CoEvo-Mem co-adapts a residual retrieval router and a relational memory graph with alternating phases and reports improved LLM agent performance, but it is not the top method on every benchmark in its own results.
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
-
CoEvo-Mem: Co-Evolving Retrieval Policy and Memory Bank for LLM Agents
CoEvo-Mem co-adapts a residual retrieval router and a relational memory graph with alternating phases and reports improved LLM agent performance, but it is not the top method on every benchmark in its own results.