← all datasets

xbench-DeepSearch

Emerging
6papers using it
2025first seen

'XBench-DeepSearch' is a benchmark dataset that contains complex question-answer pairs generated from authentic web sources, used to evaluate the deep reasoning capabilities of multi-turn agents in long-horizon interactions.

Papers using xbench-DeepSearch (6)

xbench-DeepSearch β€” datasets β€” ai-agents