AMA is a multi-agent system that dynamically manages memory granularity and enforces consistency for LLM agents, achieving better performance on long-context tasks with 80% less token consumption.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
AMA: Adaptive Memory via Multi-Agent Collaboration
AMA is a multi-agent system that dynamically manages memory granularity and enforces consistency for LLM agents, achieving better performance on long-context tasks with 80% less token consumption.