Search-QA

We publicly release a new large-scale dataset, called SearchQA, for machine comprehension, or question-answering. Unlike recently released datasets, such as DeepMind CNN/DailyMail and SQuAD, the proposed SearchQA was constructed to reflect a full pipeline of general question-answering. That is, we start not from an exi

Papers using Search-QA (4)

LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents2026StepOPSD: Step-Aware Online Preference Distillation for Agent Reinforcement Learning2026SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization2026Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning2026