mlsanityData to 14 Oct 2026

Evaluating Cognitive Age Alignment in Interactive AI Agents

arXiv 2605.17894 ↗First posted 18 May 2026cs.AIcited by 2

On the map: LLM reasoning → Reasoning benchmarks and evaluation

also in 2 more
Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 24 of its 58 references that are in the map. First posted on arXiv 18 May 2026.

Builds on

24 of 58 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Doing Things with Words: Rethinking Theory of Mind Simulation in Large Language Models15 Oct

Other references · 23

  1. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  2. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,919
  3. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
  4. 2023NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmarkcited by 348
  5. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactionscited by 254
  6. 2023Emergent autonomous scientific research capabilities of large language modelscited by 132
  7. 2025MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Researchcited by 64
  8. 2024What is the Visual Cognition Gap between Humans and Multimodal LLMs?cited by 30
  9. 2023Evidence of interrelated cognitive-like capabilities in large language models: Indications of artificial general intelligence or achievement?cited by 27
  10. 2023Working Memory Capacity of ChatGPT: An Empirical Studycited by 23
  11. 2023Comparing Machines and Children: Using Developmental Psychology Experiments to Assess the Strengths and Weaknesses of LaMDA Responsescited by 9
  12. 2025Do Psychometric Tests Work for Large Language Models? Evaluation of Tests on Sexism, Racism, and Moralitycited by 9
11 more
  1. 2025Safe-Child-LLM: A Developmental Benchmark for Evaluating LLM Safety in Child-LLM Interactionscited by 7
  2. 2026Toward Cognitive Supersensing in Multimodal Large Language Modelcited by 7
  3. 2024The Cognitive Capabilities of Generative AI: A Comparative Analysis with Human Benchmarkscited by 6
  4. 2024Benchmarking LLMs for Mimicking Child-Caregiver Language in Interactioncited by 6
  5. 2025Large Language Models as Psychological Simulators: A Methodological Guidecited by 6
  6. 2024Automatic Annotation of Grammaticality in Child-Caregiver Conversationscited by 5
  7. 2025Visual Large Language Models Exhibit Human-Level Cognitive Flexibility in the Wisconsin Card Sorting Testcited by 5
  8. 2025SproutBench: A Benchmark for Safe and Ethical Large Language Models for Youthcited by 5
  9. 2025Evaluating LLM Safety Across Child Development Stages: A Simulated Agent Approachcited by 3
  10. 2026Children's Intelligence Tests Pose Challenges for MLLMs? KidGym: A 2D Grid-Based Reasoning Benchmark for MLLMscited by 2
  11. 2025Beyond Benchmarks: LLM Evaluation with an Anthropomorphic and Lifecycle-oriented Roadmapcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Decoding Children's Gait Behaviorcited by 1
  2. 2026ChronoVision: Temporal Reasoning via Latent State Reconstructioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Evaluating Multimodal Large Language Models with Daily Composite Tasks in Home Environments
  2. 2026Uneven Evolution of Cognition Across Generations of Generative AI Models
  3. 2026The Age of Curiosity Meets the Age of AI: Benchmarking Child Safety in Large Language Models
  4. 2025The Philosophical Foundations of Growing AI Like A Child
  5. 2026LEVANTE-bench: Multi-Scale Comparison of VLMs to Children Using Cognitive Tasks (or, "Is Your VLM Smarter Than a 5th Grader?")
  6. 2026Can Large Language Models Simulate Human Cognition Beyond Behavioral Imitation?
  7. 2025Towards Aligning Multimodal LLMs with Human Experts: A Focus on Parent-Child Interaction
  8. 2026CogGym: Towards Large-Scale Comparative Evaluation of Human and Machine Cognition