RecMem reduces memory construction token costs by up to 87% in long-running LLM agents by consolidating memory only upon sustained recurrence of semantically similar interactions, while exceeding the accuracy of three prior systems.
Do not confuse the time of conversation with the time when an event actually happened if the text distinguishes them
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
-
RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents
RecMem reduces memory construction token costs by up to 87% in long-running LLM agents by consolidating memory only upon sustained recurrence of semantically similar interactions, while exceeding the accuracy of three prior systems.