New agentic memory framework uses 118K tokens per query. LangMem burns through 3.26M. (opens in new tab)

Long-horizon reasoning exposes a core weakness in AI agents: context windows fill up fast, and retrieval pipelines return noise instead of signal.To solve this, researchers at the National University of Singapore developed This multi-step memory reconstruction is integrated into the reasoning process of the large language model (LLM). While not the only framework in this space, MRAgent significantly reduces token consumption and runtime costs compared to other agentic memory management approa...