Key papers

• ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU (2026)
  Fan Jiang et al.
  17.67
• Metis: Memory Foundation Model (2026)
  Zeyu Zhang et al.
  17.36
• EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments (2026)
  Jundong Xu et al.
  15.90
• Memory for Large Language Models (2026)
  Sining Zhoubian et al.
  15.65
• AREX: Towards a Recursively Self-Improving Agent for Deep Research (2026)
  Shuqi Lu et al.
  15.64
• LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget (2026)
  Changhai Zhou et al.
  15.54
• MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent (2025)
  Hongli Yu et al.
  15.26
• MiniMax Sparse Attention (2026)
  Xunhao Lai et al.
  13.89
• ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory (2026)
  Jiayi Tian et al.
  13.83
• UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning (2026)
  Niu Lian et al.
  13.34
• SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD (2026)
  Dongfang Li et al.
  13.27
• Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application (2026)
  Jiachun Li et al.
  13.11
• AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents (2026)
  Xiangchen Cheng et al.
  12.98
• FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention (2026)
  Yan Wang et al.
  12.81
• AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report (2026)
  AlayaWorld Team et al.
  12.74
• SWE-Pruner Pro: The Coder LLM Already Knows What to Prune (2026)
  Yuhang Wang et al.
  12.73
• From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI (2026)
  Yongheng Zhang et al.
  12.64
• COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation (2026)
  Tianyi Zhou et al.
  12.59
• LightMem-Ego: Your AI Memory for Everyday Life (2026)
  Yijun Chen et al.
  12.31
• LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards (2026)
  Nianyi Lin et al.
  12.09
• KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill (2026)
  Yunxin Li et al.
  12.06
• Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning (2026)
  Shiding Zhu et al.
  11.76
• Qwen3 Technical Report (2025)
  An Yang, Anfeng Li, Baosong Yang, et al.
  11.70
• AutoMem: Automated Learning of Memory as a Cognitive Skill (2026)
  Shengguang Wu et al.
  11.65
• Latent Collaboration in Multi-Agent Systems (2025)
  Jiaru Zou et al.
  11.55
• Rethinking Memory as Continuously Evolving Connectivity (2026)
  Jizhan Fang et al.
  11.38
• Personal AI Agent for Camera Roll VQA (2026)
  Thao Nguyen et al.
  11.34
• MemSyco-Bench: Benchmarking Sycophancy in Agent Memory (2026)
  Zhishang Xiang et al.
  11.33
• Keep It InMind: Benchmarking the Implicit-Association Blind Spot in Agent Memory (2026)
  Ruizhe Li et al.
  11.33
• Sample-Efficient Learning from Agent Experience (2026)
  Chenhui Gou et al.
  11.17
• VisualClaw: A Real-Time, Personalized Agent for the Physical World (2026)
  Haoqin Tu et al.
  11.11
• Agent-as-a-Router: Agentic Model Routing for Coding Tasks (2026)
  Pengfei Zhou et al.
  11.10
• Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems (2026)
  Gaurav Dadhich
  11.07
• SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning (2026)
  Peng Xia et al.
  11.00
• Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses (2026)
  Pengcheng Jiang et al.
  10.97
• HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry (2026)
  Tingyang Chen et al.
  10.97
• NVIDIA-labs OO Agents: Native Python Object-Oriented Agents (2026)
  Paul Furgale et al.
  10.76
• Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents (2026)
  Ziyan Liu et al.
  10.68
• SkillGrad: Optimizing Agent Skills Like Gradient Descent (2026)
  Hanyu Wang et al.
  10.66
• Rethinking Continual Experience Internalization for Self-Evolving LLM Agents (2026)
  Jingwen Chen et al.
  10.60
• MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery (2026)
  Shangheng Du et al.
  10.60
• OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation (2026)
  Guibin Zhang et al.
  10.48
• CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery (2026)
  Ao Qu et al.
  10.43
• Self-Improvements in Modern Agentic Systems: A Survey (2026)
  Zhe Ren et al.
  10.37
• Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning (2026)
  Jiapeng Zhu et al.
  10.31
• SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills (2026)
  Yingtie Lei et al.
  10.18
• TokenPilot: Cache-Efficient Context Management for LLM Agents (2026)
  Buqiang Xu et al.
  10.10
• Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents (2026)
  Minhua Lin et al.
  10.04
• EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery (2026)
  Yougang Lyu et al.
  9.94
• Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability (2026)
  Sizhe Zhou et al.
  9.91
• Smarter and Cheaper at Once: Byte-Exact KV-Cache Grafting Turns a Frozen Small Model into a Verified-Knowledge Flywheel (2026)
  Sietse Schelpe
  9.90
• Metacognition in LLMs: Foundations, Progress, and Opportunities (2026)
  Gabrielle Kaili-May Liu et al.
  9.89
• $\Sigma$-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems (2026)
  Peilin Feng et al.
  9.84
• Xiaomi-GUI-0 Technical Report (2026)
  Wanxia Cao et al.
  9.79
• Voice Memory for Agentic Speech Recognition (2026)
  Chao-Han Huck Yang et al.
  9.68
• Joint Agent Memory and Exploration Learning via Novelty Signals (2026)
  Shizuo Tian et al.
  9.62
• Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams (2026)
  Zewen Liu et al.
  9.62
• SubtleMemory: A Benchmark for Fine-Grained Relational Memory Discrimination in Long-Horizon AI Agents (2026)
  Wenxuan Wang et al.
  9.62
• MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation (2026)
  Huawei Lin et al.
  9.55
• Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE (2026)
  Haozhan Tang et al.
  9.54