benchmark 1environment state verification 1gui automation 1reinforcement learning 1task evaluation 1
From the 1 of 3 linked papers with an AI index.
Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Interactive Reward Agent: GUI Task Evaluation via Environment-State Verification
Chenrui Shi, Yuwei Wu, Yang Liu +5
The paper introduces an Interactive Reward Agent that evaluates GUI task completion by proposing conditions and verifying them using system, application, and GUI tools, and demonst…
cs.AI2026
GUI Knowledge Bench: Revealing the Knowledge Gap of VLMs in GUI Tasks
Chenrui Shi, Zedong Yu, Zhi Gao +7
Vision language models (VLMs) have advanced graphical user interface (GUI) task automation but still lag behind humans. We hypothesize this gap stems from missing core GUI knowledg…