Memory-Augmented Agents

Follow this topic Ask about this topic

Memory-augmented agents study how AI systems can retain and use information beyond the current prompt or observation, helping them handle long tasks, partial observability, and changing user or world states. Approaches range from episodic, semantic, and procedural stores—often organized as graphs, event records, or compressed visual and action histories—to learned policies that decide what to write, retrieve, update, or forget. Work spans embodied control and navigation, GUI and web use, dialogue, coding, and research, with evaluations including RoboMemArena, RoboMME, GOAT-Bench, LongMemEval, and software-engineering benchmarks. A central tension is that more memory can improve transfer and continuity but also introduce stale or misleading evidence, interference, cost, privacy leaks, and persistent attacks, making selective retrieval and longitudinal safety evaluation important open problems.

Latest papers

349 papers64 papers in the last four weeks, up 60% on the four weeks before. 0.4% of all new papers.

ORACLE: Anticipating Scams from Partial Trajectories in Streaming App Usage
May 9, 2026Wenbo Gao, Songbai Tan, Zhongan Wang +6Online Anomaly Detection Financial Fraud Detection
Harbin Institute of Technology, Shenzhen · Shenzhen University · Zhejiang University +4
ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts
May 9, 2026Yang Luo, Zifeng Kang, Tiantian Ji +4Agent Memory Poisoning Graph-Based Agent Memory
Key Laboratory of Trustworthy Distributed Computing and Service (MoE), Beijing University of Posts and Telecommunications · Beijing University of Posts and Telecommunications · Zhongguancun Laboratory
Ace-Skill: Bootstrapping Multimodal Agents with Prioritized and Clustered Evolution
May 9, 2026Feng Xiong, Zengbin Wang, Yong Wang +5Continual Learning for LLM Agents Agent Skill Learning
1AMAP, Alibaba Group · 2CASIA · 3BNU
GASim: A Graph-Accelerated Hybrid Framework for Social Simulation
May 8, 2026Xuan Zhou, Yanhui Sun, Hantao Yao +3Multi-Agent LLM Systems Human Behavior Simulation
University of Science and Technology of China · BASIS International School Park Lane Harbour
MemCompiler: Compile, Don't Inject -- State-Conditioned Memory for Embodied Agents
May 8, 2026Xin Ding, Xinrui Wang, Yifan Yang +9Embodied AI Memory-Augmented Agents
University of Science and Technology of China · Huazhong University of Science and Technology · Microsoft Research +2
X-OmniClaw Technical Report: A Unified Mobile Agent for Multimodal Understanding and Interaction
May 7, 2026Xiaoming Ren, Ru Zhen, Chao Li +11Multimodal Grounding GUI Agents
Multi-X Team, OPPO AI Center
From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms
May 7, 2026Jinghao Luo, Yuchen Tian, Chuxue Cao +6Continual Learning for LLM Agents LLM Agent Memory
2South China Normal University · 1Hong Kong Baptist University · 3Hong Kong University of Science and Technology +2
Trojan Hippo Bench: A Dynamic Benchmark for Persistent Memory Attacks and Defenses in LLM Agents
May 3, 2026Debeshee Das, Julien Piet, Darya Kaviani +3LLM Agent Security AI Agent Security Benchmarks
ETH Zürich · UC Berkeley · Snyk
Feedback-Normalized Developer Memory for Reinforcement-Learning Coding Agents: A Safety-Gated MCP Architecture
May 2, 2026Mehmet IscanMemory-Augmented Agents Agent Memory Management
PythaLab, Yildiz Technical University, Istanbul, Türkiye
ZenBrain: A Neuroscience-Inspired 7-Layer Memory Architecture for Autonomous AI Systems
Apr 26, 2026Alexander BeringMemorization in Language Models Neural Processes
Zensation AI
Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents
Apr 22, 2026Yuxuan Cai, Wei Li, Jie Zhou +4Lifelong Learning Agents LLM Agent Skill Learning
School of Computer Science and Technology, East China Normal University, Shanghai · Shanghai AI Laboratory
FSFM: A Biologically-Inspired Framework for Selective Forgetting of Agent Memory
Apr 22, 2026Yingjie Gu, Wenjian Xiong, Liqiang Wang +7LLM Agent Security Memory-Augmented Agents
China Mobile Digital Intelligence Business Unit | China Mobile Jiutian Company | China Mobile Jiutian Research Institute
Revac: A Social Deduction Reasoning Agent
Apr 21, 2026Mihir Shriniwas Arya, Avinash Anish, Aditya RanjanGame-Playing Agents Social Deduction Games
Department of Computer Science and Engineering RV College of Engineering Bangalore · Department of Information Science and Engineering RV College of Engineering Bangalore · Department of Artificial Intelligence and Machine Learning RV College of Engineering Bangalore
Four-Axis Decision Alignment for Long-Horizon Enterprise AI Agents
Apr 21, 2026Vasundra SrininvasanLong-Horizon Agent Evaluation AI Agent Benchmarks
Stanford School of Engineering
Forage V2: Knowledge Evolution and Transfer in Autonomous Agent Organizations
Apr 21, 2026Huaqing XieLLM Agent Evaluation Memory-Augmented Agents
Independent Researcher
Explore Like Humans: Autonomous Exploration with Online SG-Memo Construction for Embodied Agents
Apr 21, 2026Xu Chen, Shichao Xie, Zhining Gu +7Embodied Navigation Semantic Mapping
Amap, Alibaba Group, China.
Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game
Apr 21, 2026HuaDong Jian, Chenghao Li, Haoyu Wang +4Multi-Agent LLM Systems Multi-Agent Collaboration
University of Electronic Science and Technology of China Chengdu, China
Gated Memory Policy
Apr 21, 2026Yihuai Gao, Jinyun Liu, Shuang Li +1Sequential Decision Making Visuomotor Policy Learning
Stanford University
Memory Centric Power Allocation for Multi-Agent Embodied Question Answering
Apr 20, 2026Chengyang Li, Shuai Wang, Kejiang Ye +5Embodied QA Wireless Resource Allocation
Department of Electrical and Computer Engineering, The University of Hong Kong, Hong Kong · Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China · Southern University of Science and Technology, Shenzhen, China +2
Long-Term Memory for VLA-based Agents in Open-World Task Execution
Apr 17, 2026Xu Huang, Weixin Mao, Yinhao Li +2Agent Memory Long-Horizon Robotic Manipulation
Nanjing University · LimX Dynamics
Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents
Apr 15, 2026Kangsan Kim, Minki Kang, Taeil Kim +3Memory-Augmented Agents Cross-Domain Transfer Learning
KAIST · New York University
Toward Autonomous Long-Horizon Engineering for ML Research
Apr 14, 2026Guoxin Chen, Jie Chen, Lei Chen +7Long-Horizon LLM Agents Multi-Agent LLM Systems
OVAL: Open-Vocabulary Augmented Memory Model for Lifelong Object Goal Navigation
Apr 14, 2026Jiahua Pei, Yi Liu, Guoping Pan +3Object-Goal Navigation Open-Vocabulary Object Navigation
Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China
MolMem: Memory-Augmented Agentic Reinforcement Learning for Sample-Efficient Molecular Optimization
Apr 14, 2026Ziqing Wang, Yibo Wen, Abhishek Pandy +2Molecular Optimization Sample-Efficient RL
Northwestern University · AbbVie
M2HRI: An LLM-Driven Multimodal Multi-Agent Framework for Personalized Human-Robot Interaction
Apr 13, 2026Shaid Hasan, Breenice Lee, Sujan Sarker +1Multi-Agent LLM Systems Multi-Agent Coordination
University of Virginia, VA, USA
ABot-Claw: A Foundation for Persistent, Cooperative, and Self-Evolving Robotic Agents
Apr 11, 2026Dongjie Huo, Haoyun Liu, Guoqing Liu +10Self-Evolving Agents Language-Conditioned Robot Control
AMAP CV Lab Alibaba Group
Artifacts as Memory Beyond the Agent Boundary
Apr 9, 2026John D. Martin, Fraser Mince, Esra'a Saleh +1Memory-Augmented Agents Reinforcement Learning
Openmind Research Institute · University of Alberta · Cohere Labs Community +3
SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents
Apr 9, 2026Xinshun Feng, Xinhao Song, Lijun Li +2Self-Evolving Agents Memory-Augmented Agents
Shanghai Artificial Intelligence Laboratory · Shanghai Jiaotong University
Event-Centric World Modeling with Memory-Augmented Retrieval for Embodied Decision-Making
Apr 8, 2026Zhaowen Fan, Rongchao Zhang, Yunxiang HanCase-Based Reasoning Embodied Navigation
School of Computer Science, Sichuan University, Chengdu 610065, China
ActionNex: A Virtual Outage Manager for Cloud Computing
Apr 3, 2026Zhenfeng Lin, Haoji Hu, Ming Hao +11AI-Assisted Decision Making Next-Action Prediction
Microsoft PRIMO, Redmond, USA · Microsoft Azure Core, Redmond, USA · Microsoft Azure CTO Office, Redmond, USA +1

May 9, 2026J/K move · Enter open · S save

ORACLE: Anticipating Scams from Partial Trajectories in Streaming App Usage

Wenbo Gao, Songbai Tan, Zhongan Wang, Fei Shen+5

Harbin Institute of Technology, Shenzhen · Shenzhen University · Zhejiang University+4

Online Anomaly Detection Financial Fraud Detection Memory-Augmented Agents Anomaly Detection Early Warning Detection

Open paper AskPDF arXiv

Smartphone scams are increasingly prevalent and typically manifest as multi-stage, cross-application processes with gradually emerging intent. Effective intervention thus requires anticipating scams before the intent becomes explicit. This is inherently challenging, as decisions must rely on partial trajectories with temporally distributed evidence. In this paper, we propose ORACLE Online Reasoning for Anticipating Cross-temporal Latent thrEats, the first agentic framework for early scam anticipation from streaming app-usage trajectories. To support this setting, we curate a real-world long-horizon benchmark of streaming app-usage trajectories, covering 12 scam types, spanning extended periods (15 days on average), involving diverse applications (95 apps), and interleaving normal and scam behaviors. To address fragmented evidence, we introduce a self-evolving context manager that adaptively consolidates entity-centric interactions over time, enabling more effective reconstruction of cross-temporal evidence from partial observations. To enhance sensitivity to latent early-stage signals, we propose an on-policy self-distillation scheme in which a teacher model, conditioned on summarized anti-scam reflections and clues by skills, supervises a student model without access to such reflections. This scheme thereby distills evidence-informed knowledge and improves recognition of emerging fraud patterns from partial trajectories. Experiments show that \method{} consistently improves early scam anticipation, yielding timely warnings while reducing false alerts in realistic streaming scenarios.