# Preprint describes KV-cache compression for GUI agents

_Thursday, August 27, 2026 at 12:00 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
Retrieved: 2026-08-27T12:50:43.809Z
Publisher: Tech & Business (techandbusiness.org)