Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

COMPANY · ENTITY #7629

GUI agents

Related event timeline, sources and context from the news index.

EVENT TIMELINE

3

RESEARCH · 1 SOURCE · arXiv cs.AI

ECHOES: privileged on-policy distillation and recursive textual history compression for long-horizon GUI agents

ECHOES is a method that trains GUI agents to compress visual history into a recursively updated textual state using a Compression-Think-Action (CTA) format. During training a multi-image-input teacher provides dense token-level privileged on-policy distillation to a student model; combined with a PMF-Gap-guided OPD-RL framework and periodic teacher updates, ECHOES improves task performance and memory fidelity without retaining screenshots at deployment and introduces the ECHOESBMK diagnostic benchmark.

6.0

RESEARCH · 1 SOURCE · arXiv cs.AI

Work2Skill: framework, dataset (WorkDemo-350) and method for reusable GUI agent skills (arXiv:2610.12984v1)

The paper introduces Work2Skill, a framework for capturing human desktop GUI experience and inducing reusable agent skills. It presents WorkRecorder for synchronized multimodal collection (screen, mouse/keyboard, accessibility tree), the WorkDemo-350 dataset of 350 screened demonstrations, and an agentic skill-induction method that improves execution model scores versus a No Skill baseline (mean gains 4.67–10.54 on MyPCBench Bounded Action and 3.11–7.50 on a 286-task OSWorld-Verified subset); code and data are on GitHub.

6.0

RESEARCH · 1 SOURCE · arXiv cs.AI

GUI-SD-v2 extends on-policy self-distillation to multi-turn GUI agents

arXiv paper (2609.27307v1) introduces GUI-SD-v2, a two-stage training framework that extends on-policy self-distillation (OPSD) from GUI grounding to multi-turn GUI interaction by jointly optimizing rollouts with and without privileged guidance and selectively distilling step-specific reasoning and memory guidance. The authors report that GUI-SD-v2 improves Pass@1 and Pass@3 over OPSD baselines and evaluated state-of-the-art methods on the AndroidWorld and MobileWorld benchmarks; code and training data are slated for public release.

6.0