MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading

ArXi:2605.10268v1 Announce Type: cross To tackle long-context reasoning tasks without the quadratic complexity of standard attention mechanisms, approaches based on agent memory have emerged, which typically maintain a dynamically updated memory when linearly processing document chunks. To mitigate the potential loss of latent evidence in this memorize-while-reading paradigm, recent works have integrated retrieval modules that allow agents to recall information previously discarded during memory overwriting.