memento. Values are copied from the source paper's tables — verify against the cited paper.
- Learning to Retrieve: Dual-Level Long-Term Memory for Text-to-SQL Agents
Learning to Retrieve beats Memento · Overall [Phase 1]
33.01 vs 28.67
- Learning to Retrieve: Dual-Level Long-Term Memory for Text-to-SQL Agents
Learning to Retrieve beats Memento · Overall [Phase 2]
22.17 vs 17.83
- Learning to Retrieve: Dual-Level Long-Term Memory for Text-to-SQL Agents
Learning to Retrieve beats Memento · Overall [Average #Turns]
7.84 vs 8.59
- Learning to Retrieve: Dual-Level Long-Term Memory for Text-to-SQL Agents
Learning to Retrieve beats Memento · Success Rate [Transferability]
69.29 vs 68.56
Newer alternatives
Recent methods in the same sub-problem, not yet superseded in the knowledge base.
- May 30, 2026