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.
InFindings of the Association for Computational Linguistics: EMNLP 2025, pages 23281–23298, Suzhou, China
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.