AIBullisharXiv – CS AI · 9h ago7/10
🧠
Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agents
Researchers introduce MAGE, a novel memory management system for LLM-based agents that organizes task histories as hierarchical state trees rather than semantic similarity clusters. The approach achieves 7.8-20.4 percentage point improvements in task success rates while reducing token consumption by 55.1% on long-horizon tasks with interdependent decisions.