Agentic AI doesn’t have a model problem. It has a retrieval problem.

T2Covered by 1 source · first reported by The New Stack at 15 Oct, 12:00 UTC

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.

dev

Sources

• T2Agentic AI doesn’t have a model problem. It has a retrieval problem.The New Stack15 Oct, 12:00