Personalized agents that interact with users over long periods must maintain persistent memory across sessions and update it as circumstances change. However, existing benchmarks predominantly frame long-term memory evaluation as fact retrieval from past conversations, providing limited insight into agents' ability to consolidate memory over time or handle frequent knowledge updates. We introduce Memora, a long-term memory benchmark spanning weeks to months long user conversations. The benchmark evaluates three memory-grounded tasks: remembering, reasoning, and recommending. To ensure data quality, we employ automated memory-grounding checks and human evaluation. We further introduce Forgetting-Aware Memory Accuracy (FAMA), a metric that penalizes reliance on obsolete or invalidated memory when evaluating long-term memory. Evaluations of four LLMs and six memory agents reveal frequent reuse of invalid memories and failures to reconcile evolving memories. Memory agents offer marginal improvements, exposing shortcomings in long-term memory for personalized agents.
Harbin Institute of Technology（哈尔滨工业大学）；iFLYTEK Research（科大讯飞研究院）
Deep pretrained language models have achieved great success in the way of pretraining first and then fine-tuning. But such a sequential transfer learning paradigm often confronts the catastrophic forgetting problem and leads to sub-optimal performance. To fine-tune with less forgetting, we propose a recall and learn mechanism, which adopts the idea of multi-task learning and jointly learns pretraining tasks and downstream tasks. Specifically, we propose a Pretraining Simulation mechanism to recall the knowledge from pretraining tasks without data, and an Objective Shifting mechanism to focus t…
RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Peng Cheng Laboratory（鹏城实验室）；Huazhong University of Science and Technology（华中科技大学）；Xiamen University（厦门大学）；The Hong Kong University of Science and Technology, Guangzhou（香港科技大学（广州））；School of Biomedical Engineering, Tsinghua University（清华大学生物医学工程学院）
Personalized Graph-Empowered Large Language Model for Proactive Information Access
Department of Computer Science（计算机科学系）；Information Engineering National Taiwan University Taipei, Taiwan（信息工程国立台湾大学台北市）；Department of Computer Science National Yang Ming Chiao Tung University Hsinchu, Taiwan（计算机科学国立阳明交通大学新竹市）；Institute of Information Science Academia Sinica Taipei, Taiwan（信息科学研究所台湾学术院台北市）；Information Engineering AI Research Center (AINTU) National Taiwan University Taipei, Taiwan（信息工程人工智能研究中心（AINTU）国立台湾大学台北市）
BAPO: Base-Anchored Preference Optimization for Overcoming Forgetting in Large Language Models Personalization
Graduate School of AI, KAIST（韩国科学技术院人工智能研究生院）；Samsung Advanced Institute of Technology（三星先进技术研究院）；Department of Electrical and Computer Engineering, UBC（不列颠哥伦比亚大学电气与计算机工程系）
When Forgetting is not Catastrophic: On the Mechanics of Spurious Forgetting
MPI for Intelligent Systems, Tübingen（马克斯·普朗克智能系统研究所（蒂宾根））；Jinesis Lab, University of Toronto & Vector Institute（Jinesis实验室，多伦多大学与向量研究所）；EuroSafeAI；Hector Foundation（赫克托基金会）；Stanford University（斯坦福大学）；ELLIS Institute Tübingen（ELLIS研究所（蒂宾根））
Embodied Agents Meet Personalization: Investigating Challenges and Solutions Through the Lens of Memory Utilization
Department of Artificial Intelligence, Yonsei University（人工智能系，延世大学）；Department of Computer Science and Engineering, Texas A&M University（计算机科学与工程系，德克萨斯大学）
Time-Incremental Continued Pretraining of LLMs: Knowledge Updates Without Catastrophic Forgetting
Concordia University（康考迪亚大学）；Mila – Quebec AI Institute（米拉-魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）；Laval University（拉瓦尔大学）；University of Tübingen（蒂宾根大学）；Tübingen AI Center（蒂宾根人工智能中心）
Alopex: A Computational Framework for Enabling On-Device Function Calls with LLMs
TensorOpera Inc.（TensorOpera公司）；Stevens Institute of Technology（史蒂文斯理工学院）；University of California, Irvine（加州大学欧文分校）；Hong Kong University of Science and Technology（香港科技大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Forgotten in Weights, Recovered by Tools: Agentic Tool Unlearning for LLM Agents
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；University of Notre Dame（圣母大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；Northwestern University（西北大学）；MIT（麻省理工学院）
Recall Isn't Enough: Bounding Commitments in Personalized Language Systems
OpenAsk；Stern School of Business, New York University（纽约大学 Stern 学院）；Bank of Hebei（河北银行）；Lingnan College, Sun Yat-sen University（中山大学 Lingnan 学院）；School of Economics, Xiamen University（厦门大学 经济学院）；BitMart；Binance
RecGPT: Generative Personalized Prompts for Sequential Recommendation via ChatGPT Training Paradigm
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；Peking University（北京大学）；Kuaishou Technology（快手科技）；Unaffliated（无所属机构）
According to Me: Long-Term Personalized Referential Memory QA
Department of Engineering, University of Cambridge, United Kingdom（剑桥大学工程系）；Department of Physics, University of Cambridge, United Kingdom（剑桥大学物理系）；Independent Researcher（独立研究者）
