AI search agents don't fail at searching, they fail at asking the right questions when queries get ambiguous

Summary

AI search agents rarely fail at multi-step research because of the search itself. Their real problem is not asking the user for clarification when queries are ambiguous. A new benchmark called DiscoBench shows that models searching repeatedly instead of asking follow-up questions actually perform worse, at 51.9 percent, than those that just guess. Even the best model only hits 43 percent overall accuracy. When ambiguity is removed from the queries, accuracy jumps by up to 40 points. The article

SpinGraph analysis pending — check back after processing.

• Mistral CEO Mensch says proprietary AI models give labs a front-row seat to your business processes
• AI private schools sell wealthy US families on personalized learning over traditional education
• Hollywood wants Seedance banned and reportedly also wants to keep using it
• Open-source tool pxpipe hides text in PNGs to cut Claude Code and Fable 5 token costs up to 70%
• Anthropic developer shares prompting tips for Fable 5 that focus on finding your own blind spots first
• A 26,000-student study shows AI's hidden learning cost takes two full years to surface