Boosting Search Engines with Interactive Agents

This paper presents first successful steps in designing agents that learn meta-strategies for iterative query refinement. 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. We obtain retrieval and answer quality performance comparable to recent neural methods using a traditional term-based BM25 ranking function. We provide an in-depth analysis of the search policies.