1
EASy: Towards Efficient LLM-Based Agentic System
EASy为LLM智能体系统提速增效，直击推理与行动协同的优化痛点
arXiv:2608.04588v1 Announce Type: cross Abstract: Agentic systems have emerged as a promising paradigm for solving complex tasks by coordinating speci…
2
AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems
揭示LLM Agent生态中"蠕虫式"攻击新威胁，安全防护刻不容缓
arXiv:2603.15727v3 Announce Type: replace-cross Abstract: Autonomous LLM-based agents increasingly operate as long-running processes forming densely i…
3
AutoRAS: Learning Robust Agentic Systems with Primitive Representations
用原始表示学习鲁棒智能体系统，ICML 2026 前沿方法带你突破 Agent 稳定性瓶颈。
arXiv:2606.21445v1 Announce Type: new Abstract: The automated design of agentic systems offers a promising pathway for scaling large language models (…
4
From Human Guidance to Autonomy: Agent Skill System for End-to-End LLM Deployment on Spatial NPUs
面向空间NPU的端到端LLM部署，提出Agent技能系统实现从人工指导到自主运行，架构与机器学习协同创新。
arXiv:2606.07586v1 Announce Type: new Abstract: Spatial neural processing units (NPUs) provide an energy-efficient platform for edge LLM inference, bu…
5
Architecting Agentic Communities using Design Patterns
用设计模式为AI社群搭建可复用架构，从模式角度解决多Agent协作的系统化问题。
arXiv:2601.03624v3 Announce Type: replace Abstract: The rapid evolution of Large Language Models (LLM) and subsequent Agentic AI technologies requires…