HabitusMem: Belief Memory over Evolving User Preferences for LLM Agents
Organizations: Mohamed bin Zayed University of Artificial Intelligence · Alibaba Group
Abstract
Personalized LLM agents must act on a user's current preferences, which change across interactions and are rarely stated in full. Existing memory systems store and retrieve content from the interaction history and leave the agent to work out which preferences still hold and where they apply. Such content does not indicate whether a preference is still current or where it applies, so agents often act on outdated or misapplied preferences. We instead treat memory as the assistant's belief about the user. Following Bourdieu's account of habitus as durable but revisable dispositions, we model the user as a latent preference state that every interaction, including the current request, both reveals and updates. The belief summarizes what the history supports about this state, and memory consists of the individual beliefs that bear on the agent's current decision, each with its evidence, scope, and status. We implement this view in HabitusMem, a trained writer that states these beliefs as text records for a frozen agent. Across two agent families, HabitusMem achieves the best results among memory systems on both PersonaMem-v2 and VitaBench 2.0. Controlled analyses show that learned request conditioning drives the answering gain, while auxiliary training tasks improve tool use.
Figures & tables
| Memory | Know- | Pro- | Pro- | Crea- | Trans- | Personal- | Trouble | Chat | Social | Overall |
|---|---|---|---|---|---|---|---|---|---|---|
| ledge | Writing | tive | lation | |||||||
| Qwen3.5-397B-A17B | ||||||||||
| Base LLM | 0.644 | 0.408 | 0.381 | 0.420 | 0.438 | 0.433 | 0.393 | 0.396 | 0.386 | 0.446 |
| Full context | 0.519 | 0.594 | 0.573 | 0.543 | 0.624 | 0.585 | 0.599 | 0.548 | 0.565 | 0.569 |
| RAG | 0.436 | 0.481 | 0.453 | 0.462 | 0.486 | 0.470 | 0.437 | 0.450 | 0.474 | 0.460 |
| Rewrite | 0.519 | 0.503 | 0.466 | 0.466 | 0.479 | 0.469 | 0.509 | 0.440 | 0.485 | 0.484 |
| Memory | Qwen3.5-397B-A17B Agent | DeepSeek-V4-Flash-0731 Agent | ||||
|---|---|---|---|---|---|---|
| Base LLM | 0.0895 | 0.2010 | 0.0182 | 0.0833 | 0.1946 | 0.0130 |
| Full context | 0.3382 | 0.5888 | 0.1297 | 0.3119 | 0.5409 | 0.1102 |
| Ground-truth profile | 0.3330 | 0.5888 | 0.1193 | 0.3839 | 0.6316 | 0.1569 |
| RAG | 0.2857 | 0.5391 | 0.0864 | 0.2251 | 0.4705 | 0.0562 |
| Rewrite | 0.3139 | 0.6109 | 0.0700 | 0.3123 | 0.5863 | 0.0869 |
| Qwen3.5-397B-A17B Agent | DeepSeek-V4-Flash-0731 Agent | |||||
| Writer | ||||||
| Base, static | 0.2510 | 0.4620 | 0.0840 | 0.2700 | 0.5040 | 0.0840 |
| Base + request | 0.3410 | 0.5380 | 0.1620 | 0.2897 | 0.5320 | 0.0866 |
| Base + unrelated | 0.1940 | 0.3700 | 0.0610 | 0.2100 | 0.4250 | 0.0600 |
| Trained, static | 0.2640 | 0.4530 | 0.1040 | 0.2480 | 0.4660 | 0.0890 |
| Parent writer | 0.3012 | 0.5214 | 0.1245 | 0.3243 | 0.5499 | 0.1310 |
Appendix figures & tables7 assets
Supplementary material from the paper’s appendix.
Appendix
| Qwen3.5-397B-A17B | DeepSeek-V4-Flash-0731 | |||
| Setting | Accuracy | Generation | Accuracy | Generation |
| HabitusMem (default) | 0.5372 | 0.3257 | 0.4842 | 0.3824 |
| Inference intervention (writer fixed) | ||||
| Without request conditioning | 0.4004 | 0.1345 | 0.3394 | 0.1995 |
| With an unrelated request | 0.4019 | 0.1247 | 0.3376 | 0.1859 |
| Training component removed (retrained) | ||||
| Qwen3.5-397B-A17B | DeepSeek-V4-Flash-0731 | |||
| Writer | Accuracy | Generation | Accuracy | Generation |
| Training lineage | ||||
| Base, static | 0.383 | 0.112 | 0.329 | 0.181 |
| Base + request | 0.393 | 0.146 | 0.345 | 0.211 |
| Base + unrelated | 0.401 | 0.133 | 0.347 | 0.189 |
| Trained, static | 0.406 | 0.135 | 0.335 | 0.200 |
| Factor | Condition | Full, Qwen | Full, DeepSeek | Plain, Qwen |
|---|---|---|---|---|
| Attribution | Self | 10/10 | 10/10 | 10/10 |
| Gift / prior interest | 0/10 | 1/10 | 0/10 | |
| Scope | Unconditional, partner | 10/10 | 10/10 | 10/10 |
| Unconditional, solo | 10/10 | 10/10 | 10/10 | |
| Conditional, partner | 10/10 | 10/10 | 10/10 | |
| Conditional, solo | 10/10 | 2/10 | 7/10 |
LLM Agent Memory
Large language model agent memory lets agents retain, organize, retrieve, and update information across interactions and long-running tasks.
See all 401 papers