infrastructure
The Sandboxes Shared Eight Times More Memory Than Linux Found
AgentZip compressed related agent environments against their common template, then hid much of the restore cost inside the model’s waiting time.
Summary
AgentZip compressed related agent environments against their common template, then hid much of the restore cost inside the model’s waiting time.
High-fanout agent jobs can open many concurrent sandboxes that begin from one template and follow related trajectories, leaving redundancy that ordinary per-page compression misses. AgentZip compresses against the template and across sandboxes, expands the set of pages considered profitable, prefetches restoration, and schedules expensive work during LLM waits. Across the authors’ training and inference workloads, sandbox-owned memory fell by as much as 8.7×, versus 2.1× for the tested Linux configuration. Execution-aware scheduling and prefetching reduced the slowdown of aggressive compression from as high as 3.1× to 1.40×. These are preprint results on the reported workloads, not a universal capacity guarantee.
Why it matters
AgentZip compressed related agent environments against their common template, then hid much of the restore cost inside the model’s waiting time.
Limits and context
- These are preprint results on the reported workloads, not a universal capacity guarantee.
Key claims
AgentZip compressed related agent environments against their common template, then hid much of the restore cost inside the model’s waiting time.
Qualification: These are preprint results on the reported workloads, not a universal capacity guarantee.
Evidence: source-2026-09-12-001
Sources
- arXiv preprint 2609.11294arXiv · primary research
Corrections
No corrections have been recorded for this story.