cs.HCOct 31, 2025

AURA: A Reinforcement Learning Framework for AI-Driven Adaptive Conversational Surveys

Authors: Jinwen Tang, Yi Shang

Organizations: University of Missouri, Department of Electrical Engineering and Computer Science, Columbia, MO, USA

Abstract

Conventional online surveys provide limited personalization, often resulting in low engagement and superficial responses. Although AI survey chatbots improve convenience, most are still reactive: they rely on fixed dialogue trees or static prompt templates and therefore cannot adapt within a session to fit individual users, which leads to generic follow-ups and weak response quality. We address these limitations with AURA (Adaptive Understanding through Reinforcement Learning for Assessment), a reinforcement learning framework for AI-driven adaptive conversational surveys. AURA quantifies response quality using a four-dimensional LSDE metric (Length, Self-disclosure, Emotion, and Specificity) and selects follow-up question types via an epsilon-greedy policy that updates the expected quality gain within each session. Initialized with priors extracted from 96 prior campus-climate conversations (467 total chatbot-user exchanges), the system balances exploration and exploitation across 10-15 dialogue exchanges, dynamically adapting to individual participants in real time. In controlled evaluations, AURA achieved a +0.076 mean gain in response quality and a statistically significant improvement over non-adaptive baselines (p=0.044, d=0.66), driven by a 63% reduction in specification prompts and a 10x increase in validation behavior. These results demonstrate that reinforcement learning can give survey chatbots improved adaptivity, transforming static questionnaires into interactive, self-improving assessment systems.

Figures & tables

Explore similar work

CardsList
  1. Towards Detecting AI-Assisted Responses in Online Surveys

    Sep 15, 2026Qizhou Wang, Bogdan Mamaev, Christopher LeckieAI-Generated Text Detection

  2. LLMs as survey respondents: Comparison to simple semantic baselines

    Oct 21, 2026Esko Lehtonen, Tommi Buder-GröndahlLarge Language Model-Based Data AugmentationLanguage Model Generation Evaluation

  3. SurveyWeave: An Agentic Framework for Automated Survey Generation

    Nov 14, 2026Franklin Zhang, Xiao Yang, Xin Luna Dong +1Autonomous Research Agents