# Preprint describes KV-cache compression for GUI agents

_Published Thursday, August 27, 2026 at 7:07 AM EDT · Science, AI · Latest · Tier 2 — Notable_

Researchers introduced ST-Lite, a training-free KV-cache compression method for vision-language GUI agents, in an arXiv preprint. It filters redundant interface frames, retains UI-element boundaries and uses a flat per-layer cache budget. Across seven GUI benchmarks and two backbones, the authors report matching or exceeding full-cache task accuracy on the primary backbone at a 20% budget, with up to 2.35x decoding speedup at fivefold compression. The implementation is linked from the preprint.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2603.00188)

---
Canonical: https://techandbusiness.org/newswire/fncF6h3TtrOSMwduLdmmAA
Published: 2026-08-27T11:07:23.330Z
Story chronology: 2026-08-27T04:00:00.000Z
Retrieved: 2026-10-11T21:47:36.580Z
Publisher: Tech & Business (techandbusiness.org)