AMA-Bench

Researchers introduced RSM-full, an online clustered-memory pipeline for long-horizon LLM deployments, achieving 83% of Full-Context quality at 32% of the token cost on the AMA-Bench benchmark at a 4k…

Researchers propose MESA, a task-adaptive multi-structure evidence selection framework for long-horizon agent memory, which dynamically selects and fuses a query-specific subset from five complementar…