# Researchy Questions: A Dataset of Multi-Perspective, Decompositional Questions for LLM Web Agents

arXiv: https://arxiv.org/abs/2402.17896 · HTML: https://mlsanity.com/paper/2402.17896/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 36 of its 59 references that are in the map.
- First posted on arXiv 27 Feb 2024.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 30 of 36)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [ELI5: Long Form Question Answering](https://mlsanity.com/paper/1907.09190/) (2019)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis](https://mlsanity.com/paper/2307.12856/) (2023)
- [Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy](https://mlsanity.com/paper/2305.15294/) (2023)
- [Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP](https://mlsanity.com/paper/2212.14024/) (2022)
- [Evaluating Verifiability in Generative Search Engines](https://mlsanity.com/paper/2304.09848/) (2023)
- [HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data](https://mlsanity.com/paper/2004.07347/) (2020)
- [SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine](https://mlsanity.com/paper/1704.05179/) (2017)
- [Don't Make Your LLM an Evaluation Benchmark Cheater](https://mlsanity.com/paper/2311.01964/) (2023)
- [RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking](https://mlsanity.com/paper/2110.07367/) (2021)

## Built on by (most cited first, 23 of 23)

- [Evaluation of Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2405.07437/) (2024)
- [A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges](https://mlsanity.com/paper/2508.05668/) (2025)
- [WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research](https://mlsanity.com/paper/2509.13312/) (2025)
- [Ragnar"ok: A Reusable RAG Framework and Baselines for TREC 2024 Retrieval-Augmented Generation Track](https://mlsanity.com/paper/2406.16828/) (2024)
- [Initial Nugget Evaluation Results for the TREC 2024 RAG Track with the AutoNuggetizer Framework](https://mlsanity.com/paper/2411.09607/) (2024)
- [FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents](https://mlsanity.com/paper/2504.13128/) (2025)
- [Support Evaluation for the TREC 2024 RAG Track: Comparing Human versus LLM Judges](https://mlsanity.com/paper/2504.15205/) (2025)
- [ResearchArena: Benchmarking Large Language Models' Ability to Collect and Organize Information as Research Agents](https://mlsanity.com/paper/2406.10291/) (2024)
- [APTBench: Benchmarking Agentic Potential of Base LLMs During Pre-Training](https://mlsanity.com/paper/2510.24397/) (2025)
- [An Adversary-Resistant Multi-Agent LLM System via Credibility Scoring](https://mlsanity.com/paper/2505.24239/) (2025)
- [Do RAG Systems Cover What Matters? Evaluating and Optimizing Responses with Sub-Question Coverage](https://mlsanity.com/paper/2410.15531/) (2024)
- [Query Decomposition for RAG: Balancing Exploration-Exploitation](https://mlsanity.com/paper/2510.18633/) (2025)
- [A Vision for Geo-Temporal Deep Research Systems: Towards Comprehensive, Transparent, and Reproducible Geo-Temporal Information Synthesis](https://mlsanity.com/paper/2506.14345/) (2025)
- [Incorporating Q&A Nuggets into Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.13222/) (2026)
- [AgentDisCo: Towards Disentanglement and Collaboration in Open-ended Deep Research Agents](https://mlsanity.com/paper/2605.11732/) (2026)
- [DoGMaTiQ: Automated Generation of Question-and-Answer Nuggets for Report Evaluation](https://mlsanity.com/paper/2605.04458/) (2026)
- [Relational Priors as Convergence Pressure in LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2608.03239/) (2026)
- [Benchmarking LLM Serving Systems for Agentic AI Workloads with XPerf](https://mlsanity.com/paper/2608.20370/) (2026)
- [Document Quality Scoring for Web Crawling](https://mlsanity.com/paper/2504.11011/) (2025)
- [Magic, Madness, Heaven, Sin: LLM Output Diversity is Everything, Everywhere, All at Once](https://mlsanity.com/paper/2604.01504/) (2026)
- [An Interactive Paradigm for Deep Research](https://mlsanity.com/paper/2605.24266/) (2026)
- [Not Worth Another Token: Marginal Value Estimation for Efficient Deep Research Agents](https://mlsanity.com/paper/2608.08389/) (2026)
- [Benchmarking and Training Reward Models for Cross-Source Evidence Grounding in Search Agents](https://mlsanity.com/paper/2610.17827/) (2026)

## Abstract (arXiv)

Existing question answering (QA) datasets are no longer challenging to most powerful Large Language Models (LLMs). Traditional QA benchmarks like TriviaQA, NaturalQuestions, ELI5 and HotpotQA mainly study ``known unknowns'' with clear indications of both what information is missing, and how to find it to answer the question. Hence, good performance on these benchmarks provides a false sense of security. A yet unmet need of the NLP community is a bank of non-factoid, multi-perspective questions involving a great deal of unclear information needs, i.e. ``unknown uknowns''. We claim we can find such questions in search engine logs, which is surprising because most question-intent queries are indeed factoid. We present Researchy Questions, a dataset of search engine queries tediously filtered to be non-factoid, ``decompositional'' and multi-perspective. We show that users spend a lot of ``effort'' on these questions in terms of signals like clicks and session length, and that they are also challenging for GPT-4. We also show that ``slow thinking'' answering techniques, like decomposition into sub-questions shows benefit over answering directly. We release ~ 100k Researchy Questions, along with the Clueweb22 URLs that were clicked.