Boosting Search Engines with Interactive Agents

By Leonard Adolphs, Benjamin Boerschinger, Christian Buck, Michelle Chen Huebscher, Massimiliano Ciaramita, Lasse Espeholt, Thomas Hofmann, Yannic Kilcher. 2021

24 citations recorded by the source corpus.

This paper presents first successful steps in designing search agents that learn meta-strategies for iterative query refinement in information-seeking tasks. Our approach uses machine reading to guide the selection of refinement terms from aggregated search results. Agents are then empowered with simple but effective search operators to exert fine-grained and transparent control over queries and search results. We develop a novel way of generating synthetic search sessions, which leverages the power of transformer-based language models through (self-)supervised learning. We also present a reinforcement learning agent with dynamically constrained actions that learns interactive search strategies from scratch. Our search agents obtain retrieval and answer quality performance comparable to recent neural methods, using only a traditional term-based BM25 ranking function and interpretable discrete reranking and filtering actions.

Subfields: Natural Language Processing, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

In Reinforcement Learning

Citations in the corpus

Augmented Language Models: a Survey (2023, background): “While there are early works focused on models that could interface with external tools, they employ ad-hoc tool-dependent architectures (Adolphs et al., 2022; Buck et al., 2018; Nogueira and Cho, 2017; Zhong et al., 2018).”
Internet-augmented language models through few-shot prompting for open-domain question answering (2022, background): “1, the complexity of certain (multi-hop) questions pose problems to this simple approach, calling for more sophisticated learning to search approaches (Adolphs et al., 2021; Komeili et al., 2021; Nakano et al., 2021).”
WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents (2022, background): “Several papers have explored the use of the web for information extraction [34] and retrieval [1], question answering [57, 25], dialog [45], and training language models on webtext [2].”
Reason first, then respond: Modular Generation for Knowledge-infused Dialogue (2021, methodology): “In reinforcement learning settings, generating natural language has been used as an intermediate planning step (Sharma et al., 2021; Hu et al., 2019), and in particular in goal-oriented dialogue (Yarats and Lewis, 2018) and open-domain QA (Adolphs et al., 2021) as well.”
Understanding HTML with Large Language Models (2022, background): “…websites for training web-based agents, with application to task fulﬁllment (Yao et al., 2022; Gur et al., 2021; Burns et al., 2022; Mazumder and Riva, 2020; Shi et al., 2017; Liu et al., 2018) as well as information retrieval or question-answering (Adolphs et al., 2021; Nogueira and Cho, 2016).”
A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis (2023, background): “…decision making task where agents manipulate browsers following given instructions (Shi et al., 2017), such as form filling (Diaz et al., 2013) or information retrieval (Adolphs et al., 2022) through the sequence of computer actions (Li et al., 2020; Mazumder & Riva, 2020; Shvo et al., 2021).”
CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning (2021, methodology): “RL-based QR for Retrieval Nogueira and Cho (2017) and Adolphs et al. (2021) apply RL based on gold passage labels to do non-conversational query reformulation for retrieval.”