← all datasets

Xbench

Emerging

3papers using it

2025first seen

🔎 Find this dataset

Papers using Xbench (3)

LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent2026

Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL2025 · 1 cites

Planner-R1: Reward Shaping Enables Efficient Agentic RL with Smaller LLMs2025

Xbench — datasets — reinforcement-learning