HotpotQA

Dataset Card for BEIR Benchmark hotpotqa is one of the datasets from the Question Answering task within BEIR, measuring Wikipedia article retrieval for a given multi-hop query. Dataset Summary BEIR is a heterogeneous benchmark built from 18 diverse datasets representing 9 information retrieval tasks. Fact-checking: FEV

Papers using HotpotQA (29)

Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory2026Tool-Schema Compression Enables Agentic RAG Under Constrained Context Budgets2026KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents2024 · 4 citesCodeAgents: A Token-Efficient Framework for Codified Multi-Agent Reasoning in LLMs2025 · 4 citesBridge Evidence: Static Retrieval Utility Does Not Predict Causal Utility in Multi-Step Agentic Search2026Track, Rank, Crack: Epistemic Working Memory Scales Multi-Hop Reasoning in Language Agents2026MemPro: Agentic Memory Systems as Evolvable Programs2026Cascading Hallucination in Agentic RAG: The CHARM Framework for Detection and Mitigation2026AdaMEM: Test-Time Adaptive Memory for Language Agents2026Semantic Early-Stopping for Iterative LLM Agent Loops2026When Latent Agents Lie: KV-Cache Integrity in Multi-Agent LLM Collaboration2026Contrastive Reflection for Iterative Prompt Optimization2026ZEBRA: Zero-shot Budgeted Resource Allocation for LLM Orchestration2026Parallel Context Compaction for Long-Horizon LLM Agent Serving2026Proper Scoring Rules for Agentic Uncertainty Quantification2026Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-Wiki2026StepOPSD: Step-Aware Online Preference Distillation for Agent Reinforcement Learning2026Prompt Codebooks: Discrete Compositional Optimization for Language Model Instruction Refinement2026Critic-R: Improving Agentic Search using Instruction-tuned Retrievers with Natural Language Introspective Feedback2026Answer Only as Precisely as Justified: Calibrated Claim-Level Specificity Control for Agentic Systems2026GRASP: Graph Agentic Search over Propositions for Multi-hop Question Answering2026Decoupling Search from Reasoning: A Vendor-Agnostic Grounding Architecture for LLM Agents2026Scaling Multi-agent Systems: A Smart Middleware for Improving Agent Interactions2026MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents2026PseudoAct: Leveraging Pseudocode Synthesis for Flexible Planning and Action Control in Large Language Model Agents2026MAR:Multi-Agent Reflexion Improves Reasoning Abilities in LLMs2025Mission Impossible: Feedback-Guided Dynamic Interactive Planning for Improving Reasoning on LLMs2025DebFlow: Automating Agent Creation via Agent Debate2025Smurfs: Multi-agent System Using Context-efficient DFSDT For Tool Planning2024