Awesome Memory

Key papers

• EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments (2026)
  Jundong Xu et al.
  16.01
• MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent (2025)
  Hongli Yu et al.
  15.38
• MiniMax Sparse Attention (2026)
  Xunhao Lai et al.
  14.00
• Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application (2026)
  Jiachun Li et al.
  13.22
• From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI (2026)
  Yongheng Zhang et al.
  12.75
• COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation (2026)
  Tianyi Zhou et al.
  12.70
• LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards (2026)
  Nianyi Lin et al.
  12.21
• HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry (2026)
  Tingyang Chen et al.
  11.97
• Latent Collaboration in Multi-Agent Systems (2025)
  Jiaru Zou et al.
  11.66
• Rethinking Memory as Continuously Evolving Connectivity (2026)
  Jizhan Fang et al.
  11.49
• Personal AI Agent for Camera Roll VQA (2026)
  Thao Nguyen et al.
  11.45
• TokenPilot: Cache-Efficient Context Management for LLM Agents (2026)
  Buqiang Xu et al.
  11.32
• VisualClaw: A Real-Time, Personalized Agent for the Physical World (2026)
  Haoqin Tu et al.
  11.22
• SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning (2026)
  Peng Xia et al.
  11.12
• Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses (2026)
  Pengcheng Jiang et al.
  11.09
• Qwen3 Technical Report (2025)
  An Yang, Anfeng Li, Baosong Yang, et al.
  11.05
• SkillGrad: Optimizing Agent Skills Like Gradient Descent (2026)
  Hanyu Wang et al.
  10.77
• Rethinking Continual Experience Internalization for Self-Evolving LLM Agents (2026)
  Jingwen Chen et al.
  10.72
• CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery (2026)
  Ao Qu et al.
  10.54
• Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning (2026)
  Jiapeng Zhu et al.
  10.42
• OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation (2026)
  Guibin Zhang et al.
  10.25
• AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing (2026)
  Jisong Cai et al.
  10.21
• Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents (2026)
  Minhua Lin et al.
  10.15
• Joint Agent Memory and Exploration Learning via Novelty Signals (2026)
  Shizuo Tian et al.
  9.73
• SubtleMemory: A Benchmark for Fine-Grained Relational Memory Discrimination in Long-Horizon AI Agents (2026)
  Wenxuan Wang et al.
  9.73
• MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation (2026)
  Huawei Lin et al.
  9.66
• Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization (2026)
  Zeyuan Liu et al.
  9.60
• TIDE: Trajectory-based Diagnostic Evaluation of Test-Time Improvement in LLM Agents (2026)
  Hang Yan et al.
  9.48
• WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction (2026)
  Chengzhi Liu et al.
  9.43
• Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents (2026)
  Haoyi Hu et al.
  9.41
• Mem-$\pi$: Adaptive Memory through Learning When and What to Generate (2026)
  Xiaoqiang Wang et al.
  9.29
• Reasoning Under 1 Billion: Memory-Augmented Reinforcement Learning for Large Language Models (2025)
  Hung Le et al.
  9.17
• Omni-simplemem: Autoresearch-guided Discovery Of Lifelong Multimodal Agent Memory (2026)
  Jiaqi Liu, Zipeng Ling, Shi Qiu, et al.
  9.02
• OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent (2026)
  Bowen Yang et al.
  8.96
• Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory (2026)
  Haozhen Zhang et al.
  8.94
• MemTrain: Self-Supervised Context Memory Training (2026)
  Ziheng Li et al.
  8.87
• ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning (2025)
  Shu Zhao et al.
  8.67
• SEDM: Scalable Self-Evolving Distributed Memory for Agents (2025)
  Haoran Xu et al.
  8.67
• Stateful Visual Encoders for Vision-Language Models (2026)
  Zirui Wang et al.
  8.57
• Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents (2026)
  Ziyan Liu et al.
  8.53
• Hogwild! Inference: Parallel LLM Generation via Concurrent Attention (2025)
  Gleb Rodionov et al.
  8.39
• Next Embedding Prediction Makes World Models Stronger (2026)
  George Bredis et al.
  8.38
• Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning (2025)
  Tong Wu et al.
  8.35
• Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents (2026)
  Chongrui Ye et al.
  8.17
• EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery (2026)
  Yougang Lyu et al.
  7.79
• MemoTime: Memory-Augmented Temporal Knowledge Graph Enhanced Large Language Model Reasoning (2025)
  Xingyu Tan et al.
  7.63
• See What I See, Know What I Think: Dense Latent Communication Across Heterogeneous Agents (2026)
  Siyi Chen et al.
  7.37
• From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms (2026)
  Jing Luo et al.
  7.30
• Tangram: Unlocking Non-Uniform KV Cache Compression for Efficient Multi-turn LLM Serving (2026)
  Hyungmin Kim et al.
  6.95
• AURA: Action-Gated Memory for Robot Policies at Constant VRAM (2026)
  Josef Chen
  6.75
• Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory (2026)
  Haoran Sun et al.
  6.75
• A History-Aware Visually Grounded Critic for Computer Use Agents (2026)
  Jaewoo Lee et al.
  6.75
• Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations (2026)
  Dongming Jiang et al.
  6.73
• SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent (2026)
  Yuyang Hu et al.
  6.69
• Agentic Uncertainty Quantification (2026)
  Jiaxin Zhang et al.
  6.67
• Agent4Edu: Generating Learner Response Data by Generative Agents for Intelligent Education Systems (2025)
  Weibo Gao et al.
  6.58
• Synergistic Multi-agent Framework With Trajectory Learning For Knowledge-intensive Tasks (2024)
  Shengbin Yue, Siyuan Wang, Wei Chen, et al.
  6.56
• Autonomous LLM Agent: A Memory-Augmented, Edge-Optimized SHAP Explanations With Zero-Day Attack Resilience in IoT/Industrial IoT Networks (2026)
  Y. Saheed et al.
  6.52
• Position: Agentic Evolution is the Path to Evolving LLMs (2026)
  Minhua Lin et al.
  6.25
• UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization (2026)
  Zhengxi Lu et al.
  6.07