Supporting Reflection in LLM-based Exploratory Search
2026-07-13 • Human-Computer Interaction
Human-Computer Interaction
AI summaryⓘ
The authors created TrailLM, a tool that helps people keep track of their search steps when looking for new information using large language models (LLMs). Instead of just giving quick answers, TrailLM shows users how their understanding changes and helps them think about their search process. This way, users can better reflect on their strategies and goals. The system aims to combine the speed of LLMs with more thoughtful exploration.
Large Language Modelsexploratory searchsensemakingmetacognitioninformation seekingsearch strategiesreflectionuser interfaceworkflow
Authors
Giulia Di Fede, Salvatore Andolina
Abstract
Large Language Models (LLMs) can make exploratory search more efficient but may undermine the reflection and iterative sensemaking needed in unfamiliar domains. Existing LLM tools often prioritize rapid answers over supporting users in tracking how their understanding evolves and how well their strategies align with their goals. We present TrailLM, a system that helps users reconstruct and revisit their exploration paths to support reflection and metacognitive engagement during information seeking. By aligning LLM assistance with users' sensemaking workflows, TrailLM aims to preserve the benefits of LLM-based search while enhancing opportunities for critical reflection on one's own search process.