GTA-2 benchmark shows frontier models achieve below 50% on atomic tool tasks and only 14.39% success on realistic long-horizon workflows, with execution harnesses like Manus providing substantial gains.
Navigating the digital world as humans do: Universal visual grounding for gui agents
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
BAMI mitigates precision and ambiguity biases in GUI grounding via coarse-to-fine focus and candidate selection, raising accuracy on ScreenSpot-Pro without training.
HalluClear supplies a taxonomy, calibrated evaluation, and lightweight post-training mitigation that reduces hallucinations in GUI agents using only 9K samples.
citing papers explorer
-
GTA-2: Benchmarking General Tool Agents from Atomic Tool-Use to Open-Ended Workflows
GTA-2 benchmark shows frontier models achieve below 50% on atomic tool tasks and only 14.39% success on realistic long-horizon workflows, with execution harnesses like Manus providing substantial gains.
-
BAMI: Training-Free Bias Mitigation in GUI Grounding
BAMI mitigates precision and ambiguity biases in GUI grounding via coarse-to-fine focus and candidate selection, raising accuracy on ScreenSpot-Pro without training.
-
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.