cs.AINov 10, 2026

Personalized Memory Rubrics: Learning What to Remember per User via Rubric-Guided Credit Assignment

Authors: Yupeng Han, Kai Zhang, Shuochen Liu, Ze Liu, Xianquan Wang, Zhihong Pan, Xiangyu Zhao, Qi Liu, 

Organizations: University of Science and Technology of China & City University of Hong Kong & State Key Laboratory of Cognitive Intelligence · University of Science and Technology of China & State Key Laboratory of Cognitive Intelligence · City University of Hong Kong

Abstract

Long-horizon personalized agents maintain an evolving memory by continuously deciding what to add, modify, or discard. However, learning an optimal update policy remains challenging. Conventional training relies solely on terminal question-answering accuracy, yielding a coarse feedback signal that treats all intermediate updates identically. Furthermore, update utility is inherently user-specific, as identical memory actions may yield opposite effects across different user personas. Existing methods fail to address this heterogeneity, relying on globally shared evaluation standards with at most a single scalar intermediate reward. To address these challenges, we propose Personalized Memory Rubrics (PMR), a framework that translates terminal feedback into fine-grained, per-step, and per-user credit assignment. PMR decomposes evaluation into a universal layer capturing cross-persona failure patterns and a per-user adaptive layer modeling individual traits as a specialized delta over the universal baseline. Through Rubric-Guided Credit Assignment, PMR redistributes credit at the token level, selectively amplifying validated decisions on successful trajectories while falling back to standard policy optimization on failed ones to avoid unreliable attribution. The rubric and memory policy co-evolve in a closed loop with anti-circularity guarantees. Crucially, PMR incurs zero inference overhead, operating without any rubric or external judge during deployment. Extensive experiments across four benchmarks demonstrate consistent gains over strong memory-augmented baselines.

Figures & tables

Explore similar work

CardsList
  1. Learning What to Share and What to Personalize: Hierarchical Strategy Co-Evolution for Agent Memory

    Aug 26, 2026Yupeng Han, Shuochen Liu, Kai Zhang +3Agent Memory ManagementMemory-Augmented Language Model Agents

  2. Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory

    May 1, 2026Derong Xu, Shuochen Liu, Pengfei Luo +8Memorization in Language ModelsMemorization in Generative Models