让消费级显卡运行百万智能体，靠异步内存分离技术。
Warp-Cortex: An Asynchronous, Memory-Efficient Architecture for Million-Agent Cognitive Scaling on Consumer Hardware
- 用拓扑思维重构记忆结构，将内存复杂度从线性降至常数。
- 单张4090显卡支持100个智能体，总显存仅2.2GB。
- 适合想在普通电脑上跑大规模多智能体系统的开发者。
当前多智能体大语言模型框架存在内存线性增长问题，导致消费级硬件无法实现并行推理。本文提出Warp Cortex异步架构，通过解耦智能体逻辑与物理内存，理论上实现百万智能体认知扩展。利用单一权重共享和受拓扑数据分析启发的拓扑突触机制，将权重内存复杂度从O(N * L)降至O(1)，上下文内存降至O(N * k)，其中k << L。将键值缓存视为潜在空间中的点云，采用基于威森复形的稀疏化方法，保留上下文流形的持久同调特征。在单张NVIDIA RTX 4090上，实测证明可支持100个并发智能体，总显存仅2.2 GB，理论容量超过1000个智能体，直至计算延迟成为瓶颈。此外提出参照注入机制，无需干扰主生成流程即可实现子智能体对主生成的异步影响。
原文摘要 · Abstract (English)
Current multi-agent Large Language Model (LLM) frameworks suffer from linear memory scaling, rendering "System 2" parallel reasoning impractical on consumer hardware. We present Warp Cortex, an asynchronous architecture that theoretically enables million-agent cognitive scaling by decoupling agent logic from physical memory. Through Singleton Weight Sharing and a novel Topological Synapse--inspired by hybrid landmarking techniques from Topological Data Analysis (TDA)--we reduce memory complexity from O(N * L) to O(1) for weights and O(N * k) for context, where k << L. By treating the KV-cache as a point cloud in latent space, we apply witness-complex-inspired sparsification to preserve persistent homological features of the context manifold. On a single NVIDIA RTX 4090, we empirically demonstrate 100 concurrent agents at 2.2 GB total VRAM, with theoretical capacity exceeding 1,000 agents before compute latency becomes the bottleneck. We further introduce Referential Injection, a non-intrusive KV-cache update mechanism that allows asynchronous sub-agents to influence primary generation without stream disruption.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。