New agentic memory framework uses 118K tokens per query. LangMem burns through 3.26M.

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 MRAgent, a framework that abandons the static "retrieve-then-reason" approach. Instead, it uses a mechanism that allows an agent to dynamically develop its memory based on accumulating evidence. This multi-step memory reconstruction is integrated into the reasoning proces