SE-GA combines Test-Time Memory Extension for dynamic context retrieval with Memory-Augmented Self-Evolution training to reach 89.0% on ScreenSpot and 75.8% on AndroidControl-High.
History-aware reasoning for gui agents
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
HalluClear supplies a taxonomy, calibrated evaluation, and lightweight post-training mitigation that reduces hallucinations in GUI agents using only 9K samples.
citing papers explorer
-
SE-GA: Memory-Augmented Self-Evolution for GUI Agents
SE-GA combines Test-Time Memory Extension for dynamic context retrieval with Memory-Augmented Self-Evolution training to reach 89.0% on ScreenSpot and 75.8% on AndroidControl-High.
-
HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents
HalluClear supplies a taxonomy, calibrated evaluation, and lightweight post-training mitigation that reduces hallucinations in GUI agents using only 9K samples.