COVE coordinates memory-based and parameter-based LLM self-evolution by routing tasks, scheduling training on plateau or cold-start signals, and keeping volatile API knowledge out of model weights via an anti-recitation penalty.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning What to Remember and What to Internalize in LLM Self-Evolution via Adaptive Memory-Parameter Coordination
COVE coordinates memory-based and parameter-based LLM self-evolution by routing tasks, scheduling training on plateau or cold-start signals, and keeping volatile API knowledge out of model weights via an anti-recitation penalty.