The paper introduces Router-Mem, an evidence-conditioned progressive execution framework for long-horizon agent memory. It first runs a shared, low-cost retrieval prefix, then uses a lightweight sufficiency router to make a single-token early-termination decision. If the retrieved evidence is insufficient, the system expands memory blocks and performs deeper analysis and aggregation. The abstract reports scores of 55.17% on AMA-Bench and 38.77% on BEAM, while reducing average inference time by 27.3% and 25.5%, respectively, compared with full memory execution.
No heat snapshots are available in the last 24 hours.