EvoGUI: An Evolution-Aware Benchmark for GUI State-Transition Understanding
GUI agents must reason about how actions transform interface states, but end-to-end success rates entangle this ability with perception, grounding, planning, and recovery. We introduce EvoGUI, a diagnostic framework that converts normalized GUI trajectories into three complementary visual question answering probes: temporal ordering, inverse action/value prediction, and contrastive one-step successor discrimination. Their labels are derived from trajectory order and logged actions, requiring no additional task-label annotation after trajectory normalization. We instantiate EvoGUI-Bench from Mi
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzyOverlapping authors or contributors · 62%sgl-project/sglang →
“Shared author/contributor keys: zhou”
- FuzzySimilar title/name (fuzzy) · 59%jeinlee1991/chinese-llm-benchmark →
“Fuzzy title match (0.73): “EvoGUI: An Evolution-Aware Benchmark for GUI State-Transitio” ≈ “jeinlee1991/chinese-llm-benchmark””
- LinkedLinked via arxiv author · 85%Yaohan Yang →
“EvoGUI: An Evolution-Aware Benchmark for GUI State-Transition Understanding”
- LinkedLinked via arxiv author · 85%Minglei Shi →
“EvoGUI: An Evolution-Aware Benchmark for GUI State-Transition Understanding”
- LinkedLinked via arxiv author · 85%Borui Zhang →
“EvoGUI: An Evolution-Aware Benchmark for GUI State-Transition Understanding”
- LinkedLinked via arxiv author · 85%Jie Zhou →
“EvoGUI: An Evolution-Aware Benchmark for GUI State-Transition Understanding”
- LinkedLinked via arxiv author · 85%Jiwen Lu →
“EvoGUI: An Evolution-Aware Benchmark for GUI State-Transition Understanding”