EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents 事件

EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents arXiv:2606.05894v1 Announce Type: new Abstract: Long-horizon agents can archive large histories, but future answers still incur retrieval, rereading, and context costs. When retained memory misses answer-relevant evidence, the system must return to larger portions of the raw history. We study budgeted evidence survival: before the query is known, which source evidence should be retained so that it remains recoverabl