Evidence · DiggingBeagle record
VeriCUA: Verification as Agentic Exploration for Computer-Using Agents
The paper reports 90.5 percent AndroidWorld verification accuracy for VeriCUA versus 78.4 percent for a vision-language judge, with VeriCUA deciding on 82 percent of that sample.
- Source role
- primary disclosure
Evidence record
The paper reports 90.5 percent AndroidWorld verification accuracy for VeriCUA versus 78.4 percent for a vision-language judge, with VeriCUA deciding on 82 percent of that sample.
Claim-level citations (2)
- supportsVeriCUA verifies computer-using agents by exploring state instead of trusting screenshots: The paper reports 90.5 percent AndroidWorld verification accuracy for VeriCUA versus 78.4 percent for a vision-language judge, with VeriCUA deciding on 82 percent of that sample.
Method: Evidence Discipline; Online Verification and Experiments, Table 1
- supportsVeriCUA verifies computer-using agents by exploring state instead of trusting screenshots: In the authors' AndroidWorld online evaluation, VeriCUA reached 90.5 percent overall accuracy with an 82 percent decision rate, versus 78.4 percent accuracy with 100 percent decisions for the VLM judge.
Online Verification, Table 1, AndroidWorld accuracy and decision rates