cs.AINov 19, 2026

HabitusMem: Belief Memory over Evolving User Preferences for LLM Agents

Authors: Yifan Lu, Gaoyang Guo, Wen Chen, Ziyun Zou, Jian Wu, Han Zhu, Imran Razzak

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 Such content does not indicate whether a preference is still current or where it applies, so agents often act on outdated or misapplied preferences.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

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. QUMem: Personalized Memory for Query-Conditioned User-State Inference in LLM Agents

    Aug 17, 2026Heng Wang, Yifei Li, Lingling Zhang +4Long-Term Conversational MemoryAgent Memory Management

  2. Know It, Act on It: Investigating Memory Utilization in LLM Personalization

    Jul 31, 2026Zhaoxin Feng, Jianfei Ma, Emmanuele ChersoniLLM PersonalizationLLM Agent Memory

  3. HABIT-Bench: Evaluating Habit Induction from Longitudinal Weak Evidence in Agent Memory

    Oct 17, 2026Junming Zhang, Rubin Wei, Xu Cheng +7LLM Agent MemoryMemory Agent Benchmarks