multi-hop QA benchmarks

Multi-hop QA benchmarks are datasets used to evaluate the ability of models to answer questions that require reasoning over multiple pieces of evidence or information.

Papers using multi-hop QA benchmarks (6)

Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning2025Think Big, Search Small: Where Capacity Matters in Hierarchical Search Agents?2026Divide and Cooperate: Role-Decomposed Multi-Agent LLM Training with Cross-Agent Learning Signals2026Beyond Monolithic Architectures: A Multi-Agent Search and Knowledge Optimization Framework for Agentic Search2026Do Agents Need to Plan Step-by-Step? Rethinking Planning Horizon in Data-Centric Tool Calling2026StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning2026