Reliable Post-Retrieval Assembly for Agent Memory: Separating Evidence Extraction from Policy Execution

LLM-based memory systems can retrieve relevant evidence yet still fail when answer generation entangles semantic filtering, conflict resolution, prior suppression, and output generation in one step. We study this failure as a problem of post-retrieval assembly. In the MemoryAgentBench (MAB) release used here, FactConsolidation explicitly states that newer facts have larger serial numbers, yet the best reported retrieval or memory result is 54% single-hop and all 22 reported systems score at most 7% multi-hop. We evaluate a structured assembly interface in which an LLM first extracts semantically matching evidence into a candidate representation and a separate stage executes the required answer policy. At 262K, this pipeline reaches 82% and 93% single-hop accuracy and 27% and 41% multi-hop accuracy with gpt-4o-mini and gpt-4o, respectively, exceeding every result reported in the MAB v3 FactConsolidation comparison. This is a task-level result, not a claim that the evaluated memory architectures are broadly inferior. A controlled whole-pipeline comparison, with identical backbone, retrieved top-10 evidence, chunking, and 100 examples per condition, improves single-hop accuracy by 10.8 percentage points on average and 21 points at 262K. A targeted comparison using the same extraction setup shows that changing only the final policy executor contributes 2.0 points on average and 0 points at 262K. Most of the gain therefore comes from separating evidence identification from final policy execution rather than from the freshness operator itself. A LongMemEval check finds no significant overall advantage over direct LLM judgment (26/45 versus 29/45; paired exact McNemar p = 0.45), bounding the result to current-value questions with explicit version metadata. The evidence identifies post-retrieval assembly as a distinct reliability boundary between retrieval and answer generation.