SALIMORY trains an LM to orchestrate cognitive memory operations via stage-wise process rewards, cutting memory failures by one-third and more than doubling good personalization rates.
LD-Agent: Longitudinal dialogue agent with self-evolving memory.arXiv preprint arXiv:2406.18484,
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
-
SaliMory: Orchestrating Cognitive Memory for Conversational Agents
SALIMORY trains an LM to orchestrate cognitive memory operations via stage-wise process rewards, cutting memory failures by one-third and more than doubling good personalization rates.