Memora benchmark and FAMA metric show that LLMs and memory agents frequently reuse invalid memories and struggle to reconcile evolving information in long-term interactions.
The user has successfully met or exceeded their daily goal in 100% of the recorded sessions in this series
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents
Memora benchmark and FAMA metric show that LLMs and memory agents frequently reuse invalid memories and struggle to reconcile evolving information in long-term interactions.