Evaluating Cognitive Age Alignment in Interactive AI Agents

Yifan Shen; Jiawen Zhang; Jian Xu; Junho Kim; Ismini Lourentzou; Xu Cao; Meihuan Huang

cs.AIMay 18, 2026

Evaluating Cognitive Age Alignment in Interactive AI Agents

Authors: Yifan Shen, Jiawen Zhang, Jian Xu, Junho Kim, Ismini Lourentzou, Xu Cao, Meihuan Huang

Organizations: 1PediaMed AI · University of Illinois Urbana-Champaign · 4Peking University · 3Shenzhen Children’s Hospital · 5Hong Kong Polytechnic University

Abstract

While agentic AI and its core multimodal large language models (MLLMs) have demonstrated remarkable promise in language and visual reasoning across domains ranging from daily life to advanced scientific research, a profound gap remains between artificial and human intelligence. Despite the integration of powerful tools and advanced MLLMs, state-of-the-art AI agents frequently fail at foundational, seemingly simple tasks that a child can resolve with ease. Inspired by the Wechsler Intelligence Scale for Children (WISC), we introduce ChildAgentEval, the first psychometrically grounded interactive benchmark for evaluating cognitive age alignment in MLLM-based agents. ChildAgentEval systematically compares the reasoning performance of various MLLM-based interactive agents against age-specific human developmental stages, exposing where current agentic AI systems can and cannot simulate age-specific cognitive behavior.

Explore similar work

The Age of Curiosity Meets the Age of AI: Benchmarking Child Safety in Large Language Models
May 25, 2026Samee Arif, Angana Borah, Rada MihalceaLarge Language Model Safety Age
LEVANTE-bench: Multi-Scale Comparison of VLMs to Children Using Cognitive Tasks (or, "Is Your VLM Smarter Than a 5th Grader?")
Jun 3, 2026Alvin Wei Ming Tan, David Cardinal, Tania Lorido-Botran +3Vision-Language Cognitive Science
PACE: A Proxy for Agentic Capability Evaluation
Jul 2, 2026Yueqi Song, Lintang Sutawika, Jiarui Liu +8Agentic Benchmarks Agentic Evaluations

May 25, 2026 · cs.CLJ/K move · Enter open · S save

The Age of Curiosity Meets the Age of AI: Benchmarking Child Safety in Large Language Models

Samee Arif, Angana Borah, Rada Mihalcea

University of Michigan

Children increasingly have access to Large Language Models (LLMs), which may expose them to responses that are developmentally inappropriate or require age-sensitive safety, guidance, and boundaries. Existing LLM safety evaluations largely focus on general harmful-content avoidance and do not explicitly target child-facing safety. We introduce KIDBench, a benchmark for evaluating child-facing LLM safety for ages 7-11 using a LLM-as-a-Judge rubric grounded in developmental-psychology. KIDBench contains realistic child queries across ten categories, with single-turn prompts and multi-turn child-actor simulations. We compare no-cues prompts with no child context, implicit-cues prompts that suggest a child speaker, and explicit age instructions. Implicit-cues improve scores by 8.6-46.8% over no-cue, while explicit age provides an additional 9.9-30.4% improvement over implicit-cues. Cross-lingual and cultural evaluations show uneven safety behavior across languages and country contexts. Multi-turn simulations show peak quality drops of up to 0.959 points on the 1-5 scale. We also introduce KIDGuardLlama, a child-safety evaluator, and KIDLlama, a child-safe response model. Code, data, and evaluation resources are available at https://github.com/MichiganNLP/kidbench.

Large Language Model Safety Age

Open paper Ask about it PDF

Abstract

Explore similar work

The Age of Curiosity Meets the Age of AI: Benchmarking Child Safety in Large Language Models

LEVANTE-bench: Multi-Scale Comparison of VLMs to Children Using Cognitive Tasks (or, "Is Your VLM Smarter Than a 5th Grader?")

PACE: A Proxy for Agentic Capability Evaluation