# Adaptive Information Seeking for Open-Domain Question Answering

arXiv: https://arxiv.org/abs/2109.06747 · HTML: https://mlsanity.com/paper/2109.06747/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 40 references that are in the map.
- First posted on arXiv 14 Sep 2021.

## Builds on (most cited first, 26 of 26)

- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [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)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval](https://mlsanity.com/paper/2009.12756/) (2020)
- [Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering](https://mlsanity.com/paper/1911.10470/) (2019)
- [Keep CALM and Explore: Language Models for Action Generation in Text-based Games](https://mlsanity.com/paper/2010.02903/) (2020)
- [Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering](https://mlsanity.com/paper/1908.08167/) (2019)
- [Cognitive Graph for Multi-Hop Reading Comprehension at Scale](https://mlsanity.com/paper/1905.05460/) (2019)
- [Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval](https://mlsanity.com/paper/2101.00436/) (2021)
- [Answering Complex Open-domain Questions Through Iterative Query Generation](https://mlsanity.com/paper/1910.07000/) (2019)
- [Revealing the Importance of Semantic Retrieval for Machine Reading at Scale](https://mlsanity.com/paper/1909.08041/) (2019)
- [SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval](https://mlsanity.com/paper/2009.13013/) (2020)
- [Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering](https://mlsanity.com/paper/1905.05733/) (2019)
- [Differentiable Reasoning over a Virtual Knowledge Base](https://mlsanity.com/paper/2002.10640/) (2020)
- [Multi-Hop Paragraph Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/1906.06606/) (2019)
- [Ranking Paragraphs for Improving Answer Recall in Open-Domain Question Answering](https://mlsanity.com/paper/1810.00494/) (2018)
- [Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering](https://mlsanity.com/paper/1909.07598/) (2019)
- [HopRetriever: Retrieve Hops over Wikipedia to Answer Complex Questions](https://mlsanity.com/paper/2012.15534/) (2020)
- [Do Multi-hop Readers Dream of Reasoning Chains?](https://mlsanity.com/paper/1910.14520/) (2019)
- [HAS-QA: Hierarchical Answer Spans Model for Open-domain Question Answering](https://mlsanity.com/paper/1901.03866/) (2019)
- [Adaptive Information Gathering via Imitation Learning](https://mlsanity.com/paper/1705.07834/) (2017)

## Built on by (most cited first, 29 of 29)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models](https://mlsanity.com/paper/2405.14831/) (2024)
- [LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs](https://mlsanity.com/paper/2406.15319/) (2024)
- [Chain-of-Skills: A Configurable Model for Open-domain Question Answering](https://mlsanity.com/paper/2305.03130/) (2023)
- [ConTextual Masked Auto-Encoder for Dense Passage Retrieval](https://mlsanity.com/paper/2208.07670/) (2022)
- [Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge](https://mlsanity.com/paper/2210.12338/) (2022)
- [Interpretable AMR-Based Question Decomposition for Multi-hop Question Answering](https://mlsanity.com/paper/2206.08486/) (2022)
- [RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling](https://mlsanity.com/paper/2310.10567/) (2023)
- [Retrieval-Enhanced Machine Learning: Synthesis and Opportunities](https://mlsanity.com/paper/2407.12982/) (2024)
- [Match-Prompt: Improving Multi-task Generalization Ability for Neural Text Matching via Prompt Learning](https://mlsanity.com/paper/2204.02725/) (2022)
- [Capturing Global Structural Information in Long Document Question Answering with Compressive Graph Selector Network](https://mlsanity.com/paper/2210.05499/) (2022)
- [Query-as-context Pre-training for Dense Passage Retrieval](https://mlsanity.com/paper/2212.09598/) (2022)
- [Counterfactual Multihop QA: A Cause-Effect Approach for Reducing Disconnected Reasoning](https://mlsanity.com/paper/2210.07138/) (2022)
- [Zero-Shot Retrieval with Search Agents and Hybrid Environments](https://mlsanity.com/paper/2209.15469/) (2022)
- [Feedback-Aware Monte Carlo Tree Search for Efficient Information Seeking in Goal-Oriented Conversations](https://mlsanity.com/paper/2501.15056/) (2025)
- [CoT-MAE v2: Contextual Masked Auto-Encoder with Multi-view Modeling for Passage Retrieval](https://mlsanity.com/paper/2304.03158/) (2023)
- [Retrieval Oriented Masking Pre-training Language Model for Dense Passage Retrieval](https://mlsanity.com/paper/2210.15133/) (2022)
- [Performance Prediction for Multi-hop Questions](https://mlsanity.com/paper/2308.06431/) (2023)
- [Prompt-based Conservation Learning for Multi-hop Question Answering](https://mlsanity.com/paper/2209.06923/) (2022)
- [Challenging Decoder helps in Masked Auto-Encoder Pre-training for Dense Passage Retrieval](https://mlsanity.com/paper/2305.13197/) (2023)
- [Retrieval from Within: An Intrinsic Capability of Attention-Based Models](https://mlsanity.com/paper/2605.05806/) (2026)
- [LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback](https://mlsanity.com/paper/2204.11545/) (2022)
- [Cross-Model Comparative Loss for Enhancing Neuronal Utility in Language Understanding](https://mlsanity.com/paper/2301.03765/) (2023)
- [Momentum Posterior Regularization for Multi-hop Dense Retrieval](https://mlsanity.com/paper/2502.20399/) (2024)
- [Qsnail: A Questionnaire Dataset for Sequential Question Generation](https://mlsanity.com/paper/2402.14272/) (2024)
- [Fusing Knowledge and Language: A Comparative Study of Knowledge Graph-Based Question Answering with LLMs](https://mlsanity.com/paper/2509.09272/) (2025)
- [Gradually Excavating External Knowledge for Implicit Complex Question Answering](https://mlsanity.com/paper/2603.08148/) (2026)

## Abstract (arXiv)

Information seeking is an essential step for open-domain question answering to efficiently gather evidence from a large corpus. Recently, iterative approaches have been proven to be effective for complex questions, by recursively retrieving new evidence at each step. However, almost all existing iterative approaches use predefined strategies, either applying the same retrieval function multiple times or fixing the order of different retrieval functions, which cannot fulfill the diverse requirements of various questions. In this paper, we propose a novel adaptive information-seeking strategy for open-domain question answering, namely AISO. Specifically, the whole retrieval and answer process is modeled as a partially observed Markov decision process, where three types of retrieval operations (e.g., BM25, DPR, and hyperlink) and one answer operation are defined as actions. According to the learned policy, AISO could adaptively select a proper retrieval action to seek the missing evidence at each step, based on the collected evidence and the reformulated query, or directly output the answer when the evidence set is sufficient for the question. Experiments on SQuAD Open and HotpotQA fullwiki, which serve as single-hop and multi-hop open-domain QA benchmarks, show that AISO outperforms all baseline methods with predefined strategies in terms of both retrieval and answer evaluations.