cs.AINov 11, 2026

Food Critic: An Agentic Visualization System for Auditable Restaurant-Safety Reasoning

Authors: Arleth Salinas, Ishrat Jahan Eliza, Valerio Pascucci

Organizations: University of Utah

Abstract

Generative AI agents are increasingly being embedded into visualization systems that can search data, invoke tools, summarize evidence, and produce recommendations. However, when agents rely solely on their own knowledge, the visualization problem is not only whether the agent provides a useful answer, but also whether users can inspect how that answer is grounded. We present Food Critic, an agentic visualization system for diners' restaurant decision support that integrates public health inspection records with crowd review data. The system grounds agents under three conditions: a database-only ReAct agent, a retrieval- augmented agent with access to food-safety regulations, and an ontology-guided agent that produces structured hypotheses and typed evidence. Food Critic externalizes the agent's reasoning within these groundings as inspectable visual evidence. We evaluate LLM models with several use cases under each grounding of our agentic system. Our work positions restaurant choice as a concrete case for studying human-agent collaboration, visual provenance of agent reasoning, and the design of visual interfaces for grounded GenAI decision support.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. OmniFood-Bench: Evaluating VLMs for Nutrient Reasoning and Personalized Health Advice

    Jul 9, 2026Qian Jiang, Zhecheng Shi, Jingpu Yang +2VLM EvaluationMedical VLMs

  2. Agent-as-a-Judge

    Nov 13, 2026Runyang You, Hongru Cai, Caiqi Zhang +5LLM-as-a-JudgeLLM Agent Evaluation