Atomic user model retrieves 8 fields at 23% context to match full-profile personalization
Authors self-report: building user profiles into an "Atomic User Model" (AUM) with a stable identity core and retrieving 8 fields per task matches full-profile personalized writing quality at only 23% of the context
ImportanceLocalEvidenceE2 unreplicated
Build user profiles into an "Atomic User Model" (AUM) with a stable identity core and retrieve a few fields per task into the prompt: four authors self-report that 8 retrieved fields match the personalized writing quality of the full profile at only 23% of the context (211 vs 915 tokens).
The prior approach injected the entire user profile into the prompt, at high context cost; four preregistered controls show the gains come from profile structure, not the retrieval method.
Experiments used 16 simulated users, 6 style-sensitive task types, and 3 random seeds, self-tested by the authors, not peer-reviewed or independently replicated; the preprint was submitted September 10 and updated to v2 on September 16 (arXiv:2609.12086).
Source: arXiv:2609.12086 abstract page ↗