Unverified50% confidenceFactExact time
The research team conducted experimental validation on five widely used GUI agents.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
Unverified尼尔森诺曼集团的研究表明，大多数可用性问题在5名测试用户后就能被发现71% similarUnverifiedThe research team systematically tested StochBench using an agent based on Opus 4.8.70% similarUnverifiedThe research team used the Llama-3.1-8B-Instruct model as the experimental subject, examining probe generalization performance on 3 held-out deception detection datasets.68% similarUnverifiedThe research team conducted extensive evaluations using multiple agent frameworks on both proprietary models and open-weight models; state-of-the-art models such as GLM-5.2 and Claude-Sonnet-4.6 achieved only slightly above passing performance.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/898616API
curl https://kongchang.com/api/v1/knowledge/claims/898616MCP
get_claim(id=898616)