EviMem improves accuracy on temporal and multi-hop questions in long-term conversational memory by iteratively diagnosing and filling evidence gaps, achieving 81.6% and 85.2% judge accuracy on LoCoMo at 4.5x lower latency than MIRIX.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Order-invariant cluster first-order logic has expressive power no greater than first-order logic on bounded-degree graphs.
citing papers explorer
-
EviMem: Evidence-Gap-Driven Iterative Retrieval for Long-Term Conversational Memory
EviMem improves accuracy on temporal and multi-hop questions in long-term conversational memory by iteratively diagnosing and filling evidence gaps, achieving 81.6% and 85.2% judge accuracy on LoCoMo at 4.5x lower latency than MIRIX.
-
Order-invariant cluster first-order logic on graph classes of bounded degree
Order-invariant cluster first-order logic has expressive power no greater than first-order logic on bounded-degree graphs.