User as Engram: Internalizing Per-User Memory as Local Parametric Edits
Quick Answer
This paper shows that The 'User as Engram' model proposes storing user-specific content as local edits in a memory table, enhancing reasoning accuracy by 5.6x while maintaining a 33,000x smaller memory footprint compared to traditional per-user LoRA adapters.
Key Points
- User-specific facts stored as surgical edits in a hash-keyed memory table.
- Achieves 5.6x higher indirect reasoning accuracy than per-user LoRA.
- Maintains a 33,000x smaller memory footprint compared to traditional methods.
- Allows multiple users to coexist with additive and lossless edits.
- Retrieval efficiency improves significantly after ~100 facts.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Personal memory in a language model is two problems: content and reasoning skill. The brain keeps the two apart (a sparse, local engram in the hippocampus for each episode, a slow neocortex for the shared skills that interpret it), so a new fact need not overwrite everything else. Most personalization today keeps a user's facts outside the weights, in a natural-language memory file or a retrieval index. When facts are written into the model instead, the standard recipe is the per-user LoRA adapter, which does the opposite of the brain, folding content and skill into one global weight delta. Writing a user's facts as a LoRA contaminates text unrelated to them; writing the same facts as local Engram rows leaves it mathematically untouched, resulting in a roughly 33,000x smaller memory footprint.
We therefore propose User as Engram: store a user's content as surgical edits to the hash-keyed memory table of an Engram model, and carry the reasoning skill in one shared adapter. This layered design matches per-user LoRA's direct recall while delivering 5.6x higher indirect-reasoning accuracy on average, and never makes a single user worse at reasoning than the untouched base. The edit is a glass box: writing a fact switches on its lookup at exactly the trigger, adds the value the answer needs, leaves every other position unchanged to the last bit, and fails if written into the wrong layer. Because different users' facts land in disjoint hash slots, their edits compose: many users live in one shared table at once, stacking additively and losslessly, where a per-user LoRA, a single global weight delta, admits only one. Upon retrieval, a per-user Engram table does not grow with the population the retriever must search, so past ~100 facts it overtakes a retrieval pipeline on a 2.5x larger model.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.19172 [cs.AI] |
| (or arXiv:2606.19172v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.19172 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Bojie Li [view email]
[v1]
Wed, 17 Jun 2026 15:15:19 UTC (447 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.