HKUST 研究人员提出 AgentZip，通过压缩冗余内存提升多代理沙盒效率
Very cool paper on memory compression for agents. If you run many agent sandboxes in parallel for R...
朋友，HKUST 的研究团队搞了个叫 AgentZip 的东西，专门解决多代理沙盒内存占用过高的问题，能把内存压缩到原来的 1/8.7，比 Linux 的 2.1 倍压缩效果更好。
这篇论文提出了一种名为 AgentZip 的方法，用于压缩多代理沙盒中高度冗余的内存。当运行许多并行沙盒时，内存变得非常冗余，压缩这些冗余可以减少沙盒内存使用量，最高可达 8.7 倍。该方法通过压缩与模板和兄弟沙盒相关的页面来实现，包括相似但不完全相同的页面。它会在代理等待 LLM 时运行昂贵的压缩，并在恢复时预取页面以控制速度下降。
Very cool paper on memory compression for agents. If you run many agent sandboxes in parallel for R...
Very cool paper on memory compression for agents. If you run many agent sandboxes in parallel for RL or evals, memory becomes highly redundant. This work suggests that compressing against that redundancy cuts sandbox memory by up to 8.7x. Memory is becoming the capacity limit for high-fanout agent workloads. One task can spawn many concurrent sandboxes, and they all start from the same template and run related trajectories. HKUST researchers measured 76 to 96% of pages with template-relative or cross-sandbox redundancy. AgentZip compresses pages against the template and against sibling sandboxes, including pages that are similar without being identical. It runs expensive compression while the agent is waiting on the LLM, and it prefetches pages at restore time to control slowdown. Results: Sandbox-owned memory drops by up to 8.7x, against 2.1x for the Linux configuration. Aggressive compression slows execution by 3.1x on its own, and the scheduling and prefetching bring that down to 1.40x. Paper: arxiv.org/abs/2609.11294 Chat with Paper: academy.dair.ai/papers/memory-… 💬 15 🔄 6 ❤️ 41 👀 4151 📊 24 ⚡
