Boosting Search Engines with Interactive Agents

TL;DR

This paper introduces interactive search agents that learn to refine queries iteratively using machine reading, synthetic search sessions, and reinforcement learning, achieving high-quality retrieval with transparent control.

Contribution

The paper presents a novel approach combining machine reading, synthetic session generation, and reinforcement learning to develop interpretable, effective search agents for iterative query refinement.

Findings

Agents achieve retrieval and answer quality comparable to neural methods.

Use of transformer-based models for synthetic session generation.

Effective reinforcement learning strategies for interactive search control.

Abstract

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.