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 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 approaches.The limits of passive retrieval in long-horizon tasksIn classic retrieval pipelines, documents are retr