Enhancing Mobile "How-to" Queries with Automated Search Results Verification and Reranking
Lei Ding, Jeshwanth Bheemanpally, Yi Zhang
TL;DR
This work tackles the reliability gap in How-to search results by introducing an automated verification and reranking pipeline that tests on-device executable instructions. The authors implement a three-stage system (instruction extraction, on-device verification, and reranking) within the MagicWand platform and the How-to WeWeb dataset, achieving substantial improvements over a Google baseline. Key contributions include zero-shot instruction extraction with grounding, an on-device action agent, and neural reranking models that integrate execution feedback. The approach promises more accurate, personalized, and scalable online technical support for mobile devices and motivates cross-platform extensions and richer data collection in the future.
Abstract
Many people use search engines to find online guidance to solve computer or mobile device problems. Users frequently encounter challenges in identifying effective solutions from search results, often wasting time trying ineffective solutions that seem relevant yet fail to solve real problems. This paper introduces a novel approach to improving the accuracy and relevance of online technical support search results through automated search results verification and reranking. Taking "How-to" queries specific to on-device execution as a starting point, we developed the first solution that allows an AI agent to interpret and execute step-by-step instructions in the search results in a controlled Android environment. We further integrated the agent's findings into a reranking mechanism that orders search results based on the success indicators of the tested solutions. The paper details the architecture of our solution and a comprehensive evaluation of the system through a series of tests across various application domains. The results demonstrate a significant improvement in the quality and reliability of the top-ranked results. Our findings suggest a paradigm shift in how search engine ranking for online technical support help can be optimized, offering a scalable and automated solution to the pervasive challenge of finding effective and reliable online help.