Tag
该论文研究了边缘设备上小型 LLM 智能体在长对话与重人设上下文中的"人设-逻辑干扰"问题，并提出解耦架构 AO-DA，将逻辑推理与人设表达分离到两条推理路径，实验证明解耦后的逻辑路径在上下文污染下保持结构不变性。
Monday.com's Sidekick AI agent transitioned from a multi-agent architecture (200+ tools) to a deep agent architecture, solving context pollution and cost issues through three-layer tool discovery, priority delegation, code writing, and self-healing mechanisms.