AI RESEARCH

Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory

arXiv CS.AI

ArXi:2605.10870v1 Announce Type: new Long-horizon language agents must operate under limited runtime memory, yet existing memory mechanisms often organize experience around descriptive criteria such as relevance, salience, or summary quality. For an agent, however, memory is valuable not because it faithfully describes the past, but because it preserves the distinctions between histories that must remain separated under a fixed budget to good decisions.