On BrowseComp-Plus, GPT-4.1 answered 93.49% of the questions correctly when it was given the supporting documents directly. When an agent The post Agentic AI doesn’t have a model problem. It has a retrieval problem. appeared first on The New Stack.
Agentic AI doesn’t have a model problem. It has a retrieval problem.
On BrowseComp-Plus, GPT-4.1 answered 93.49% of the questions correctly when it was given the supporting documents direct...
By Dhallo News · October 15, 2026 at 5:30 PM IST

Source: The New Stack
Have feedback on this article?Report error or suggestion
