DRBENCHER: Can Your Agent Identify the Entity, Retrieve Its Properties and Do the Math?

arXiv:2604.09251v1 Announce Type: new Abstract: Deep research agents increasingly interleave web browsing with multi-step computation, yet existing benchmarks evaluate these capabilities in isolation, creating a blind spot in assessing real-world performance. We introduce DRBENCHER, a synthetic benchmark generator for questions that require both browsing and computation. It enforces four criteria: verifiability (gold answers are computed by executing parameterized code over knowledge-graph value